diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..3c09653d086d8a4eb54b14318d6ffbb0cb64c716 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +checkpoint-14/tokenizer.json filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..0c51bf4c1f5eeaeff98724ce3d93de5c5deafe57 --- /dev/null +++ b/README.md @@ -0,0 +1,61 @@ +--- +license: other +base_model: google/paligemma-3b-mix-448 +tags: +- llama-factory +- full +- generated_from_trainer +model-index: +- name: paligemma-3b-wat2024-chat-v0.2 + results: [] +--- + + + +[Visualize in Weights & Biases](https://wandb.ai/sambitsekharai/huggingface/runs/2lpuvwid) +# paligemma-3b-wat2024-chat-v0.2 + +This model is a fine-tuned version of [google/paligemma-3b-mix-448](https://huggingface.co/google/paligemma-3b-mix-448) on the llava_wat dataset. + +## Model description + +More information needed + +## Intended uses & limitations + +More information needed + +## Training and evaluation data + +More information needed + +## Training procedure + +### Training hyperparameters + +The following hyperparameters were used during training: +- learning_rate: 3e-06 +- train_batch_size: 1 +- eval_batch_size: 8 +- seed: 42 +- distributed_type: multi-GPU +- num_devices: 8 +- gradient_accumulation_steps: 16 +- total_train_batch_size: 128 +- total_eval_batch_size: 64 +- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 +- lr_scheduler_type: cosine +- lr_scheduler_warmup_steps: 50 +- num_epochs: 2.0 + +### Training results + + + +### Framework versions + +- Transformers 4.43.2 +- Pytorch 2.1.2+git70dfd51 +- Datasets 2.19.1 +- Tokenizers 0.19.1 diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..ff9246e420971b10c510b39a0de289132c2bf23f --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,3 @@ +{ + "": 257152 +} diff --git a/all_results.json b/all_results.json new file mode 100644 index 0000000000000000000000000000000000000000..129ba325cf722334de02751dea62be7e1cf2335a --- /dev/null +++ b/all_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 1.792, + "total_flos": 30998735618048.0, + "train_loss": 4.085959434509277, + "train_runtime": 5425.5762, + "train_samples_per_second": 0.367, + "train_steps_per_second": 0.003 +} \ No newline at end of file diff --git a/checkpoint-14/added_tokens.json b/checkpoint-14/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..ff9246e420971b10c510b39a0de289132c2bf23f --- /dev/null +++ b/checkpoint-14/added_tokens.json @@ -0,0 +1,3 @@ +{ + "": 257152 +} diff --git a/checkpoint-14/config.json b/checkpoint-14/config.json new file mode 100644 index 0000000000000000000000000000000000000000..619f881de9074b0e079b7cd1ab483a2eabff9707 --- /dev/null +++ b/checkpoint-14/config.json @@ -0,0 +1,41 @@ +{ + "_name_or_path": "google/paligemma-3b-mix-448", + "architectures": [ + "PaliGemmaForConditionalGeneration" + ], + "bos_token_id": 2, + "eos_token_id": 1, + "hidden_size": 2048, + "ignore_index": -100, + "image_token_index": 257152, + "model_type": "paligemma", + "pad_token_id": 0, + "projection_dim": 2048, + "text_config": { + "hidden_size": 2048, + "intermediate_size": 16384, + "model_type": "gemma", + "num_attention_heads": 8, + "num_hidden_layers": 18, + "num_image_tokens": 1024, + "num_key_value_heads": 1, + "torch_dtype": "float32", + "vocab_size": 257216 + }, + "torch_dtype": "bfloat16", + "transformers_version": "4.43.2", + "use_cache": false, + "vision_config": { + "hidden_size": 1152, + "image_size": 448, + "intermediate_size": 4304, + "model_type": "siglip_vision_model", + "num_attention_heads": 16, + "num_hidden_layers": 27, + "num_image_tokens": 1024, + "patch_size": 14, + "projection_dim": 2048, + "projector_hidden_act": "gelu_fast", + "vision_use_head": false + } +} diff --git a/checkpoint-14/generation_config.json b/checkpoint-14/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..cd9e5e9d63f83590138b0318869731ac7a2f5246 --- /dev/null +++ b/checkpoint-14/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 2, + "eos_token_id": 1, + "pad_token_id": 0, + "transformers_version": "4.43.2" +} diff --git a/checkpoint-14/global_step14/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/checkpoint-14/global_step14/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7a455f3284e1567a5f5398b9f36b38d10dc7b9ae --- /dev/null +++ b/checkpoint-14/global_step14/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e05a1de7d699fe8e2713759f43db02496d88143fa4a789939c99f10434598a29 +size 3766541296 diff --git a/checkpoint-14/global_step14/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/checkpoint-14/global_step14/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a0e47d1a7ec165cdade501702524139ae4dc5297 --- /dev/null +++ b/checkpoint-14/global_step14/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:815286c73d31a0a37d939360df105cdac4fcd4f7cdd4ed014674b653954b2231 +size 3766541296 diff --git a/checkpoint-14/global_step14/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/checkpoint-14/global_step14/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..541111ff092441770abcbfcbdc3b054a74040075 --- /dev/null +++ b/checkpoint-14/global_step14/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:111660e54eb4a5bd3ffb986032144c3e0535729766f49dce70fa79ace87060e2 +size 3766541296 diff --git a/checkpoint-14/global_step14/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/checkpoint-14/global_step14/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4068d6d17094077f638c36d9d8b61d6eed07e392 --- /dev/null +++ b/checkpoint-14/global_step14/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b78941bccc76f796d06daf157dda73211161157775edc296f0403066e0186028 +size 3766541296 diff --git a/checkpoint-14/global_step14/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt b/checkpoint-14/global_step14/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..06ca92080ec17cd65b2a69e261eae9237c123121 --- /dev/null +++ b/checkpoint-14/global_step14/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:201d25de0d816cf2d94cd485b7dfbb26505646898920e65b6d38b937c145dd81 +size 3766541296 diff --git a/checkpoint-14/global_step14/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt b/checkpoint-14/global_step14/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2983a8d03a8654a151e34e7d86ef400b88d69c7e --- /dev/null +++ b/checkpoint-14/global_step14/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fd69173e242717c8bb3840b8ae7d91c02f6971324d2c716da983bb779bbe3f6 +size 3766541296 diff --git a/checkpoint-14/global_step14/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt b/checkpoint-14/global_step14/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..66c172e2b7279862284ff2d5c162fd40ffca25b5 --- /dev/null +++ b/checkpoint-14/global_step14/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:464c7b81c7ab8471940671a95a84153743a08f712f6d32a7a84c797c4515776c +size 3766541296 diff --git a/checkpoint-14/global_step14/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt b/checkpoint-14/global_step14/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..340909ba91f4f44dff4edfd860a72c33a7dfec36 --- /dev/null +++ b/checkpoint-14/global_step14/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45d3fed049feeac74a869b8221d3d4666a04efd7512d8e854670cf2f393a8cfb +size 3766541296 diff --git a/checkpoint-14/global_step14/zero_pp_rank_0_mp_rank_00_model_states.pt b/checkpoint-14/global_step14/zero_pp_rank_0_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7135a062eabcf61a753299800fc461488ef4149c --- /dev/null +++ b/checkpoint-14/global_step14/zero_pp_rank_0_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e19a2a1b0f57e72ee5c16112f8c65c822417d410bd24c9e7c191f1c4b77e0bdd +size 103801126 diff --git a/checkpoint-14/global_step14/zero_pp_rank_1_mp_rank_00_model_states.pt b/checkpoint-14/global_step14/zero_pp_rank_1_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0bff083c6d7c6f7bf03e24e404208d5b081f68ff --- /dev/null +++ b/checkpoint-14/global_step14/zero_pp_rank_1_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56e08e7fb5b87b5e123b8fb5e20497c73f3687a68adb6ac1ccebfc5a1655ce29 +size 103801062 diff --git a/checkpoint-14/global_step14/zero_pp_rank_2_mp_rank_00_model_states.pt b/checkpoint-14/global_step14/zero_pp_rank_2_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c83de6525756325d83c997ef09dd6d4a9461de61 --- /dev/null +++ b/checkpoint-14/global_step14/zero_pp_rank_2_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75c00069d119d464ffeb0e59734b01307b55dcf75cd4050bda8f4f1deba05486 +size 103801062 diff --git a/checkpoint-14/global_step14/zero_pp_rank_3_mp_rank_00_model_states.pt b/checkpoint-14/global_step14/zero_pp_rank_3_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b1ddb52c7471469c5fa22c989a0b45d670a8fbea --- /dev/null +++ b/checkpoint-14/global_step14/zero_pp_rank_3_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74d9bbf9e887c0d55b2c122a701750bdf295850db458095fe227190e05c64fb9 +size 103801062 diff --git a/checkpoint-14/global_step14/zero_pp_rank_4_mp_rank_00_model_states.pt