Convert model checkpoint to safetensors

added_tokens.json

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

config.json

@@ -2,8 +2,11 @@
   "architectures": [
     "LlamaForScore"
   ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
   "bias": false,
   "bos_token_id": 1,
+  "do_normalize": false,
   "eos_token_id": 2,
   "hidden_act": "silu",
   "hidden_size": 4096,
@@ -11,14 +14,21 @@
   "intermediate_size": 11008,
   "max_position_embeddings": 2048,
   "model_type": "llama",
+  "normalizer_type": null,
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
   "pad_token_id": 32000,
+  "pretraining_tp": 1,
   "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "score_bias": true,
   "score_dim": 1,
+  "score_type": "reward",
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.29.2",
+  "transformers_version": "4.37.2",
   "use_cache": true,
   "vocab_size": 32001
 }

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48ec553ada18ebbcd7bc87330a6ac7b3e889d3eb1e5c9a62e8712351bc36bf25
-size 1304522885
+oid sha256:be090bf3f8466a74abfb7451464d91d3731158126d613ed13d39a2c10bb0782c
+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 sha256:5b02d2c2095123b26c7b181e8bac7995ca21bbec70f447ae964511894d6c951f
-size 3972195033
+oid sha256:e13c7d20b7be6b5a9b21942ad5bf8019bef27a9e8d7e79b953fe1842e8f978a4
+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:e654d31306493ffa2eb206f1ad0c1ca33679cbd67779a6da4285dd91c1514558
-size 3980593843
+oid sha256:c5798701afd4a48d6371096e4f157d0340374cdb65d464df4e59a373ee743c27
+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 sha256:42ff59484241c8a16d35f260f0d82180cd9418317d2c19c42a79f94d3a73d9f8
-size 3957508513
+oid sha256:e90fd5675b45666eca9fe4da21c686fe0099dae2aca3595bb1ce7c83afd1af80
+size 1990284288

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b2c255b57b22d1f1a437e2551b759db20ad5c1648205aa43e3185035007a2b9
+size 1933644568

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eac6e1724b3ac4c761ee82c5d8752ba3d5366703f65237aef62e1e42691c7f3
+size 1933661176

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d75da02acfeae64926495bfc20240ad32ce1192abd3379be06f441145c2bc587
+size 1394692118

model.safetensors.index.json

@@ -0,0 +1,302 @@
+{
+  "metadata": {
+    "total_size": 13214703630
+  },
+  "weight_map": {
+    "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",
+    "normalizer.count": "model-00007-of-00007.safetensors",
+    "normalizer.mean": "model-00007-of-00007.safetensors",
+    "normalizer.var": "model-00007-of-00007.safetensors",
+    "score_head.bias": "model-00007-of-00007.safetensors",
+    "score_head.weight": "model-00007-of-00007.safetensors"
+  }
+}

pytorch_model.bin.index.json

@@ -1,330 +0,0 @@
-{
-  "metadata": {
-    "total_size": 13214711808
-  },
-  "weight_map": {
-    "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",
-    "score_head.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
 }