add model weights(>5B tokens)

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.33.1",
+  "use_cache": true,
+  "vocab_size": 46336
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "transformers_version": "4.33.1"
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeedb0ef23def3b6fb4e2f03a1df24ba1932e80e6e21a77547b131cc5ad2710a
+size 2942409392

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2da391c5875df6864f845885168a46f5def591a7606e2045df9718081507071b
+size 2923552000

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d1d17e0c90e24587b46c5accb062146aca2bb58e572e6c33c4c0f164b76d02d
+size 2923552024

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5baff9afdee7a65cf38597f53671b121cb9d4c36bfd411c5e7ea7e26566f230b
+size 2990677736

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f6a77d7b3b19f76c2df3394dfc0f422a4669bc9936551b2f77d346142567f77
+size 1931554880

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 13711712256
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00005-of-00005.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.norm.weight": "model-00005-of-00005.safetensors"
+  }
+}

pytorch_model-00001-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddf04d539045901c1d2f634b3fb506abbcf3f47fdbfb2f74ba3418309eb12978
+size 2942422261

pytorch_model-00002-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bc69d6a133e6af14305609b0ce624f1e3f05ddb25fbef4a16f5a4dde2887f4a
+size 2923566031

pytorch_model-00003-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78bc420c252f69aea0f9a433f4973ff4b9173af27c11114fcf927f3fd129bd9f
+size 2923566031

pytorch_model-00004-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaf89f16d550d39f9d44dda90a8d8060ea39edd14c352f9fbb78fbcbf419f56b
+size 2990692631

pytorch_model-00005-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5d8af0cbf9caa468e77a482b230a0c26cdb500090ce11872c866a418843122c
+size 1931562711

pytorch_model.bin.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 13711712256
+  },
+  "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-00003-of-00005.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-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-00003-of-00005.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-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-00003-of-00005.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-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-00004-of-00005.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-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-00004-of-00005.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00005-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-00005-of-00005.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00005-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.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-00002-of-00005.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-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-00002-of-00005.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-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"
+  }
+}