b/checkpoint-14/global_step14/zero_pp_rank_4_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0b8086a637dd16b0f59661ba1cc5c91e1b6febc4 --- /dev/null +++ b/checkpoint-14/global_step14/zero_pp_rank_4_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c70f1192e60fdc895bd3ae0683eed38e67cd27f5b550a6826eaf9fa66b1b5ae +size 103801062 diff --git a/checkpoint-14/global_step14/zero_pp_rank_5_mp_rank_00_model_states.pt b/checkpoint-14/global_step14/zero_pp_rank_5_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5d2816626de3d5c577b8867c4271551650bc3830 --- /dev/null +++ b/checkpoint-14/global_step14/zero_pp_rank_5_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c353b8d756ec30450499184dddc67c920362ea0f5e87cb4ced02d6824e8f7b8 +size 103801062 diff --git a/checkpoint-14/global_step14/zero_pp_rank_6_mp_rank_00_model_states.pt b/checkpoint-14/global_step14/zero_pp_rank_6_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..71436882db952a131994a391e4150ddd66129e9a --- /dev/null +++ b/checkpoint-14/global_step14/zero_pp_rank_6_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6881551b611176cae669db41c08d37db274024acdd445e2099256d103d57ac4c +size 103801062 diff --git a/checkpoint-14/global_step14/zero_pp_rank_7_mp_rank_00_model_states.pt b/checkpoint-14/global_step14/zero_pp_rank_7_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7d9522ff7752e20092d4be4f13af804b7b575082 --- /dev/null +++ b/checkpoint-14/global_step14/zero_pp_rank_7_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:225e58d3aed8425ef4fe4dc9cd9a018fccaa1c768bf20cc8f5aa9fbb5aa6b0ad +size 103801062 diff --git a/checkpoint-14/latest b/checkpoint-14/latest new file mode 100644 index 0000000000000000000000000000000000000000..0702eb07832ff8d8b5e215fcdd222f6e610eb766 --- /dev/null +++ b/checkpoint-14/latest @@ -0,0 +1 @@ +global_step14 \ No newline at end of file diff --git a/checkpoint-14/model-00001-of-00002.safetensors b/checkpoint-14/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..970ed290903547c40f13d9c68aeae62dac179017 --- /dev/null +++ b/checkpoint-14/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d93d6361131fcfcc325a52d685ca20912773f8bd1e870cc453dba3b8a700cad +size 4986813864 diff --git a/checkpoint-14/model-00002-of-00002.safetensors b/checkpoint-14/model-00002-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5140f5ae7cfc6b5128d85a9bd3204b1a633c1de4 --- /dev/null +++ b/checkpoint-14/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a26171508c249e90b06be1147d47e75e7cac50d289092b0d61f9839c611a536 +size 861970608 diff --git a/checkpoint-14/model.safetensors.index.json b/checkpoint-14/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..b8c76b58234e80cb23768096869fb3a0dc5a15a4 --- /dev/null +++ b/checkpoint-14/model.safetensors.index.json @@ -0,0 +1,610 @@ +{ + "metadata": { + "total_size": 5848702432 + }, + "weight_map": { + "language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.norm.weight": "model-00002-of-00002.safetensors", + "multi_modal_projector.linear.bias": "model-00001-of-00002.safetensors", + "multi_modal_projector.linear.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors" + } +} diff --git a/checkpoint-14/preprocessor_config.json b/checkpoint-14/preprocessor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..77bc692dcae67acc343539d9f0659d7de3c302b1 --- /dev/null +++ b/checkpoint-14/preprocessor_config.json @@ -0,0 +1,25 @@ +{ + "do_convert_rgb": null, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_processor_type": "SiglipImageProcessor", + "image_seq_length": 1024, + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "processor_class": "PaliGemmaProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "size": { + "height": 448, + "width": 448 + } +} diff --git a/checkpoint-14/rng_state_0.pth b/checkpoint-14/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..b346349ce12dd5a17d4b91ed2a5722bb52550950 --- /dev/null +++ b/checkpoint-14/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad8a35afd8967cbb748405387e44426e43ad127028e826eddc9b67d2ca873c85 +size 15984 diff --git a/checkpoint-14/rng_state_1.pth b/checkpoint-14/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..68f3c6994456cb8d0592a5375d99503c8924b1c4 --- /dev/null +++ b/checkpoint-14/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f338ce80d7c441076bfc8c53b84067a0181f5a14e80c13d5acb8150b659f4d73 +size 15984 diff --git a/checkpoint-14/rng_state_2.pth b/checkpoint-14/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..be044f6ceeed587d30e80c2f72d5aa19fdc9947b --- /dev/null +++ b/checkpoint-14/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9fbc9fa428939be10b46779f0eb5cd833e0da426b1cbdee77b3a55b6952235b +size 15984 diff --git a/checkpoint-14/rng_state_3.pth b/checkpoint-14/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..fc825249656a9b858782542bd3f4386250f1dfe0 --- /dev/null +++ b/checkpoint-14/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac55dba0b79d5fa4699d239da2f966d52040d576d31234ac8d4632e6956481bc +size 15984 diff --git a/checkpoint-14/rng_state_4.pth b/checkpoint-14/rng_state_4.pth new file mode 100644 index 0000000000000000000000000000000000000000..d30f52a44be563c152ae09db6ae934da6da0d3ed --- /dev/null +++ b/checkpoint-14/rng_state_4.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af2d0c015100768ffa23faf3b6c2d54ea89eb045603e30e55cd211e06ff34972 +size 15984 diff --git a/checkpoint-14/rng_state_5.pth b/checkpoint-14/rng_state_5.pth new file mode 100644 index 0000000000000000000000000000000000000000..c8715d27ab23ae545d58039cf949cc44ecc1da5e --- /dev/null +++ b/checkpoint-14/rng_state_5.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c60a1b40608e34bc801c8231f97b81c53b5290dfaed1b9cd0ccbeca29574a991 +size 15984 diff --git a/checkpoint-14/rng_state_6.pth b/checkpoint-14/rng_state_6.pth new file mode 100644 index 0000000000000000000000000000000000000000..1ed791b6ef76eadf0b0c55a5733411771e2ae027 --- /dev/null +++ b/checkpoint-14/rng_state_6.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ad6a142a403eb9aafc4a3a9a856bca648fe31fd22d796867baca31fb13656aa +size 15984 diff --git a/checkpoint-14/rng_state_7.pth b/checkpoint-14/rng_state_7.pth new file mode 100644 index 0000000000000000000000000000000000000000..800c3bbbc5edf7db01a8316069d439c5fb8d8c30 --- /dev/null +++ b/checkpoint-14/rng_state_7.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38bc23a138cc800b22881742c0f3f9a71731a9a7111c6058a0077e6274d21773 +size 15984 diff --git a/checkpoint-14/scheduler.pt b/checkpoint-14/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..327ebfd5c8a190d5c3b164efbb321a4dfaaa29ee --- /dev/null +++ b/checkpoint-14/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25b1118bb09e79f576cd19e7e434d4b3dd93335179a1bdb34803ce2d8e45cbd7 +size 1064 diff --git a/checkpoint-14/special_tokens_map.json b/checkpoint-14/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..0c18fdd94629ea652e2ef36ed9a422474ad0a8e8 --- /dev/null +++ b/checkpoint-14/special_tokens_map.json @@ -0,0 +1,33 @@ +{ + "additional_special_tokens": [ + "" + ], + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-14/tokenizer.json b/checkpoint-14/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..419d3c8c8da378e1f551d4348a5c2ca7616153d6 --- /dev/null +++ b/checkpoint-14/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef6773c135b77b834de1d13c75a4c98ab7a3684ffd602d1831e1f1bf5467c563 +size 17549604 diff --git a/checkpoint-14/tokenizer.model b/checkpoint-14/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..22ad048d392b4f5191be7cec47d03eb3cdb360f4 --- /dev/null +++ b/checkpoint-14/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8986bb4f423f07f8c7f70d0dbe3526fb2316056c17bae71b1ea975e77a168fc6 +size 4264023 diff --git a/checkpoint-14/tokenizer_config.json b/checkpoint-14/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1e9ef9c0ee5e46d701a6b082c1d28bd63d9c406c --- /dev/null +++ b/checkpoint-14/tokenizer_config.json @@ -0,0 +1,1767 