Upload folder using huggingface_hub

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "microsoft/phi-2",
+  "architectures": [
+    "PhiForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
+    "AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
+  },
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "hidden_act": "gelu_new",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 10240,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "phi",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "partial_rotary_factor": 0.4,
+  "qk_layernorm": false,
+  "resid_pdrop": 0.1,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 51200
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.38.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1c2ad02a37a6228c635c72831fed0159ce9dedc620e60ef814fa5e6dd6fab15
+size 4995589080

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81a1ffe2b9ee3214a165994c73924d569990876255a3290a3e28a91276312cfd
+size 563833304

model.safetensors.index.json

@@ -0,0 +1,460 @@
+{
+  "metadata": {
+    "total_size": 5559367680
+  },
+  "weight_map": {
+    "_orig_mod.lm_head.bias": "model-00002-of-00002.safetensors",
+    "_orig_mod.lm_head.weight": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.final_layernorm.bias": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.final_layernorm.weight": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.0.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.0.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.1.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.1.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.10.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.10.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.11.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.11.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.12.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.12.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.13.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.13.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.14.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.14.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.15.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.15.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.16.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.16.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.17.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.17.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.18.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.18.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.19.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.19.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.2.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.2.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.20.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.20.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.21.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.21.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.22.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.22.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.23.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.23.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.23.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.24.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.24.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.24.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.25.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.25.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.25.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.26.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.26.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.26.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.27.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.27.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.27.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.27.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.27.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.27.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.27.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.28.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.28.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.28.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.28.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.28.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.28.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.28.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.29.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.29.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.29.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.29.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.29.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.29.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.29.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.29.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.3.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.3.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.30.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.30.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.30.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.30.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.30.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.30.self_attn.dense.bias": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.30.self_attn.dense.weight": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.31.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.31.mlp.fc1.bias": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.31.mlp.fc1.weight": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.31.mlp.fc2.bias": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.31.mlp.fc2.weight": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.31.self_attn.dense.bias": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.31.self_attn.dense.weight": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "_orig_mod.model.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.4.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.4.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.5.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.5.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.6.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.6.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.7.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.7.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.8.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.8.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.9.self_attn.dense.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.9.self_attn.dense.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "_orig_mod.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors"
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da5eb84b27d1f27a72fa3c9c1688eb1d49f86242057e3a90e7ce8b000d5d9a71
+size 4984