Upload base_0020000

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 32768,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "num_local_experts": null,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "vocab_size": 250880
+}

done.txt

@@ -0,0 +1 @@
+2025-04-03 01:02:35.156606-05:00

pytorch_model-00001-of-00006.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c464ca3749daf9bc00e92e418fa9eebd6a3b182b6cfb0031b2cdff51765d4b6
+oid sha256:96c8c7ae50b6f5d5cd26d19277203c1f30c438784644f8ba60796433581c2ecf
 size 49292351711

pytorch_model-00002-of-00006.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f7930d8e4821a47b2e5e3d419308956c3f93bdae9ab12b3a03963a43c3424cc
+oid sha256:deaf606dc2e849bac8b38e59fae4f195004b610c7fd4e95f9e6faab561c88767
 size 49795739754

pytorch_model-00003-of-00006.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a69b9d074444bb6c1a64b4feff642fb00e472221896dba8f77a0a66f0ea22d4
+oid sha256:4a5ce9098c4e2499431c5dcc4e52569e5379250f58a41fe20c7d75c45d9829dd
 size 49460262641

pytorch_model-00004-of-00006.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7ca17baf4d17a90e131b4d251544f6011d120a499029a02756cb8fd4e45ae35
+oid sha256:26ff460e85cc9fcbca895d3b4efd7f8ba5a9e0f7185de3ebca149705c8227014
 size 49795739754

pytorch_model-00005-of-00006.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1e019f6fd701a862064bf4f9218a20e9778168fdfbba07f7a58ba369898e2a1
+oid sha256:f02e707a3f1684ce914428fea2519f41cb60b181d628c3f046fdecd2bf1fc6b4
 size 49460262641

pytorch_model-00006-of-00006.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2febfb2699b1ad301e5a30011ef28ecdc1b3e32a3056c7664b7591d0cfad30fb
+oid sha256:7c15efd51260852ff1fb26a137944466e9c69e9557b622d04ab8c0cf88ca0f51
 size 42447010822

pytorch_model.bin.index.json

@@ -0,0 +1,730 @@
+{
+  "metadata": {
+    "total_size": 290251112448
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00006-of-00006.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.40.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.40.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.40.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.41.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.41.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.41.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.42.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.42.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.42.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.43.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.43.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.43.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.44.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.44.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.44.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.45.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.45.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.45.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.46.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.46.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.46.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.47.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.47.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.47.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.48.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.48.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.48.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.48.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.48.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.49.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.49.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.49.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.49.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.49.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.50.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.50.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.50.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.50.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.50.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.51.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.51.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.51.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.51.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.51.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.52.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.52.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.52.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.52.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.52.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.53.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.53.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.53.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.53.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.53.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.54.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.54.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.54.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.54.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.54.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.55.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.55.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.55.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.55.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.55.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.56.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.56.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.56.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.56.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.56.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.56.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.56.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.56.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.56.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.57.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.57.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.57.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.57.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.57.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.57.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.58.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.58.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.58.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.58.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.58.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.58.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.58.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.58.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.58.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.59.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.59.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.59.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.59.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.59.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.59.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.59.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.59.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.59.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.60.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.60.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.60.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.60.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.60.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.60.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.60.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.60.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.60.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.61.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.61.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.61.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.61.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.61.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.61.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.61.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.61.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.61.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.62.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.62.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.62.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.62.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.62.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.62.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.62.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.62.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.62.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.63.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.63.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.63.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.63.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.63.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.63.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.63.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.63.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.63.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.64.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.64.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.64.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.64.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.64.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.64.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.64.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.64.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.64.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.65.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.65.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.65.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.65.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.65.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.65.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.65.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.65.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.65.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.66.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.66.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.66.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.66.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.66.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.66.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.66.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.66.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.66.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.67.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.67.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.67.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.67.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.67.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.67.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.67.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.67.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.67.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.68.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.68.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.68.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.68.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.68.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.68.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.68.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.68.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.68.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.69.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.69.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.69.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.69.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.69.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.69.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.69.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.69.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.69.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.70.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.70.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.70.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.70.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.70.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.70.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.70.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.70.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.70.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.71.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.71.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.71.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.71.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.71.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.71.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.71.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.71.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.71.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.72.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.72.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.72.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.72.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.72.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.72.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.72.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.72.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.72.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.73.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.73.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.73.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.73.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.73.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.73.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.73.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.73.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.73.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.74.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.74.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.74.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.74.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.74.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.74.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.74.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.74.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.74.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.75.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.75.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.75.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.75.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.75.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.75.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.75.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.75.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.75.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.76.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.76.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.76.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.76.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.76.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.76.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.76.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.76.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.76.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.77.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.77.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.77.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.77.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.77.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.77.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.77.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.77.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.77.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.78.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.78.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.78.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.78.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.78.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.78.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.78.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.78.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.78.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.79.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.79.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.79.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.79.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.79.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.79.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.79.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.79.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.79.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.norm.weight": "pytorch_model-00006-of-00006.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,4 @@
+{
+  "bos_token": "<|begin_of_text|>",
+  "eos_token": "<|end_of_text|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8f4e9569156ab4de1c7e7ba90054ba1af10c5ee6d2ad7268ee26f7d6179f940
+size 13486839

