Upload model

config.json

@@ -1,13 +1,18 @@
 {
+  "architectures": [
+    "SpeechLLMModel"
+  ],
   "audio_enc_dim": 1280,
   "audio_encoder_name": "facebook/hubert-xlarge-ll60k",
   "audio_processor_name": "facebook/hubert-large-ls960-ft",
   "auto_map": {
-    "AutoConfig": "config.SpeechLLMModelConfig"
+    "AutoConfig": "config.SpeechLLMModelConfig",
+    "AutoModel": "model.SpeechLLMModel"
   },
   "llm_dim": 2048,
   "llm_model_checkpoint": "hf_repo/llm_model_checkpoint",
   "llm_model_name": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
   "model_type": "custom_model",
+  "torch_dtype": "float32",
   "transformers_version": "4.38.2"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18785830f9c696dfb288148f64e92b017789e290fbfdbffa4f8c03e903ed65b2
-size 4973217960
+oid sha256:778179f27c443457a4ac527afe4c58d25902f410bdc492e7f4e09ffd23dfc6c7
+size 4975727392

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbc74aa8e2666342b54594419847adfa6279238c9416dda34a09202d00dd638f
-size 3395612080
+oid sha256:9ad7d5e98460221a543bba83cb187111a948f22a34be26ab16fda691f2d83bc2
+size 3405770712

model.py

@@ -34,28 +34,28 @@ class SpeechLLMModel(PreTrainedModel):
         self.audio_processor = AutoProcessor.from_pretrained(config.audio_processor_name)
         self.audio_encoder = HubertXCNNEnoder(config.audio_enc_dim, config.llm_dim, config.audio_encoder_name)
 
-        self.llm_model = AutoModelForCausalLM.from_pretrained(config.llm_model_checkpoint)
-        self.llm_tokenizer = AutoTokenizer.from_pretrained(config.llm_model_name)
+        # self.llm_model = AutoModelForCausalLM.from_pretrained(config.llm_model_checkpoint)
+        # self.llm_tokenizer = AutoTokenizer.from_pretrained(config.llm_model_name)
 
 
-        # self.llm_model = AutoModelForCausalLM.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0")
-        # self.llm_tokenizer = AutoTokenizer.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0")
+        self.llm_model = AutoModelForCausalLM.from_pretrained(config.llm_model_name)
+        self.llm_tokenizer = AutoTokenizer.from_pretrained(config.llm_model_name)
 
-        # peft_config = LoraConfig(
-        #     r=4,
-        #     lora_alpha=8,
-        #     target_modules=['q_proj', 'k_proj', 'v_proj', 'o_proj', 'up_proj', 'down_proj', 'gate_proj'],
-        #     lora_dropout=0.05,
-        #     task_type="CAUSAL_LM",
-        # )
-        # self.llm_model = get_peft_model(self.llm_model, peft_config)
+        peft_config = LoraConfig(
+            r=4,
+            lora_alpha=8,
+            target_modules=['q_proj', 'k_proj', 'v_proj', 'o_proj', 'up_proj', 'down_proj', 'gate_proj'],
+            lora_dropout=0.05,
+            task_type="CAUSAL_LM",
+        )
+        self.llm_model = get_peft_model(self.llm_model, peft_config)
 
     def encode(self, mel, pre_tokenized_ids, post_tokenized_ids, output_tokenized_ids):
         batch_size = mel.shape[0]
 
         with torch.no_grad():
             speech_embeds = self.audio_encoder(mel)
-        embedder = self.llm_model.model.embed_tokens
+        embedder = self.llm_model.model.model.embed_tokens
         pre_prompt_embeds = embedder(pre_tokenized_ids)
         post_prompt_embeds = embedder(post_tokenized_ids)
         output_prompt_embeds = embedder(output_tokenized_ids)

