Upload MistralForCausalLM

README.md

@@ -1,6 +1,8 @@
 ---
 library_name: transformers
-tags: []
+tags:
+- trl
+- sft
 ---
 
 # Model Card for Model ID

config.json

@@ -15,6 +15,20 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
+  "quantization_config": {
+    "_load_in_4bit": false,
+    "_load_in_8bit": true,
+    "bnb_4bit_compute_dtype": "float16",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
+  },
   "rms_norm_eps": 1e-05,
   "rope_theta": 10000.0,
   "sliding_window": 4096,

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:276d393679271dedd645df23921dd73f2249201b6d83d258818686d618bc7abb
-size 4943162240
+oid sha256:ca71bbec03bef4f3ba729d3e832cdb586f0f714d8cb6b875c36333ae5ab868ec
+size 4894789176

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cec093552b08a12b290a54531358eaae3e05c53d2100547f4e250eb5779c27b
-size 4999819232
+oid sha256:3e65dacb27e152d2c9c3b91c49421ece54446dd65aa1dba31d21194455e3e3eb
+size 4985115088

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adfd0651c13e9e7103757344664646a79f79a64ae2e865f28dabcdd471f052a2
-size 4540516256
+oid sha256:8e9c2b3cab60969c0e86e65e660fd7bf26ee82e3ddb15c2c79fe9b4ecb0624ad
+size 3938032280

model.safetensors.index.json

@@ -1,297 +1,521 @@
 {
   "metadata": {
-    "total_size": 14483464192
+    "total_size": 13817880576
   },
   "weight_map": {
     "lm_head.weight": "model-00003-of-00003.safetensors",
     "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
     "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
     "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.SCB": "model-00003-of-00003.safetensors",
     "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.SCB": "model-00001-of-00003.safetensors",
     "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.norm.weight": "model-00003-of-00003.safetensors"
   }