tokenizer_config.json

@@ -0,0 +1,1805 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250000": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250002": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250003": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250004": {
+      "content": "<|filename|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250005": {
+      "content": "<|gh_stars|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250006": {
+      "content": "<|issue_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250007": {
+      "content": "<|issue_comment|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250008": {
+      "content": "<|issue_closed|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250009": {
+      "content": "<|jupyter_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250010": {
+      "content": "<|jupyter_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250011": {
+      "content": "<|jupyter_code|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250012": {
+      "content": "<|jupyter_output|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250013": {
+      "content": "<|empty_output|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250014": {
+      "content": "<|commit_before|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250015": {
+      "content": "<|commit_msg|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250016": {
+      "content": "<|commit_after|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250017": {
+      "content": "<|reponame|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250018": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250019": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250020": {
+      "content": "<|sys_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250021": {
+      "content": "<|sys_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250022": {
+      "content": "reserved_special_token_0",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250023": {
+      "content": "reserved_special_token_1",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250024": {
+      "content": "reserved_special_token_2",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250025": {
+      "content": "reserved_special_token_3",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250026": {
+      "content": "reserved_special_token_4",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250027": {
+      "content": "reserved_special_token_5",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250028": {
+      "content": "reserved_special_token_6",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250029": {
+      "content": "reserved_special_token_7",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250030": {
+      "content": "reserved_special_token_8",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250031": {
+      "content": "reserved_special_token_9",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250032": {
+      "content": "reserved_special_token_10",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250033": {
+      "content": "reserved_special_token_11",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250034": {
+      "content": "reserved_special_token_12",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250035": {
+      "content": "reserved_special_token_13",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250036": {
+      "content": "reserved_special_token_14",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250037": {
+      "content": "reserved_special_token_15",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250038": {
+      "content": "reserved_special_token_16",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250039": {
+      "content": "reserved_special_token_17",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250040": {
+      "content": "reserved_special_token_18",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250041": {
+      "content": "reserved_special_token_19",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250042": {
+      "content": "reserved_special_token_20",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250043": {
+      "content": "reserved_special_token_21",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250044": {
+      "content": "reserved_special_token_22",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250045": {
+      "content": "reserved_special_token_23",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250046": {
+      "content": "reserved_special_token_24",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250047": {
+      "content": "reserved_special_token_25",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250048": {
+      "content": "reserved_special_token_26",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250049": {
+      "content": "reserved_special_token_27",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250050": {
+      "content": "reserved_special_token_28",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250051": {
+      "content": "reserved_special_token_29",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250052": {
+      "content": "reserved_special_token_30",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250053": {
+      "content": "reserved_special_token_31",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250054": {
+      "content": "reserved_special_token_32",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250055": {
+      "content": "reserved_special_token_33",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250056": {
+      "content": "reserved_special_token_34",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250057": {
+      "content": "reserved_special_token_35",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250058": {
+      "content": "reserved_special_token_36",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250059": {
+      "content": "reserved_special_token_37",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250060": {
+      "content": "reserved_special_token_38",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250061": {
+      "content": "reserved_special_token_39",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250062": {
+      "content": "reserved_special_token_40",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250063": {
+      "content": "reserved_special_token_41",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250064": {
+      "content": "reserved_special_token_42",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250065": {
+      "content": "reserved_special_token_43",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250066": {
+      "content": "reserved_special_token_44",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250067": {
+      "content": "reserved_special_token_45",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250068": {
+      "content": "reserved_special_token_46",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250069": {
+      "content": "reserved_special_token_47",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250070": {
+      "content": "reserved_special_token_48",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250071": {
+      "content": "reserved_special_token_49",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250072": {
+      "content": "reserved_special_token_50",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250073": {
+      "content": "reserved_special_token_51",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250074": {
+      "content": "reserved_special_token_52",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250075": {
+      "content": "reserved_special_token_53",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250076": {
+      "content": "reserved_special_token_54",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250077": {