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "4": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "5": { + "content": "<2mass>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "6": { + "content": "[@BOS@]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "7": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "8": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "9": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "10": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "11": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "12": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "13": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "14": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "15": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "16": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "17": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "18": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "19": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "20": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "21": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "22": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "23": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "24": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "25": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "26": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "27": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "28": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "29": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "30": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "31": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "32": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "33": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "34": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "35": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "36": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "37": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "38": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "39": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "40": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "41": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "42": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "43": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "44": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "45": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "46": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "47": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "48": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "49": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "50": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "51": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "52": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "53": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "54": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "55": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "56": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "57": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "58": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "59": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "60": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "61": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "62": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "63": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "64": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "65": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "66": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "67": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "68": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "69": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "70": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "71": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "72": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "73": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "74": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "75": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "76": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "77": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "78": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "79": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "80": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "81": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "82": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "83": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "84": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "85": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "86": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "87": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "88": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "89": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "90": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "91": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "92": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "93": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "94": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "95": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "96": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "97": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "98": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "99": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "100": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "101": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "102": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "103": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "104": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "105": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "106": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "107": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "108": { + "content": "\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "109": { + "content": "\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "110": { + "content": "\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "111": { + "content": "\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "112": { + "content": "\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "113": { + "content": "\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "114": { + "content": "\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "115": { + "content": "\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "116": { + "content": "\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "117": { + "content": "\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "118": { + "content": "\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "119": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "120": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "121": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "122": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "123": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "124": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "125": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "126": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "127": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "128": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "129": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "130": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "131": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "132": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "133": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "134": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "135": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "136": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "137": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "138": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "139": { + "content": "▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "140": { + "content": "▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "141": { + "content": "▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "142": { + "content": "▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "143": { + "content": "▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "144": { + "content": "▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "145": { + "content": "▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "146": { + "content": "▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "147": { + "content": "▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "148": { + "content": "▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "149": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "150": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "151": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "152": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "153": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "154": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "155": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "156": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "157": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "158": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "159": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "160": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "161": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "162": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "163": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "164": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "165": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "166": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "167": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "168": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "169": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "170": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "172": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "173": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "174": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "175": { + "content": "
", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "171": { + "content": "
", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "176": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "177": { + "content": "
", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "178": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "179": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "180": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "181": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "182": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "183": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "184": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "185": { + "content": "

", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "186": { + "content": "

", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "187": { + "content": "

", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "188": { + "content": "

", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "189": { + "content": "

", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "190": { + "content": "
", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "191": { + "content": "
", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "192": { + "content": "
", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "193": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "194": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "195": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "196": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "197": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "198": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "199": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "200": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "201": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "202": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "203": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "204": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "205": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "206": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "207": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "208": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "209": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "210": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "211": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "212": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "213": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "214": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "215": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "216": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "257152": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "" + ], + "bos_token": "", + "chat_template": "{{ '' }}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'user\n' + content + '\nmodel\n' }}{% elif message['role'] == 'assistant' %}{{ content + '\n' }}{% endif %}{% endfor %}", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "padding_side": "right", + "processor_class": "PaliGemmaProcessor", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "split_special_tokens": false, + "tokenizer_class": "GemmaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +} diff --git a/checkpoint-14/trainer_state.json b/checkpoint-14/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..e8ff1e536ca1abd01cde8c08d5b24f1f75992299 --- /dev/null +++ b/checkpoint-14/trainer_state.json @@ -0,0 +1,40 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.792, + "eval_steps": 500, + "global_step": 14, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 1.28, + "grad_norm": 57.92857011087701, + "learning_rate": 6.000000000000001e-07, + "loss": 4.1132, + "step": 10 + } + ], + "logging_steps": 10, + "max_steps": 14, + "num_input_tokens_seen": 0, + "num_train_epochs": 2, + "save_steps": 1000, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 30998735618048.0, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-14/training_args.bin b/checkpoint-14/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..23871f43017492e1ff53bd1aad5cdcf2736e6c10 --- /dev/null +++ b/checkpoint-14/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7eb5a4ebca2ac9e22067c1b25b0f7ba346c7d449e69982a206be438bdee2d84 +size 7096 diff --git a/checkpoint-14/zero_to_fp32.py b/checkpoint-14/zero_to_fp32.py new file mode 100644 index 0000000000000000000000000000000000000000..24cc342e78d1a006c782b3a4cd68d9ce786d8fd8 --- /dev/null +++ b/checkpoint-14/zero_to_fp32.py @@ -0,0 +1,604 @@ +#!/usr/bin/env python + +# Copyright (c) Microsoft Corporation. +# SPDX-License-Identifier: Apache-2.0 + +# DeepSpeed Team + +# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets +# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in +# the future. Once extracted, the weights don't require DeepSpeed and can be used in any +# application. +# +# example: python zero_to_fp32.py . pytorch_model.bin + +import argparse +import torch +import glob +import math +import os +import re +from collections import OrderedDict +from dataclasses import dataclass + +# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with +# DeepSpeed data structures it has to be available in the current python environment. +from deepspeed.utils import logger +from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS, + FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES, + FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS) + + +@dataclass +class zero_model_state: + buffers: dict() + param_shapes: dict() + shared_params: list + ds_version: int + frozen_param_shapes: dict() + frozen_param_fragments: dict() + + +debug = 0 + +# load to cpu +device = torch.device('cpu') + + +def atoi(text): + return int(text) if text.isdigit() else text + + +def natural_keys(text): + ''' + alist.sort(key=natural_keys) sorts in human order + http://nedbatchelder.com/blog/200712/human_sorting.html + (See Toothy's implementation in the comments) + ''' + return [atoi(c) for c in re.split(r'(\d+)', text)] + + +def get_model_state_file(checkpoint_dir, zero_stage): + if not os.path.isdir(checkpoint_dir): + raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist") + + # there should be only one file + if zero_stage <= 2: + file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt") + elif zero_stage == 3: + file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt") + + if not os.path.exists(file): + raise FileNotFoundError(f"can't find model states file at '{file}'") + + return file + + +def get_checkpoint_files(checkpoint_dir, glob_pattern): + # XXX: need to test that this simple glob rule works for multi-node setup too + ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys) + + if len(ckpt_files) == 0: + raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'") + + return ckpt_files + + +def get_optim_files(checkpoint_dir): + return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt") + + +def get_model_state_files(checkpoint_dir): + return get_checkpoint_files(checkpoint_dir, "*_model_states.pt") + + +def parse_model_states(files): + zero_model_states = [] + for file in files: + state_dict = torch.load(file, map_location=device) + + if BUFFER_NAMES not in state_dict: + raise ValueError(f"{file} is not a model state checkpoint") + buffer_names = state_dict[BUFFER_NAMES] + if debug: + print("Found buffers:", buffer_names) + + # recover just the buffers while restoring them to fp32 if they were saved in fp16 + buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names} + param_shapes = state_dict[PARAM_SHAPES] + + # collect parameters that are included in param_shapes + param_names = [] + for s in param_shapes: + for name in s.keys(): + param_names.append(name) + + # update with frozen parameters + frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None) + if frozen_param_shapes is not None: + if debug: + print(f"Found frozen_param_shapes: {frozen_param_shapes}") + param_names += list(frozen_param_shapes.keys()) + + # handle shared params + shared_params = [[k, v] for k, v in state_dict["shared_params"].items()] + + ds_version = state_dict.get(DS_VERSION, None) + + frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None) + + z_model_state = zero_model_state(buffers=buffers, + param_shapes=param_shapes, + shared_params=shared_params, + ds_version=ds_version, + frozen_param_shapes=frozen_param_shapes, + frozen_param_fragments=frozen_param_fragments) + zero_model_states.append(z_model_state) + + return zero_model_states + + +def parse_optim_states(files, ds_checkpoint_dir): + + total_files = len(files) + state_dicts = [] + for f in files: + state_dict = torch.load(f, map_location=device) + # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights + # and also handle the case where it was already removed by another helper script + state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None) + state_dicts.append(state_dict) + + if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]: + raise ValueError(f"{files[0]} is not a zero checkpoint") + zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE] + world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT] + + # For ZeRO-2 each param group can have different partition_count as data parallelism for expert + # parameters can be different from data parallelism for non-expert parameters. So we can just + # use the max of the partition_count to get the dp world_size. + + if type(world_size) is list: + world_size = max(world_size) + + if world_size != total_files: + raise ValueError( + f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. " + "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes." + ) + + # the groups are named differently in each stage + if zero_stage <= 2: + fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS + elif zero_stage == 3: + fp32_groups_key = FP32_FLAT_GROUPS + else: + raise ValueError(f"unknown zero stage {zero_stage}") + + if zero_stage <= 2: + fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))] + elif zero_stage == 3: + # if there is more than one param group, there will be multiple flattened tensors - one + # flattened tensor per group - for simplicity merge them into a single tensor + # + # XXX: could make the script more memory efficient for when there are multiple groups - it + # will require matching the sub-lists of param_shapes for each param group flattened tensor + + fp32_flat_groups = [ + torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts)) + ] + + return zero_stage, world_size, fp32_flat_groups + + +def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters): + """ + Returns fp32 state_dict reconstructed from ds checkpoint + + Args: + - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are) + + """ + print(f"Processing zero checkpoint '{ds_checkpoint_dir}'") + + optim_files = get_optim_files(ds_checkpoint_dir) + zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir) + print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}") + + model_files = get_model_state_files(ds_checkpoint_dir) + + zero_model_states = parse_model_states(model_files) + print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}') + + if zero_stage <= 2: + return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states, + exclude_frozen_parameters) + elif zero_stage == 3: + return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states, + exclude_frozen_parameters) + + +def _zero2_merge_frozen_params(state_dict, zero_model_states): + if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0: + return + + frozen_param_shapes = zero_model_states[0].frozen_param_shapes + frozen_param_fragments = zero_model_states[0].frozen_param_fragments + + if debug: + num_elem = sum(s.numel() for s in frozen_param_shapes.values()) + print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}') + + wanted_params = len(frozen_param_shapes) + wanted_numel = sum(s.numel() for s in frozen_param_shapes.values()) + avail_numel = sum([p.numel() for p in frozen_param_fragments.values()]) + print(f'Frozen params: Have {avail_numel} numels to process.') + print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params') + + total_params = 0 + total_numel = 0 + for name, shape in frozen_param_shapes.items(): + total_params += 1 + unpartitioned_numel = shape.numel() + total_numel += unpartitioned_numel + + state_dict[name] = frozen_param_fragments[name] + + if debug: + print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ") + + print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements") + + +def _has_callable(obj, fn): + attr = getattr(obj, fn, None) + return callable(attr) + + +def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states): + param_shapes = zero_model_states[0].param_shapes + + # Reconstruction protocol: + # + # XXX: document this + + if debug: + for i in range(world_size): + for j in range(len(fp32_flat_groups[0])): + print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}") + + # XXX: memory usage doubles here (zero2) + num_param_groups = len(fp32_flat_groups[0]) + merged_single_partition_of_fp32_groups = [] + for i in range(num_param_groups): + merged_partitions = [sd[i] for sd in fp32_flat_groups] + full_single_fp32_vector = torch.cat(merged_partitions, 0) + merged_single_partition_of_fp32_groups.append(full_single_fp32_vector) + avail_numel = sum( + [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups]) + + if debug: + wanted_params = sum([len(shapes) for shapes in param_shapes]) + wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes]) + # not asserting if there is a mismatch due to possible padding + print(f"Have {avail_numel} numels to process.") + print(f"Need {wanted_numel} numels in {wanted_params} params.") + + # params + # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support + # out-of-core computing solution + total_numel = 0 + total_params = 0 + for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups): + offset = 0 + avail_numel = full_single_fp32_vector.numel() + for name, shape in shapes.items(): + + unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape) + total_numel += unpartitioned_numel + total_params += 1 + + if debug: + print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ") + state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape) + offset += unpartitioned_numel + + # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and + # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex + # paddings performed in the code it's almost impossible to predict the exact numbers w/o the + # live optimizer object, so we are checking that the numbers are within the right range + align_to = 2 * world_size + + def zero2_align(x): + return align_to * math.ceil(x / align_to) + + if debug: + print(f"original offset={offset}, avail_numel={avail_numel}") + + offset = zero2_align(offset) + avail_numel = zero2_align(avail_numel) + + if debug: + print(f"aligned offset={offset}, avail_numel={avail_numel}") + + # Sanity check + if offset != avail_numel: + raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong") + + print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements") + + +def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states, + exclude_frozen_parameters): + state_dict = OrderedDict() + + # buffers + buffers = zero_model_states[0].buffers + state_dict.update(buffers) + if debug: + print(f"added {len(buffers)} buffers") + + if not exclude_frozen_parameters: + _zero2_merge_frozen_params(state_dict, zero_model_states) + + _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states) + + # recover shared parameters + for pair in zero_model_states[0].shared_params: + if pair[1] in state_dict: + state_dict[pair[0]] = state_dict[pair[1]] + + return state_dict + + +def zero3_partitioned_param_info(unpartitioned_numel, world_size): + remainder = unpartitioned_numel % world_size + padding_numel = (world_size - remainder) if remainder else 0 + partitioned_numel = math.ceil(unpartitioned_numel / world_size) + return partitioned_numel, padding_numel + + +def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states): + if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0: + return + + if debug: + for i in range(world_size): + num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values()) + print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}') + + frozen_param_shapes = zero_model_states[0].frozen_param_shapes + wanted_params = len(frozen_param_shapes) + wanted_numel = sum(s.numel() for s in frozen_param_shapes.values()) + avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size + print(f'Frozen params: Have {avail_numel} numels to process.') + print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params') + + total_params = 0 + total_numel = 0 + for name, shape in zero_model_states[0].frozen_param_shapes.items(): + total_params += 1 + unpartitioned_numel = shape.numel() + total_numel += unpartitioned_numel + + param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states) + state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape) + + partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size) + + if debug: + print( + f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}" + ) + + print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements") + + +def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states): + param_shapes = zero_model_states[0].param_shapes + avail_numel = fp32_flat_groups[0].numel() * world_size + # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each + # param, re-consolidating each param, while dealing with