Upload LlamaForCausalLM

README.md

@@ -1,5 +1,8 @@
 ---
 license: apache-2.0
+tags:
+- trl
+- sft
 ---
 
 # Model Card for Model ID

config.json

@@ -4,20 +4,26 @@
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
+  "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
+  "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 11008,
   "max_position_embeddings": 4096,
+  "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 32,
   "pretraining_tp": 1,
   "quantization_config": {
+    "_load_in_4bit": false,
+    "_load_in_8bit": true,
     "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_storage": "uint8",
     "bnb_4bit_quant_type": "fp4",
     "bnb_4bit_use_double_quant": false,
     "llm_int8_enable_fp32_cpu_offload": false,
@@ -33,7 +39,7 @@
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.35.2",
+  "transformers_version": "4.45.0",
   "use_cache": false,
   "vocab_size": 32000
 }

generation_config.json

@@ -6,5 +6,5 @@
   "pad_token_id": 0,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.35.2"
+  "transformers_version": "4.45.0"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12d2988594513e13dbd28c10f6657b57b97349981b577561ebb089b03f641d94
-size 4992587592
+oid sha256:b37907447b8c2b05b60cca1345794418fc36f19dafce38a593641b5bb9b22132
+size 4992605474

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cdd75225883eede66aeb783bd2e34bc338cc31784d56423a185a34415e0dfa5
-size 2555349880
+oid sha256:75f103cbbb7b81c14b997f201ae5564712c93c6077eda6f6c95e36eaebfdb2db
+size 2555358038

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 7547863040
+    "total_size": 7547863264
   },
   "weight_map": {
     "lm_head.weight": "model-00002-of-00002.safetensors",
@@ -8,641 +8,865 @@
     "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.q_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.v_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.q_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.v_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.q_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.v_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.q_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.v_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.q_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.v_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.q_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.v_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.q_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.v_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.q_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.v_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.q_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.v_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.q_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.v_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.q_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.v_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.q_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.v_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.q_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.v_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.q_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.v_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.q_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.v_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.22.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.22.mlp.gate_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.22.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.22.self_attn.k_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.22.self_attn.o_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.22.self_attn.q_proj.base_layer.SCB": "model-00002-of-00002.safetensors",
     "model.layers.22.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.base_layer.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.22.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.22.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.22.self_attn.v_proj.base_layer.SCB": "model-00002-of-00002.safetensors",
     "model.layers.22.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.base_layer.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.22.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.22.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.23.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.23.mlp.gate_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.23.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.23.self_attn.k_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.23.self_attn.o_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.23.self_attn.q_proj.base_layer.SCB": "model-00002-of-00002.safetensors",
     "model.layers.23.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.base_layer.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.23.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.23.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.23.self_attn.v_proj.base_layer.SCB": "model-00002-of-00002.safetensors",
     "model.layers.23.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.base_layer.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.23.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.23.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.24.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.24.mlp.gate_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.24.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.k_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.o_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.q_proj.base_layer.SCB": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.base_layer.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.v_proj.base_layer.SCB": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.base_layer.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.25.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.25.mlp.gate_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.25.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.k_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.o_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.q_proj.base_layer.SCB": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.base_layer.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.v_proj.base_layer.SCB": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.base_layer.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.26.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.26.mlp.gate_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.26.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.k_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.o_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.q_proj.base_layer.SCB": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.base_layer.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.v_proj.base_layer.SCB": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.base_layer.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.gate_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.k_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.o_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.q_proj.base_layer.SCB": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.base_layer.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.v_proj.base_layer.SCB": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.base_layer.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.28.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.28.mlp.gate_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.28.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.k_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.o_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.q_proj.base_layer.SCB": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.base_layer.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.v_proj.base_layer.SCB": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.base_layer.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.29.mlp.gate_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.29.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.k_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.o_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.q_proj.base_layer.SCB": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.base_layer.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.v_proj.base_layer.SCB": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.base_layer.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.q_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.v_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.30.mlp.gate_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.30.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.k_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.o_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.q_proj.base_layer.SCB": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.base_layer.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.v_proj.base_layer.SCB": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.base_layer.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.gate_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.k_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.o_proj.SCB": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.q_proj.base_layer.SCB": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.base_layer.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.v_proj.base_layer.SCB": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.base_layer.weight_format": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
     "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.q_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.v_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.q_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.v_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.q_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.v_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.q_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.v_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.q_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.v_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.q_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.v_proj.base_layer.SCB": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.base_layer.weight_format": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.norm.weight": "model-00002-of-00002.safetensors"