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 8368692736
+    "total_size": 8381308416
   },
   "weight_map": {
     "audio_encoder.cnn.1.bias": "model-00001-of-00002.safetensors",
@@ -815,206 +815,514 @@
     "audio_encoder.encoder.feature_projection.projection.bias": "model-00001-of-00002.safetensors",
     "audio_encoder.encoder.feature_projection.projection.weight": "model-00001-of-00002.safetensors",
     "audio_encoder.encoder.masked_spec_embed": "model-00001-of-00002.safetensors",
-    "llm_model.lm_head.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "llm_model.model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "llm_model.model.norm.weight": "model-00002-of-00002.safetensors"
+    "llm_model.base_model.model.lm_head.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.0.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.0.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.0.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.0.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.0.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.0.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.0.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.0.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.0.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.0.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.0.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.0.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.0.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.0.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.0.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.0.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.0.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.0.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.0.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.0.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.0.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.1.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.1.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.1.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.1.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.1.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.1.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.1.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.1.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.1.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.1.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.1.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.1.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.1.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.1.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.1.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.1.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.1.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.1.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.1.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.1.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.1.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.10.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.10.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.10.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.10.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.10.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.10.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.10.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.10.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.10.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.10.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.10.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.10.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.10.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.10.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.10.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.10.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.10.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.10.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.10.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.10.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.10.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.11.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.11.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.11.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.11.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.11.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.11.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.11.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.11.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.11.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.11.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.11.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.11.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.11.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.11.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.11.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.11.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.11.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.11.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.11.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.11.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.11.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.12.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.12.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.12.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.12.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.12.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.12.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.12.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.12.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.12.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.12.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.12.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.12.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.12.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.12.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.12.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.12.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.12.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.12.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.12.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.12.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.12.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.13.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.13.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.13.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.13.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.13.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.13.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.13.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.13.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.13.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.13.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.13.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.13.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.13.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.13.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.13.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.13.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.13.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.13.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.13.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.13.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.13.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.14.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.14.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.14.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.14.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.14.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.14.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.14.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.14.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.14.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.14.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.14.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.14.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.14.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.14.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.14.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.14.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.14.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.14.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.14.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.14.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.14.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.15.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.15.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.15.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.15.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.15.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.15.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.15.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.15.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.15.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.15.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.15.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.15.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.15.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.15.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.15.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.15.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.15.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.15.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.15.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.15.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.15.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.16.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.16.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.16.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.16.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.16.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.16.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.16.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.16.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.16.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.16.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.16.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.16.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.16.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.16.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.16.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.16.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.16.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.16.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.16.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.16.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.16.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.17.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.17.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.17.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.17.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.17.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.17.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.17.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.17.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.17.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.17.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.17.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.17.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.17.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.17.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.17.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.17.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.17.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.17.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.17.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.17.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.17.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.18.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.18.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.18.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.18.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.18.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.18.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.18.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.18.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.18.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.18.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.18.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.18.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.18.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.18.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.18.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.18.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.18.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.18.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.18.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.18.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.18.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.19.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.19.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.19.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.19.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.19.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.19.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.19.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.19.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.19.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.19.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.19.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.19.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.19.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.19.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.19.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.19.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.19.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.19.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.19.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.19.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.19.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.2.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.2.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.2.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.2.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.2.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.2.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.2.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.2.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.2.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.2.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.2.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.2.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.2.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.2.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.2.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.2.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.2.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.2.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.2.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.2.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.2.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.20.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.20.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.20.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.20.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.20.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.20.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.20.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.20.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.20.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.20.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.20.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.20.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.20.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.20.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.20.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.20.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.20.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.20.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.20.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.20.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.20.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.21.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.21.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.21.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.21.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.21.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.21.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.21.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.21.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.21.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.21.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.21.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.21.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.21.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.21.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.21.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.21.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.21.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.21.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.21.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.21.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.21.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.3.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.3.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.3.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.3.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.3.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.3.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.3.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.3.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.3.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.3.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.3.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.3.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.3.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.3.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.3.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.3.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.3.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.3.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.3.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.3.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.3.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.4.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.4.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.4.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.4.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.4.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.4.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.4.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.4.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.4.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.4.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.4.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.4.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.4.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.4.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.4.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.4.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.4.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.4.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.4.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.4.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.4.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.5.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.5.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.5.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.5.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.5.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.5.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.5.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.5.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.5.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.5.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.5.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.5.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.5.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.5.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.5.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.5.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.5.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.5.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.5.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.5.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.5.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.6.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.6.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.6.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.6.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.6.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.6.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.6.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.6.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.6.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.6.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.6.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.6.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.6.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.6.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.6.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.6.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.6.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.6.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.6.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.6.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.6.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.7.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.7.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.7.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.7.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.7.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.7.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.7.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.7.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.7.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.7.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.7.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.7.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.7.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.7.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.7.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.7.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.7.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.7.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.7.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.7.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.7.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.8.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.8.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.8.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.8.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.8.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.8.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.8.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.8.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.8.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.8.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.8.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.8.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.8.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.8.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.8.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.8.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.8.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.8.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.8.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.8.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.8.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.9.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.9.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.9.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.9.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.9.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.9.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.9.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.9.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.9.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.9.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.9.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.9.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.9.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.9.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.9.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.9.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.9.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.9.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.9.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.9.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.layers.9.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
+    "llm_model.base_model.model.model.norm.weight": "model-00002-of-00002.safetensors"
   }
 }