Convert model checkpoint to safetensors

added_tokens.json

@@ -1,3 +0,0 @@
-{
-  "<pad>": 32000
-}

config.json

@@ -2,6 +2,8 @@
   "architectures": [
     "LlamaForCausalLM"
   ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
@@ -12,11 +14,15 @@
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
-  "pad_token_id": 0,
+  "num_key_value_heads": 32,
+  "pad_token_id": 32000,
+  "pretraining_tp": 1,
   "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.29.2",
+  "transformers_version": "4.37.2",
   "use_cache": true,
   "vocab_size": 32001
 }

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 1,
   "eos_token_id": 2,
   "pad_token_id": 0,
-  "transformers_version": "4.29.2"
+  "transformers_version": "4.37.2"
 }

pytorch_model-00004-of-00004.bin → model-00001-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:587434d07217abf5eb5f697dae8f42a09abf02c3bb3a19c28c7634545bd1cbe8
-size 1566666885
+oid sha256:c7513e52a42b62a99de58e891d9539577a4204d7f38a27f18fd4353e056b00b4
+size 1981886992

pytorch_model-00001-of-00004.bin → model-00002-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f391475acdccd6c537d9f5f8b4027611c8ce029a19c9e206066e63761ae426c4
-size 3972195033
+oid sha256:b919c2b9ebd40e1392410895ababd4507333fadfba332b36116125c110a52248
+size 1990284240

pytorch_model-00002-of-00004.bin → model-00003-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db4cd595b76abe666cda3fb7c566277205c4abe5ab70e5023937cff7da6b5ed1
-size 3980593843
+oid sha256:b118a476c11bfbab90e0414134121c730cc7235229b72d3adabb1d96e8259a00
+size 1990284280

pytorch_model-00003-of-00004.bin → model-00004-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f4065057cbd191621d12f7bca07a73cd0871a6a46222f9c81c6e2c572127173
-size 3957508513
+oid sha256:50b70595e464fc08053a35f33b976285bd21290a32d6b797248a7f65de58fce7
+size 1990284288

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1014ff3d1b8a7e8a6bb1320989c2f074f6e8b25546b3e9b83620b583f0591d31
+size 1933644568

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2ba904cb300acc4df6c8001cf164ab7adfcff69280b987f61188f6c85587d2a
+size 1933661176

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbcdab0eb092888e4e2fd6e7eb8197d55d875dcd422630156fbdb51c3cdcc64a
+size 1656835800

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 13476847616
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00007-of-00007.safetensors"
+  }
+}

pytorch_model.bin.index.json

@@ -1,330 +0,0 @@
-{
-  "metadata": {
-    "total_size": 13476855808
-  },
-  "weight_map": {
-    "lm_head.weight": "pytorch_model-00004-of-00004.bin",
-    "model.embed_tokens.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
-    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
-    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
-    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
-    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
-    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
-    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
-    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
-    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
-    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
-    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
-    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
-    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
-    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
-    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
-    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
-    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
-    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
-    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
-    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
-    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
-    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
-    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
-    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
-    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
-    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
-    "model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
-    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
-    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
-    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
-    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
-    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
-    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
-    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
-    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00004.bin",
-    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
-    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
-    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.30.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
-    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
-    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
-    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
-    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
-    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
-    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
-    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
-    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00004.bin",
-    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
-    "model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
-    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
-    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
-    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
-    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
-    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
-    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
-    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
-    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00004.bin",
-    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
-    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
-    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
-    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
-    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
-    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
-    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
-    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
-    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
-    "model.norm.weight": "pytorch_model-00004-of-00004.bin"
-  }
-}

special_tokens_map.json

@@ -13,7 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<pad>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.model

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
-size 499723

tokenizer_config.json

@@ -1,34 +1,50 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
   },
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "eos_token": "</s>",
+  "legacy": true,
   "model_max_length": 512,
-  "pad_token": null,
+  "pad_token": "<pad>",
   "padding_side": "right",
   "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
 }