+      "content": "reserved_special_token_55",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250078": {
+      "content": "reserved_special_token_56",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250079": {
+      "content": "reserved_special_token_57",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250080": {
+      "content": "reserved_special_token_58",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250081": {
+      "content": "reserved_special_token_59",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250082": {
+      "content": "reserved_special_token_60",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250083": {
+      "content": "reserved_special_token_61",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250084": {
+      "content": "reserved_special_token_62",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250085": {
+      "content": "reserved_special_token_63",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250086": {
+      "content": "reserved_special_token_64",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250087": {
+      "content": "reserved_special_token_65",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250088": {
+      "content": "reserved_special_token_66",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250089": {
+      "content": "reserved_special_token_67",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250090": {
+      "content": "reserved_special_token_68",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250091": {
+      "content": "reserved_special_token_69",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250092": {
+      "content": "reserved_special_token_70",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250093": {
+      "content": "reserved_special_token_71",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250094": {
+      "content": "reserved_special_token_72",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250095": {
+      "content": "reserved_special_token_73",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250096": {
+      "content": "reserved_special_token_74",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250097": {
+      "content": "reserved_special_token_75",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250098": {
+      "content": "reserved_special_token_76",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250099": {
+      "content": "reserved_special_token_77",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250100": {
+      "content": "reserved_special_token_78",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250101": {
+      "content": "reserved_special_token_79",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250102": {
+      "content": "reserved_special_token_80",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250103": {
+      "content": "reserved_special_token_81",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250104": {
+      "content": "reserved_special_token_82",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250105": {
+      "content": "reserved_special_token_83",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250106": {
+      "content": "reserved_special_token_84",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250107": {
+      "content": "reserved_special_token_85",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250108": {
+      "content": "reserved_special_token_86",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250109": {
+      "content": "reserved_special_token_87",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250110": {
+      "content": "reserved_special_token_88",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250111": {
+      "content": "reserved_special_token_89",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250112": {
+      "content": "reserved_special_token_90",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250113": {
+      "content": "reserved_special_token_91",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250114": {
+      "content": "reserved_special_token_92",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250115": {
+      "content": "reserved_special_token_93",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250116": {
+      "content": "reserved_special_token_94",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250117": {
+      "content": "reserved_special_token_95",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250118": {
+      "content": "reserved_special_token_96",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250119": {
+      "content": "reserved_special_token_97",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250120": {
+      "content": "reserved_special_token_98",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250121": {
+      "content": "reserved_special_token_99",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250122": {
+      "content": "reserved_special_token_100",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250123": {
+      "content": "reserved_special_token_101",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250124": {
+      "content": "reserved_special_token_102",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250125": {
+      "content": "reserved_special_token_103",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250126": {
+      "content": "reserved_special_token_104",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250127": {
+      "content": "reserved_special_token_105",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250128": {
+      "content": "reserved_special_token_106",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250129": {
+      "content": "reserved_special_token_107",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250130": {
+      "content": "reserved_special_token_108",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250131": {
+      "content": "reserved_special_token_109",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250132": {
+      "content": "reserved_special_token_110",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250133": {
+      "content": "reserved_special_token_111",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250134": {
+      "content": "reserved_special_token_112",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250135": {
+      "content": "reserved_special_token_113",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250136": {
+      "content": "reserved_special_token_114",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250137": {
+      "content": "reserved_special_token_115",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250138": {
+      "content": "reserved_special_token_116",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250139": {
+      "content": "reserved_special_token_117",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250140": {
+      "content": "reserved_special_token_118",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250141": {
+      "content": "reserved_special_token_119",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250142": {
+      "content": "reserved_special_token_120",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250143": {
+      "content": "reserved_special_token_121",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250144": {
+      "content": "reserved_special_token_122",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250145": {
+      "content": "reserved_special_token_123",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250146": {
+      "content": "reserved_special_token_124",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250147": {
+      "content": "reserved_special_token_125",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250148": {
+      "content": "reserved_special_token_126",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250149": {
+      "content": "reserved_special_token_127",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250150": {
