add model v1.0

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "intfloat/e5-mistral-7b-instruct",
+  "architectures": [
+    "MistralModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

lora/adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "intfloat/e5-mistral-7b-instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "up_proj",
+    "q_proj",
+    "gate_proj",
+    "down_proj"
+  ],
+  "task_type": "FEATURE_EXTRACTION"
+}

lora/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7afdf0ac097091e50c30e1b756c352a3b772950739b3b99961f1781271ab6683
+size 41999896

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d76b9716a4c840a38ed5cbcc50350d56c9a6bca5ad19e750d303245de769ff49
+size 4978975232

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcb5d9787f23fef2cde63c2906e4d5b3a7c82fa38157519b1360db01f955c678
+size 4899116152

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86fe0dc083d0587234328f5a4ee4598f3069e23d0c860ea884f3d49b0b6322ca
+size 4999812808

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ee93d8bc45133da3f344f693782648b9874eae2f191bdaaaf6640f446001af9
+size 4999812808

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a146f539398aa13bdbd6597fa9f5fb4815e63196d181af753cb9d9d7ee10743a
+size 4832007216

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2930473d3c1a64e010315822b2617894960ed7bb60d053a8eefc0bce1083f32
+size 3724726552

model.safetensors.index.json

@@ -0,0 +1,297 @@
+{
+  "metadata": {
+    "total_size": 28442640384
+  },
+  "weight_map": {
+    "embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.27.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "layers.28.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.28.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.28.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.28.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.28.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.28.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.28.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.28.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.29.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.29.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.29.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.29.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}