| { | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "Qwen3VLForConditionalGeneration" | |
| ], | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": null, | |
| "chunk_size_feed_forward": 0, | |
| "cross_attention_hidden_size": null, | |
| "decoder_start_token_id": null, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "dtype": null, | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": null, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "image_token_id": 151655, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "min_length": 0, | |
| "model_type": "qwen3_vl", | |
| "no_repeat_ngram_size": 0, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": null, | |
| "prefix": null, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "quantization": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine", | |
| "language_model.model.embed_tokens": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.0.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.0.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.0.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.0.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.0.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.0.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.0.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.1.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.1.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.1.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.1.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.1.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.1.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.1.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.2.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.2.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.2.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.2.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.2.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.2.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.2.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.3.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.3.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.3.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.3.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.3.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.3.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.3.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.4.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.4.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.4.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.4.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.4.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.4.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.4.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.5.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.5.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.5.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.5.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.5.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.5.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.5.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.6.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.6.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.6.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.6.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.6.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.6.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.6.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.7.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.7.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.7.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.7.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.7.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.7.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.7.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.8.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.8.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.8.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.8.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.8.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.8.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.8.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.9.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.9.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.9.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.9.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.9.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.9.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.9.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.10.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.10.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.10.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.10.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.10.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.10.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.10.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.11.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.11.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.11.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.11.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.11.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.11.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.11.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.12.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.12.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.12.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.12.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.12.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.12.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.12.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.13.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.13.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.13.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.13.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.13.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.13.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.13.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.14.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.14.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.14.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.14.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.14.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.14.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.14.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.15.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.15.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.15.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.15.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.15.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.15.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.15.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.16.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.16.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.16.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.16.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.16.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.16.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.16.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.17.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.17.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.17.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.17.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.17.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.17.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.17.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.18.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.18.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.18.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.18.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.18.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.18.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.18.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.19.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.19.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.19.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.19.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.19.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.19.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.19.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.20.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.20.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.20.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.20.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.20.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.20.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.20.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.21.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.21.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.21.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.21.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.21.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.21.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.21.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.22.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.22.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.22.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.22.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.22.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.22.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.22.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.23.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.23.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.23.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.23.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.23.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.23.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.23.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.24.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.24.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.24.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.24.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.24.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.24.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.24.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.25.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.25.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.25.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.25.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.25.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.25.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.25.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.26.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.26.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.26.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.26.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.26.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.26.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.26.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.27.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.27.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.27.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.27.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.27.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.27.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.27.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| } | |
| }, | |
| "quantization_config": { | |
| "group_size": 32, | |
| "bits": 4, | |
| "mode": "affine", | |
