Upload LlamaForCausalLM

config.json

@@ -1,7 +1,7 @@
 {
   "_name_or_path": "./epoch_1_hf",
   "architectures": [
-    "LlamaModel"
+    "LlamaForCausalLM"
   ],
   "bos_token_id": 1,
   "eos_token_id": 2,

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.33.1"
+}

pytorch_model-00001-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f29a27276094692ca4f4908b19e5d15a2c8f435f84596ccbd97df805fd94eb3
-size 9877981746
+oid sha256:2c0441321416f343274943b726bcf8e83c395f85065a5874522527f97401826d
+size 9877982386

pytorch_model-00002-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:405ecb7cbb771ea019b426d738a6d0bfc468dc10665be7e0165296b5307121a9
-size 9894793126
+oid sha256:4f424d51606d9314469c22aef3ce4ce274e775c6aca9572678cd18afddd332aa
+size 9894793766

pytorch_model-00003-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8dbf91cf2697eda55c17f2089e96294c090db6cc8969387289deafbe46f1afc
-size 6656697127
+oid sha256:4a312f726b76e314f05fe31b0ef9efb09a1bd9dedb93f70bb148727dceddde2c
+size 7180985861

pytorch_model.bin.index.json

@@ -1,297 +1,298 @@
 {
   "metadata": {
-    "total_size": 26429374464
+    "total_size": 26953662464
   },
   "weight_map": {
-    "embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "norm.weight": "pytorch_model-00003-of-00003.bin"
+    "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-00002-of-00003.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-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-00002-of-00003.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-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-00002-of-00003.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-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-00002-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-00002-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-00003-of-00003.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-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-00003-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-00003-of-00003.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-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-00003-of-00003.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-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-00003-of-00003.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-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.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"
   }
 }