update to alpaca-13b

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/dataset/yukangchen/hf_models/sft-models/Llama-2-13b-chat-longlora-32k-sft",
+  "_name_or_path": "/dataset/pretrained-models/Llama-2-13b-chat-hf",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -14,11 +14,15 @@
   "num_attention_heads": 40,
   "num_hidden_layers": 40,
   "num_key_value_heads": 40,
+  "pad_token_id": 0,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
+  "rope_scaling": {
+    "factor": 8.0,
+    "type": "linear"
+  },
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
+  "torch_dtype": "float32",
   "transformers_version": "4.31.0",
   "use_cache": true,
   "vocab_size": 32001

generation_config.json

@@ -1,6 +0,0 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "transformers_version": "4.31.0"
-}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7004f96184372b0d7f8615bbea40dde597d9dc2644bd4cd739bb55108e77602d
+size 9956547112

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a29ae775bdb4f5504ddb6f2d68c413bc670a47e4a12f99f1a4086d0fee940233
+size 9940838856

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a8d40ee13184b7381f70f0416b32601ab65d4762a45935489bcf987348c2be7
+size 9940839248

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9772c2bae2cf86070b4aea601f1bb0e2e0b3b16b84babb2dc0a2d01a839fb1dc
+size 9867397864

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43a99188500fea557549bd052d6841cf3e156572d969cd7cf64d22a150e20f69
+size 9867439056

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fe91cef23013939dee1d382877b612c359daff7a632feb9c53cda39a13b6c84
+size 2490492968

model.safetensors.index.json

@@ -0,0 +1,410 @@
+{
+  "metadata": {
+    "total_size": 52063508480
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.rotary_emb.inv_freq": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

pytorch_model-00001-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:612dfb98f13599d992ffc50b0e58fe2e88d9d086616b29afa4c221f92f30efac
+size 9956565387

pytorch_model-00002-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3787b2fbfb678f78be7a68c4f8bb459c5b9edbd138a70d8f8e57c10b4e7f587c
+size 9940857409

pytorch_model-00003-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab4508d3162ab16a9b150ffd1ffacd424df01d99749d9750e73f8f410b0a8f68
+size 9940858031

pytorch_model-00004-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f34a9ebec64c75079758082fafe0dd24f3af2a63d6b14e9ecde2639184be6327
+size 9867416377

pytorch_model-00005-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ca970ac3061ff91911d9394241a667d11dd4aa21fcd3f602a264eab18d2d7ae
+size 9867458049

pytorch_model-00006-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:274f28f24117c10842f3623342f1cb9e3aa1c5913da1a05304663442784ea2b7
+size 2490496879

pytorch_model.bin.index.json

@@ -1,370 +1,410 @@
 {
   "metadata": {
-    "total_size": 26031749120
+    "total_size": 52063508480
   },
   "weight_map": {
-    "lm_head.weight": "pytorch_model-00003-of-00003.bin",
-    "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.norm.weight": "pytorch_model-00003-of-00003.bin"
+    "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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-00002-of-00006.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-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-00002-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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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-00003-of-00006.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-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-00003-of-00006.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-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.rotary_emb.inv_freq": "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-00003-of-00006.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-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.rotary_emb.inv_freq": "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-00005-of-00006.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00006.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00006-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.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-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.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-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.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-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.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
+    "model.norm.weight": "pytorch_model-00006-of-00006.bin"
   }
 }

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "[PAD]",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -19,7 +19,7 @@
     "single_word": false
   },
   "legacy": false,
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 32768,
   "pad_token": null,
   "padding_side": "right",
   "sp_model_kwargs": {},