| "language_model.model.embed_tokens": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.0.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.0.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.0.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.0.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.0.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.0.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.0.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.1.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.1.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.1.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.1.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.1.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.1.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.1.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.2.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.2.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.2.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.2.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.2.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.2.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.2.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.3.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.3.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.3.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.3.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.3.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.3.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.3.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.4.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.4.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.4.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.4.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.4.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.4.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.4.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.5.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.5.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.5.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.5.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.5.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.5.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.5.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.6.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.6.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.6.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.6.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.6.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.6.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.6.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.7.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.7.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.7.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.7.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.7.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.7.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.7.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.8.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.8.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.8.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.8.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.8.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.8.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.8.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.9.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.9.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.9.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.9.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.9.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.9.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.9.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.10.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.10.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.10.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.10.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.10.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.10.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.10.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.11.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.11.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.11.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.11.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.11.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.11.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.11.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.12.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.12.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.12.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.12.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.12.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.12.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.12.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.13.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.13.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.13.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.13.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.13.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.13.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.13.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.14.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.14.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.14.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.14.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.14.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.14.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.14.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.15.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.15.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.15.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.15.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.15.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.15.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.15.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.16.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.16.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.16.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.16.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.16.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.16.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.16.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.17.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.17.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.17.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.17.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.17.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.17.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.17.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.18.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.18.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.18.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.18.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.18.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.18.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.18.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.19.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.19.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.19.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.19.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.19.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.19.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.19.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.20.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.20.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.20.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.20.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.20.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.20.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.20.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.21.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.21.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.21.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.21.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.21.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.21.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.21.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.22.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.22.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.22.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.22.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.22.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.22.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.22.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.23.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.23.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.23.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.23.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.23.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.23.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.23.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.24.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.24.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.24.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.24.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.24.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.24.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.24.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.25.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.25.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.25.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.25.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.25.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.25.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.25.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.26.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.26.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.26.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.26.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.26.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.26.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.26.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.27.self_attn.q_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.27.self_attn.k_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.27.self_attn.v_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.27.self_attn.o_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.27.mlp.gate_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "language_model.model.layers.27.mlp.down_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "language_model.model.layers.27.mlp.up_proj": { | |
| "group_size": 64, | |
| "bits": 4 | |
| } | |
| }, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "sep_token_id": null, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "text_config": { | |
| "vocab_size": 151936, | |
| "max_position_embeddings": 262144, | |
| "hidden_size": 2048, | |
| "intermediate_size": 6144, | |
| "num_hidden_layers": 28, | |
| "num_attention_heads": 16, | |
| "num_key_value_heads": 8, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "initializer_range": 0.02, | |
| "rms_norm_eps": 1e-06, | |
| "use_cache": true, | |
| "rope_theta": 5000000, | |
| "rope_scaling": { | |
| "mrope_interleaved": true, | |
| "mrope_section": [ | |
| 24, | |
| 20, | |
| 20 | |
| ], | |
| "rope_type": "default" | |
| }, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "return_dict": true, | |
| "output_hidden_states": false, | |
| "torchscript": false, | |
| "dtype": "bfloat16", | |
| "pruned_heads": {}, | |
| "tie_word_embeddings": true, | |
| "chunk_size_feed_forward": 0, | |
| "is_encoder_decoder": false, | |
| "is_decoder": false, | |
| "cross_attention_hidden_size": null, | |
| "add_cross_attention": false, | |
| "tie_encoder_decoder": false, | |
| "architectures": null, | |
| "finetuning_task": null, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "task_specific_params": null, | |
| "problem_type": null, | |
| "tokenizer_class": null, | |
| "prefix": null, | |
| "bos_token_id": 151643, | |
| "pad_token_id": null, | |
| "eos_token_id": 151645, | |
| "sep_token_id": null, | |
| "decoder_start_token_id": null, | |
| "max_length": 20, | |
| "min_length": 0, | |
| "do_sample": false, | |
| "early_stopping": false, | |
| "num_beams": 1, | |
| "temperature": 1.0, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "typical_p": 1.0, | |
| "repetition_penalty": 1.0, | |
| "length_penalty": 1.0, | |
| "no_repeat_ngram_size": 0, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "bad_words_ids": null, | |
| "num_return_sequences": 1, | |
| "output_scores": false, | |
| "return_dict_in_generate": false, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "remove_invalid_values": false, | |
| "exponential_decay_length_penalty": null, | |
| "suppress_tokens": null, | |
| "begin_suppress_tokens": null, | |
| "num_beam_groups": 1, | |
| "diversity_penalty": 0.0, | |
| "_name_or_path": "", | |
| "model_type": "qwen3_vl_text", | |
| "tf_legacy_loss": false, | |
| "use_bfloat16": false, | |
| "output_attentions": false | |
| }, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torchscript": false, | |
| "transformers_version": "4.57.1", | |
| "typical_p": 1.0, | |
| "use_bfloat16": false, | |
| "video_token_id": 151656, | |
| "vision_config": { | |
| "return_dict": true, | |
| "output_hidden_states": false, | |
| "torchscript": false, | |
| "dtype": null, | |
| "pruned_heads": {}, | |
| "tie_word_embeddings": true, | |
| "chunk_size_feed_forward": 0, | |
| "is_encoder_decoder": false, | |
| "is_decoder": false, | |
| "cross_attention_hidden_size": null, | |
| "add_cross_attention": false, | |
| "tie_encoder_decoder": false, | |
| "architectures": null, | |
| "finetuning_task": null, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "task_specific_params": null, | |
| "problem_type": null, | |
| "tokenizer_class": null, | |
| "prefix": null, | |
| "bos_token_id": null, | |
| "pad_token_id": null, | |
| "eos_token_id": null, | |
| "sep_token_id": null, | |
| "decoder_start_token_id": null, | |
| "max_length": 20, | |
| "min_length": 0, | |
| "do_sample": false, | |
| "early_stopping": false, | |
| "num_beams": 1, | |
| "temperature": 1.0, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "typical_p": 1.0, | |
| "repetition_penalty": 1.0, | |
| "length_penalty": 1.0, | |
| "no_repeat_ngram_size": 0, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "bad_words_ids": null, | |
| "num_return_sequences": 1, | |
| "output_scores": false, | |
| "return_dict_in_generate": false, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "remove_invalid_values": false, | |
| "exponential_decay_length_penalty": null, | |
| "suppress_tokens": null, | |
| "begin_suppress_tokens": null, | |
| "num_beam_groups": 1, | |
| "diversity_penalty": 0.0, | |
| "_name_or_path": "", | |
| "model_type": "qwen3_vl", | |
| "tf_legacy_loss": false, | |
| "use_bfloat16": false, | |
| "depth": 24, | |
| "hidden_size": 1024, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "intermediate_size": 4096, | |
| "num_heads": 16, | |
| "in_channels": 3, | |
| "patch_size": 16, | |
| "spatial_merge_size": 2, | |
| "temporal_patch_size": 2, | |
| "out_hidden_size": 2048, | |
| "num_position_embeddings": 2304, | |
| "initializer_range": 0.02, | |
| "deepstack_visual_indexes": [ | |
| 5, | |
| 11, | |
| 17 | |
| ], | |
| "output_attentions": false | |
| }, | |
| "vision_end_token_id": 151653, | |
| "vision_start_token_id": 151652 | |
| } |