padding if any + + # merge list of dicts, preserving order + param_shapes = {k: v for d in param_shapes for k, v in d.items()} + + if debug: + for i in range(world_size): + print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}") + + wanted_params = len(param_shapes) + wanted_numel = sum(shape.numel() for shape in param_shapes.values()) + # not asserting if there is a mismatch due to possible padding + avail_numel = fp32_flat_groups[0].numel() * world_size + print(f"Trainable params: Have {avail_numel} numels to process.") + print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.") + + # params + # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support + # out-of-core computing solution + offset = 0 + total_numel = 0 + total_params = 0 + for name, shape in param_shapes.items(): + + unpartitioned_numel = shape.numel() + total_numel += unpartitioned_numel + total_params += 1 + + partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size) + + if debug: + print( + f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}" + ) + + # XXX: memory usage doubles here + state_dict[name] = torch.cat( + tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)), + 0).narrow(0, 0, unpartitioned_numel).view(shape) + offset += partitioned_numel + + offset *= world_size + + # Sanity check + if offset != avail_numel: + raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong") + + print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements") + + +def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states, + exclude_frozen_parameters): + state_dict = OrderedDict() + + # buffers + buffers = zero_model_states[0].buffers + state_dict.update(buffers) + if debug: + print(f"added {len(buffers)} buffers") + + if not exclude_frozen_parameters: + _zero3_merge_frozen_params(state_dict, world_size, zero_model_states) + + _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states) + + # recover shared parameters + for pair in zero_model_states[0].shared_params: + if pair[1] in state_dict: + state_dict[pair[0]] = state_dict[pair[1]] + + return state_dict + + +def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False): + """ + Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with + ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example + via a model hub. + + Args: + - ``checkpoint_dir``: path to the desired checkpoint folder + - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14`` + - ``exclude_frozen_parameters``: exclude frozen parameters + + Returns: + - pytorch ``state_dict`` + + Note: this approach may not work if your application doesn't have sufficient free CPU memory and + you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with + the checkpoint. + + A typical usage might be :: + + from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint + # do the training and checkpoint saving + state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu + model = model.cpu() # move to cpu + model.load_state_dict(state_dict) + # submit to model hub or save the model to share with others + + In this example the ``model`` will no longer be usable in the deepspeed context of the same + application. i.e. you will need to re-initialize the deepspeed engine, since + ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it. + + If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead. + + """ + if tag is None: + latest_path = os.path.join(checkpoint_dir, 'latest') + if os.path.isfile(latest_path): + with open(latest_path, 'r') as fd: + tag = fd.read().strip() + else: + raise ValueError(f"Unable to find 'latest' file at {latest_path}") + + ds_checkpoint_dir = os.path.join(checkpoint_dir, tag) + + if not os.path.isdir(ds_checkpoint_dir): + raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist") + + return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters) + + +def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False): + """ + Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be + loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed. + + Args: + - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``) + - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin) + - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14`` + - ``exclude_frozen_parameters``: exclude frozen parameters + """ + + state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters) + print(f"Saving fp32 state dict to {output_file}") + torch.save(state_dict, output_file) + + +def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None): + """ + 1. Put the provided model to cpu + 2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` + 3. Load it into the provided model + + Args: + - ``model``: the model object to update + - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``) + - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14`` + + Returns: + - ``model`: modified model + + Make sure you have plenty of CPU memory available before you call this function. If you don't + have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it + conveniently placed for you in the checkpoint folder. + + A typical usage might be :: + + from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint + model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir) + # submit to model hub or save the model to share with others + + Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context + of the same application. i.e. you will need to re-initialize the deepspeed engine, since + ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it. + + """ + logger.info(f"Extracting fp32 weights") + state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag) + + logger.info(f"Overwriting model with fp32 weights") + model = model.cpu() + model.load_state_dict(state_dict, strict=False) + + return model + + +if __name__ == "__main__": + + parser = argparse.ArgumentParser() + parser.add_argument("checkpoint_dir", + type=str, + help="path to the desired checkpoint folder, e.g., path/checkpoint-12") + parser.add_argument( + "output_file", + type=str, + help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)") + parser.add_argument("-t", + "--tag", + type=str, + default=None, + help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1") + parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters") + parser.add_argument("-d", "--debug", action='store_true', help="enable debug") + args = parser.parse_args() + + debug = args.debug + + convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, + args.output_file, + tag=args.tag, + exclude_frozen_parameters=args.exclude_frozen_parameters) diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..619f881de9074b0e079b7cd1ab483a2eabff9707 --- /dev/null +++ b/config.json @@ -0,0 +1,41 @@ +{ + "_name_or_path": "google/paligemma-3b-mix-448", + "architectures": [ + "PaliGemmaForConditionalGeneration" + ], + "bos_token_id": 2, + "eos_token_id": 1, + "hidden_size": 2048, + "ignore_index": -100, + "image_token_index": 257152, + "model_type": "paligemma", + "pad_token_id": 0, + "projection_dim": 2048, + "text_config": { + "hidden_size": 2048, + "intermediate_size": 16384, + "model_type": "gemma", + "num_attention_heads": 8, + "num_hidden_layers": 18, + "num_image_tokens": 1024, + "num_key_value_heads": 1, + "torch_dtype": "float32", + "vocab_size": 257216 + }, + "torch_dtype": "bfloat16", + "transformers_version": "4.43.2", + "use_cache": false, + "vision_config": { + "hidden_size": 1152, + "image_size": 448, + "intermediate_size": 4304, + "model_type": "siglip_vision_model", + "num_attention_heads": 16, + "num_hidden_layers": 27, + "num_image_tokens": 1024, + "patch_size": 14, + "projection_dim": 2048, + "projector_hidden_act": "gelu_fast", + "vision_use_head": false + } +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..cd9e5e9d63f83590138b0318869731ac7a2f5246 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 2, + "eos_token_id": 1, + "pad_token_id": 0, + "transformers_version": "4.43.2" +} diff --git a/model-00001-of-00002.safetensors b/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..970ed290903547c40f13d9c68aeae62dac179017 --- /dev/null +++ b/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d93d6361131fcfcc325a52d685ca20912773f8bd1e870cc453dba3b8a700cad +size 4986813864 diff --git a/model-00002-of-00002.safetensors b/model-00002-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5140f5ae7cfc6b5128d85a9bd3204b1a633c1de4 --- /dev/null +++ b/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a26171508c249e90b06be1147d47e75e7cac50d289092b0d61f9839c611a536 +size 861970608 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..b8c76b58234e80cb23768096869fb3a0dc5a15a4 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,610 @@ +{ + "metadata": { + "total_size": 5848702432 + }, + "weight_map": { + "language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.norm.weight": "model-00002-of-00002.safetensors", + "multi_modal_projector.linear.bias": "model-00001-of-00002.safetensors", + "multi_modal_projector.linear.