11

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/root/chai/mistralai/Mistral-Nemo-Instruct-2407",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 131072
+}

dataset_dict.json

@@ -0,0 +1 @@
+{"splits": ["train"]}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.46.3"
+}

model-00001-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24f916ef748281d89a6fd8b0360d0e86a719f00cd5af64e0e8d6cdf33fec62a8
+size 4991306232

model-00002-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65626074a66eb6bad6c33549e845f8d4d38dd61c394bfeeeee121951561267b9
+size 4739731736

model-00003-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b757484028976e4ddab02393886cb1cba3f037c7344d9c06bbb99bdc4b069d54
+size 4949488128

model-00004-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fab606cd505e41becf182eb6a63960586494d1479c77652b6e80779a370ae9e
+size 4865561240

model-00005-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3495f4f56ea304eea1ce6363573df190c7dc3de43eba1d3099a8b8d35f85beda
+size 4949488160

model-00006-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6c6bef2106295f21fdc9c49689a72da3cfc686b749a9d83ac34495f9c8dc9b6
+size 4865561240

model-00007-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aebe8ba92797406ee24d8bc29ccbff99d645c50ea36840129f2f1c22b03274b
+size 4949488160

model-00008-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:982585485dc72a6b7d7f5afdc836510ce3c9efab1d6602033062e9fbdd12218e
+size 4865561240

model-00009-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8716a849cc2161a97fe2f7f3ca4bcc369e9ba3968db956835ca4bf1ee34bce0c
+size 4949488160

model-00010-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd220ae78ce2946bde217a2c19d3e5a6fd8cec406532dfd71a193ffb5a0bde19
+size 4865497344

model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 48991129600
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00010-of-00010.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.norm.weight": "model-00010-of-00010.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0240ce510f08e6c2041724e9043e33be9d251d1e4a4d94eb68cd47b954b61d2
+size 17078292

train/cache-0414f60d44f352d0_00000_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8501b0ce75bb38bf2f16c22aed32a97ce261536bc3e659212eb6546d29fbd871
+size 20811312

train/cache-0414f60d44f352d0_00001_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09b548afb0f37ae08de097d3ff8d79ad6c9308f33b1e807ecc23f7d8c4483a0d
+size 20410104

train/cache-0414f60d44f352d0_00002_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad60accaaef98d3c9bbaf291b597039250e9051a47c837685d324f47268635a8
+size 20351200

train/cache-0414f60d44f352d0_00003_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:982654d4e97dc7bc365987658cbd0aff17256dbbb8d87850f91576fb04073591
+size 20220088

train/cache-0414f60d44f352d0_00004_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea0254c87d0054b94c9cf3773c80a3e367bbd242f46fe1e7c91b22d2dc218099
+size 19806016

train/cache-0414f60d44f352d0_00005_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76677d88fcf0f92776623df61ae82c3f0ef6a1aa00f9dfcbdc37bcb21eb416dd
+size 19947368

train/cache-0414f60d44f352d0_00006_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b45c1275920e4fd367a36b2a9b737fc389cda27a64a4abe6e86872e1ae56aaf
+size 19249000

train/cache-0414f60d44f352d0_00007_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1f34f798282cee7abbebbb2ff76bb639fafb1bf77ff4ac0e33d1d90608ec8eb
+size 20874728

train/cache-09699ca714411ece_00000_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:996d1d7d0881ae374555f648b7b49808d085c97d5317f7211fcd313a2383cc9f
+size 20811312

train/cache-09699ca714411ece_00001_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:509b0bbd9e54075bbb64230aa9ce7ab9728a41a0fac77833c7dcfb2e69f824ef
+size 20410104

train/cache-09699ca714411ece_00002_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d05a0da8fabe2f2fcfeeb6c322841d14f4fb3fa5727ce644e1622f41519347e
+size 20351200

train/cache-09699ca714411ece_00003_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25d7086c84ce51ef7ac78809adb962c65befeb1b5e5911bf755995cb5965017a
+size 20220088

train/cache-09699ca714411ece_00004_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:524280b1a08b6c323de4726b555931767e0b6fe9b1df2361af4d66b1d73c737e
+size 19806016

train/cache-09699ca714411ece_00005_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eaa20b091751f4c12dcf4d9695d5521e919fb9f1b5d6497548567c0a2e6af15
+size 19947368

train/cache-09699ca714411ece_00006_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd20967e86dc2b17121580b762c14816fa7b7c71bd6d2fcb7351adb7a7140082
+size 19249000

train/cache-09699ca714411ece_00007_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a03db5f9ad2bb87e4b895a091e32291120a7064b3f6131d19f8886d0d031eedf
+size 20874728

train/cache-0f161304cfc02f95.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd97e41d0937a2745f9803927686e51d14ad63ab3d6838cd922d0d69490d7efc
+size 782136

train/cache-1b1a7b12968b1a91_00000_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c8458cd44b49a0e6e9c0030d236dc56f10bc6f598555e4068d2f558bcbfed80
+size 606528

train/cache-1b1a7b12968b1a91_00001_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab36a8aac8f2c11554eb6188b56be4d9fdbc2c63f83171e11566f080e1e07bc9
+size 616952

train/cache-1b1a7b12968b1a91_00002_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3d2249cc46808e86bb5a3b0a40ce7f8f3678d2d0a6346d11973b620ba7562a7
+size 595936

train/cache-1b1a7b12968b1a91_00003_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:770f68285c21c2337dd3b419f1cca13027cd396c062e4aeca913977aee98b347
+size 596112

train/cache-1b1a7b12968b1a91_00004_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f24b7fbf8738de784cedecfac56cdb61120c39589e4dc5c74de26ab30a1ebb
+size 635856

train/cache-1b1a7b12968b1a91_00005_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44aed4a6c190b3e774213befe181b9cb56703bc720203b381c044ac812a81581
+size 632512

train/cache-1b1a7b12968b1a91_00006_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b4895d863302dfbfe643b90a315874b41d62fb264c93be315ebee713453e64d
+size 623024

train/cache-1b1a7b12968b1a91_00007_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:841a92cda75d7735337eff1f6a8afec543dbb11235075990a1ca69c6a28145eb
+size 575680

train/cache-1c0a2e1600799789_00000_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f25713e45907a134130a6cc4186aed19ba28d65a28151d38d11e240bba34352
+size 606528

train/cache-1c0a2e1600799789_00001_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40c8f293e9108d96bf3d0aad137166fad1c77d9f097db5207b37b6479e029684
+size 616952

train/cache-1c0a2e1600799789_00002_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebcc6115a3dded449feac20ac06c2ece7c46f579a39eda95962de0370e14a525
+size 595936

train/cache-1c0a2e1600799789_00003_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5abaf0ac3a3b21c7f88157e03b5176039bf945903e61160bcfeba4598c65f26e
+size 596112

train/cache-1c0a2e1600799789_00004_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2808ccd71ef771f7a13fd792d17e6517cb730e328d646cbaa0db4e9dbd7d85a
+size 635856

train/cache-1c0a2e1600799789_00005_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccb4040cdf5021b8f2a980520e3112a07380aa364b982096bca5b8c7de582d3f
+size 632512

train/cache-1c0a2e1600799789_00006_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df253ba0161d45bcb26d29179c96d66d12fbeabf28e9fb1b84d4936da693e0e2
+size 623024

train/cache-1c0a2e1600799789_00007_of_00008.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d95c2629a3082f1b2529341402533a4cb61666bc9987175cc24c653d0c674a32
+size 575680