+      "content": "reserved_special_token_128",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250151": {
+      "content": "reserved_special_token_129",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250152": {
+      "content": "reserved_special_token_130",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250153": {
+      "content": "reserved_special_token_131",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250154": {
+      "content": "reserved_special_token_132",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250155": {
+      "content": "reserved_special_token_133",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250156": {
+      "content": "reserved_special_token_134",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250157": {
+      "content": "reserved_special_token_135",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250158": {
+      "content": "reserved_special_token_136",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250159": {
+      "content": "reserved_special_token_137",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250160": {
+      "content": "reserved_special_token_138",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250161": {
+      "content": "reserved_special_token_139",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250162": {
+      "content": "reserved_special_token_140",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250163": {
+      "content": "reserved_special_token_141",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250164": {
+      "content": "reserved_special_token_142",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250165": {
+      "content": "reserved_special_token_143",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250166": {
+      "content": "reserved_special_token_144",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250167": {
+      "content": "reserved_special_token_145",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250168": {
+      "content": "reserved_special_token_146",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250169": {
+      "content": "reserved_special_token_147",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250170": {
+      "content": "reserved_special_token_148",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250171": {
+      "content": "reserved_special_token_149",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250172": {
+      "content": "reserved_special_token_150",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250173": {
+      "content": "reserved_special_token_151",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250174": {
+      "content": "reserved_special_token_152",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250175": {
+      "content": "reserved_special_token_153",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250176": {
+      "content": "reserved_special_token_154",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250177": {
+      "content": "reserved_special_token_155",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250178": {
+      "content": "reserved_special_token_156",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250179": {
+      "content": "reserved_special_token_157",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250180": {
+      "content": "reserved_special_token_158",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250181": {
+      "content": "reserved_special_token_159",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250182": {
+      "content": "reserved_special_token_160",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250183": {
+      "content": "reserved_special_token_161",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250184": {
+      "content": "reserved_special_token_162",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250185": {
+      "content": "reserved_special_token_163",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250186": {
+      "content": "reserved_special_token_164",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250187": {
+      "content": "reserved_special_token_165",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250188": {
+      "content": "reserved_special_token_166",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250189": {
+      "content": "reserved_special_token_167",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250190": {
+      "content": "reserved_special_token_168",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250191": {
+      "content": "reserved_special_token_169",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250192": {
+      "content": "reserved_special_token_170",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250193": {
+      "content": "reserved_special_token_171",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250194": {
+      "content": "reserved_special_token_172",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250195": {
+      "content": "reserved_special_token_173",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250196": {
+      "content": "reserved_special_token_174",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250197": {
+      "content": "reserved_special_token_175",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250198": {
+      "content": "reserved_special_token_176",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250199": {
+      "content": "reserved_special_token_177",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250200": {
+      "content": "reserved_special_token_178",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250201": {
+      "content": "reserved_special_token_179",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250202": {
+      "content": "reserved_special_token_180",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250203": {
+      "content": "reserved_special_token_181",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250204": {
+      "content": "reserved_special_token_182",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250205": {
+      "content": "reserved_special_token_183",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250206": {
+      "content": "reserved_special_token_184",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250207": {
+      "content": "reserved_special_token_185",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250208": {
+      "content": "reserved_special_token_186",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250209": {
+      "content": "reserved_special_token_187",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250210": {
+      "content": "reserved_special_token_188",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250211": {
+      "content": "reserved_special_token_189",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250212": {
+      "content": "reserved_special_token_190",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250213": {
+      "content": "reserved_special_token_191",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250214": {
+      "content": "reserved_special_token_192",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250215": {
+      "content": "reserved_special_token_193",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250216": {
+      "content": "reserved_special_token_194",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250217": {
+      "content": "reserved_special_token_195",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250218": {
+      "content": "reserved_special_token_196",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250219": {
+      "content": "reserved_special_token_197",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250220": {
+      "content": "reserved_special_token_198",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250221": {
+      "content": "reserved_special_token_199",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}