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors", + "vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors" + } +} diff --git a/preprocessor_config.json b/preprocessor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..77bc692dcae67acc343539d9f0659d7de3c302b1 --- /dev/null +++ b/preprocessor_config.json @@ -0,0 +1,25 @@ +{ + "do_convert_rgb": null, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_processor_type": "SiglipImageProcessor", + "image_seq_length": 1024, + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "processor_class": "PaliGemmaProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "size": { + "height": 448, + "width": 448 + } +} diff --git a/runs/Aug10_17-57-55_amd-G262-ZO0-00/events.out.tfevents.1723312694.amd-G262-ZO0-00.14080.0 b/runs/Aug10_17-57-55_amd-G262-ZO0-00/events.out.tfevents.1723312694.amd-G262-ZO0-00.14080.0 new file mode 100644 index 0000000000000000000000000000000000000000..36f004d5c456dd095ef41fa4caca854580d16963 --- /dev/null +++ b/runs/Aug10_17-57-55_amd-G262-ZO0-00/events.out.tfevents.1723312694.amd-G262-ZO0-00.14080.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:500c00bd0e24cffc7a63107984d21d7008c6eda15f36585258412ed6d2db5333 +size 6125 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..0c18fdd94629ea652e2ef36ed9a422474ad0a8e8 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,33 @@ +{ + "additional_special_tokens": [ + "" + ], + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..419d3c8c8da378e1f551d4348a5c2ca7616153d6 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef6773c135b77b834de1d13c75a4c98ab7a3684ffd602d1831e1f1bf5467c563 +size 17549604 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..22ad048d392b4f5191be7cec47d03eb3cdb360f4 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8986bb4f423f07f8c7f70d0dbe3526fb2316056c17bae71b1ea975e77a168fc6 +size 4264023 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1e9ef9c0ee5e46d701a6b082c1d28bd63d9c406c --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,1767 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "4": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "5": { + "content": "<2mass>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "6": { + "content": "[@BOS@]", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "7": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "8": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "9": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "10": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "11": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "12": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "13": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "14": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "15": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "16": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "17": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "18": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "19": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "20": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "21": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "22": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "23": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "24": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "25": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "26": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "27": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "28": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "29": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "30": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "31": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "32": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "33": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "34": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "35": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "36": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "37": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "38": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "39": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "40": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "41": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "42": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "43": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "44": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "45": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "46": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "47": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "48": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "49": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "50": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "51": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "52": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "53": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "54": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "55": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "56": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "57": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "58": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "59": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "60": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "61": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "62": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "63": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "64": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "65": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "66": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "67": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "68": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "69": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "70": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "71": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "72": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "73": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "74": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "75": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "76": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "77": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "78": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "79": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "80": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "81": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "82": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "83": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "84": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "85": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "86": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "87": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "88": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "89": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "90": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "91": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "92": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "93": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "94": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "95": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "96": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "97": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "98": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "99": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "100": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "101": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "102": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "103": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "104": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "105": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "106": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "107": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "108": { + "content": "\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "109": { + "content": "\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "110": { + "content": "\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "111": { + "content": "\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "112": { + "content": "\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "113": { + "content": "\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "114": { + "content": "\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "115": { + "content": "\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "116": { + "content": "\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "117": { + "content": "\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "118": { + "content": "\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "119": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "120": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "121": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "122": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "123": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "124": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "125": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "126": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "127": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "128": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "129": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "130": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "131": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "132": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "133": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "134": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "135": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "136": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "137": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "138": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "139": { + "content": "▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "140": { + "content": "▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "141": { + "content": "▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "142": { + "content": "▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "143": { + "content": "▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "144": { + "content": "▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "145": { + "content": "▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "146": { + "content": "▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "147": { + "content": "▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "148": { + "content": "▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "149": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "150": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "151": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "152": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "153": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "154": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "155": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "156": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "157": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "158": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "159": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "160": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "161": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "162": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "163": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "164": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "165": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "166": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "167": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "168": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "169": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "170": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "172": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "173": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "174": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "175": { + "content": "
", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "171": { + "content": "
", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "176": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "177": { + "content": "
", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "178": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "179": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "180": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "181": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "182": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "183": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "184": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "185": { + "content": "

", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "186": { + "content": "

", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "187": { + "content": "

", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "188": { + "content": "

", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "189": { + "content": "

", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "190": { + "content": "
", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "191": { + "content": "
", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "192": { + "content": "
", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "193": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "194": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "195": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "196": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "197": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "198": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "199": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "200": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "201": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "202": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "203": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "204": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "205": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "206": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "207": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "208": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "209": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "210": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "211": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "212": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "213": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "214": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "215": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "216": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "257152": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "" + ], + "bos_token": "", + "chat_template": "{{ '' }}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'user\n' + content + '\nmodel\n' }}{% elif message['role'] == 'assistant' %}{{ content + '\n' }}{% endif %}{% endfor %}", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "padding_side": "right", + "processor_class": "PaliGemmaProcessor", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "split_special_tokens": false, + "tokenizer_class": "GemmaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +} diff --git a/train_results.json b/train_results.json new file mode 100644 index 0000000000000000000000000000000000000000..129ba325cf722334de02751dea62be7e1cf2335a --- /dev/null +++ b/train_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 1.792, + "total_flos": 30998735618048.0, + "train_loss": 4.085959434509277, + "train_runtime": 5425.5762, + "train_samples_per_second": 0.367, + "train_steps_per_second": 0.003 +} \ No newline at end of file diff --git a/trainer_log.jsonl b/trainer_log.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..a8613d293861aafa22a8d47fd43dde6986709162 --- /dev/null +++ b/trainer_log.jsonl @@ -0,0 +1,2 @@ +{"current_steps": 10, "total_steps": 14, "loss": 4.1132, "learning_rate": 6.000000000000001e-07, "epoch": 1.28, "percentage": 71.43, "elapsed_time": "1:07:49", "remaining_time": "0:27:07", "throughput": "0.00", "total_tokens": 0} +{"current_steps": 14, "total_steps": 14, "epoch": 1.792, "percentage": 100.0, "elapsed_time": "1:30:21", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..d8760e43a4622fbe606cbd1d61661325ffee5b70 --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,49 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.792, + "eval_steps": 500, + "global_step": 14, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 1.28, + "grad_norm": 57.92857011087701, + "learning_rate": 6.000000000000001e-07, + "loss": 4.1132, + "step": 10 + }, + { + "epoch": 1.792, + "step": 14, + "total_flos": 30998735618048.0, + "train_loss": 4.085959434509277, + "train_runtime": 5425.5762, + "train_samples_per_second": 0.367, + "train_steps_per_second": 0.003 + } + ], + "logging_steps": 10, + "max_steps": 14, + "num_input_tokens_seen": 0, + "num_train_epochs": 2, + "save_steps": 1000, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 30998735618048.0, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..23871f43017492e1ff53bd1aad5cdcf2736e6c10 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7eb5a4ebca2ac9e22067c1b25b0f7ba346c7d449e69982a206be438bdee2d84 +size 7096 diff --git a/training_loss.png b/training_loss.png new file mode 100644 index 0000000000000000000000000000000000000000..36acf5515d3d97b1d96e8accba13e274345c8c09 Binary files /dev/null and b/training_loss.png differ