Trained with Unsloth

README.md

@@ -8,6 +8,7 @@ tags:
 - unsloth
 - llama
 - trl
+- sft
 base_model: Replete-AI/Llama-3-11.5B-Instruct-V2
 ---
 

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "Replete-AI/Llama-3-11.5B-Instruct-V2",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128255,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.40.2",
+  "unsloth_version": "2024.5",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128009
+  ],
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.40.2"
+}

pytorch_model-00001-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdc824713582e9edcd100fedb13295c7aeb8440571e1de6d0db1ee16e8d7dafa
+size 4976718402

pytorch_model-00002-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b70d257d466699f7ccbe8f986cf1db4addd038598c9f63ee26c58f530e546f67
+size 4999826694

pytorch_model-00003-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d636883c673a44d53169a7a455f02f4fa6f05b16b99ccc3c62063e37c516bfa
+size 4915939082

pytorch_model-00004-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d348405d743ab4042cdda87543a515903abd132a106071094402a575f205ec0
+size 4999843656

pytorch_model-00005-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:393989b224282663944eb3189f4913ec136cfe79f2f3e0b3c1ef0875ebc364a4
+size 3147930224

pytorch_model.bin.index.json

@@ -0,0 +1,442 @@
+{
+  "metadata": {
+    "total_size": 23040106496
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00005-of-00005.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.40.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.40.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.40.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.41.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.41.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.41.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.42.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.42.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.42.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.43.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.43.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.43.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.44.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.44.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.44.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.45.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.45.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.45.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.46.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.46.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.46.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.47.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.47.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.47.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.norm.weight": "pytorch_model-00005-of-00005.bin"
+  }
+}