update

app.py

@@ -167,8 +167,6 @@ def do_inference(full_text):
     model_paths = [
     'model_finetuned/HuggingFaceH4-zephyr-7b-beta_fold0_best.pth']
 
-    # config_path = ("/home/rashmi/Documents/kaggle/h2oai_predict_llm/src/models_exp56/config.pth")
-
     def prepare_input(cfg, text):
         inputs = cfg.tokenizer.encode_plus(
             text,
@@ -182,7 +180,6 @@ def do_inference(full_text):
             inputs[k] = torch.tensor(v, dtype=torch.long)
         return inputs
 
-    # model = CustomModel()
     state = torch.load(model_paths[0], map_location=torch.device("cpu"))
     model.load_state_dict(state["model"] ,strict=False)
     model.eval()
@@ -236,8 +233,6 @@ with gr.Blocks(title=title) as demo: # theme=theme
     example_list = sample_examples[['Question','Response','target']].sample(2).values.tolist()
     gr.Markdown(f"## {title}")
     with gr.Row():
-        # with gr.Column(scale=1):
-            # gr.Markdown("### Question and LLM Response")
             question_text = gr.Textbox(lines=2, placeholder="Question:", label="")
             response_text = gr.Textbox(lines=2, placeholder="Response:", label="")
             target_text = gr.Textbox(lines=1, placeholder="Target:", label="", interactive=False , visible=False)
@@ -250,7 +245,6 @@ with gr.Blocks(title=title) as demo: # theme=theme
     gr.Examples(
         example_list,
         [question_text,response_text,target_text],
-        # cache_examples=True,   
     )
 
 demo.launch(greet)

save_pretrained_model/zephyr-7b-beta/config.json

@@ -1,26 +0,0 @@
-{
-  "_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
-  "architectures": [
-    "MistralForCausalLM"
-  ],
-  "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": "4.36.0.dev0",
-  "use_cache": true,
-  "vocab_size": 32000
-}

save_pretrained_model/zephyr-7b-beta/generation_config.json

@@ -1,6 +0,0 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "transformers_version": "4.36.0.dev0"
-}

save_pretrained_model/zephyr-7b-beta/model-00001-of-00006.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2023a2a717ff20e941c21d68bc48916354e976800a8393ba11df59060584ac3a
-size 4987196936

save_pretrained_model/zephyr-7b-beta/model-00002-of-00006.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:89d0d703099ade2eb1e06019d8fc176598a599a92a5c70b55e8a5cb77215b421
-size 4899116440

save_pretrained_model/zephyr-7b-beta/model-00003-of-00006.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:448db92c8f5e610971f050d84dd16607e0e895b34d07cf0cd3e21b88c3131aeb
-size 4999813120

save_pretrained_model/zephyr-7b-beta/model-00004-of-00006.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5e49c54167036eee8493ccfa313edec808f8b6c508ef747c7a84e7abe2b01c3a
-size 4999813128

save_pretrained_model/zephyr-7b-beta/model-00005-of-00006.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b0edab06947c8702d3a61fab57f84e052d46fbbd77e8e3e206bc7d0802879022
-size 4832007496

save_pretrained_model/zephyr-7b-beta/model-00006-of-00006.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a2caf0970ab661caf158ca08992d814798689d101e70b19a7fd2e4b7b45eff73
-size 4249014896

save_pretrained_model/zephyr-7b-beta/model.safetensors.index.json

@@ -1,298 +0,0 @@
-{
-  "metadata": {
-    "total_size": 28966928384
-  },
-  "weight_map": {
-    "lm_head.weight": "model-00006-of-00006.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.norm.weight": "model-00006-of-00006.safetensors"
-  }
-}