diff --git a/chat_template.jinja b/chat_template.jinja
index 5817f39a52fc6647e2f071195a7ddb7d4ca6ad20..85e6d86c1707eab26462f3979384667b228ed363 100644
--- a/chat_template.jinja
+++ b/chat_template.jinja
@@ -52,11 +52,10 @@
   <|im_system|>tool_declare<|im_middle|>{{ tools | tojson(separators=(',', ':')) }}<|im_end|>
 {%- endif -%}
 
-{%- if messages|length == 0 or messages[0]['role'] != 'system' -%}
-  <|im_system|>system<|im_middle|>You are Kimi, an AI assistant created by Moonshot AI.<|im_end|>
-{%- endif -%}
-  
 {%- for message in hist_msgs -%}
+  {%- if loop.first and messages[0]['role'] != 'system' -%}
+  <|im_system|>system<|im_middle|>You are Kimi, an AI assistant created by Moonshot AI.<|im_end|>
+  {%- endif -%}
   {{set_roles(message)}}
   {%- if message['role'] == 'assistant' -%}
     <think></think>{{render_content(message)}}
diff --git a/config.json b/config.json
index 40d9e35b2c17a5438622701f56a9861d33537561..c037c113c2418fb8a817eec4bdba972653652b1f 100644
--- a/config.json
+++ b/config.json
@@ -97,13 +97,375 @@
             "target_device": null
         },
         "exclude": [
-            "re:model.layers.*self_attn.*",
-            "re:model.layers.*mlp.gate",
             "lm_head",
-            "re:model.layers.*mlp.gate_proj",
-            "re:model.layers.*mlp.up_proj",
-            "re:model.layers.*mlp.down_proj",
-            "re:model.layers.*shared_experts.*"
+            "model.layers.0.mlp.down_proj",
+            "model.layers.0.mlp.gate_proj",
+            "model.layers.0.mlp.up_proj",
+            "model.layers.0.self_attn.kv_a_proj_with_mqa",
+            "model.layers.0.self_attn.kv_b_proj",
+            "model.layers.0.self_attn.o_proj",
+            "model.layers.0.self_attn.q_a_proj",
+            "model.layers.0.self_attn.q_b_proj",
+            "model.layers.1.mlp.gate",
+            "model.layers.1.self_attn.kv_a_proj_with_mqa",
+            "model.layers.1.self_attn.kv_b_proj",
+            "model.layers.1.self_attn.o_proj",
+            "model.layers.1.self_attn.q_a_proj",
+            "model.layers.1.self_attn.q_b_proj",
+            "model.layers.10.mlp.gate",
+            "model.layers.10.self_attn.kv_a_proj_with_mqa",
+            "model.layers.10.self_attn.kv_b_proj",
+            "model.layers.10.self_attn.o_proj",
+            "model.layers.10.self_attn.q_a_proj",
+            "model.layers.10.self_attn.q_b_proj",
+            "model.layers.11.mlp.gate",
+            "model.layers.11.self_attn.kv_a_proj_with_mqa",
+            "model.layers.11.self_attn.kv_b_proj",
+            "model.layers.11.self_attn.o_proj",
+            "model.layers.11.self_attn.q_a_proj",
+            "model.layers.11.self_attn.q_b_proj",
+            "model.layers.12.mlp.gate",
+            "model.layers.12.self_attn.kv_a_proj_with_mqa",
+            "model.layers.12.self_attn.kv_b_proj",
+            "model.layers.12.self_attn.o_proj",
+            "model.layers.12.self_attn.q_a_proj",
+            "model.layers.12.self_attn.q_b_proj",
+            "model.layers.13.mlp.gate",
+            "model.layers.13.self_attn.kv_a_proj_with_mqa",
+            "model.layers.13.self_attn.kv_b_proj",
+            "model.layers.13.self_attn.o_proj",
+            "model.layers.13.self_attn.q_a_proj",
+            "model.layers.13.self_attn.q_b_proj",
+            "model.layers.14.mlp.gate",
+            "model.layers.14.self_attn.kv_a_proj_with_mqa",
+            "model.layers.14.self_attn.kv_b_proj",
+            "model.layers.14.self_attn.o_proj",
+            "model.layers.14.self_attn.q_a_proj",
+            "model.layers.14.self_attn.q_b_proj",
+            "model.layers.15.mlp.gate",
+            "model.layers.15.self_attn.kv_a_proj_with_mqa",
+            "model.layers.15.self_attn.kv_b_proj",
+            "model.layers.15.self_attn.o_proj",
+            "model.layers.15.self_attn.q_a_proj",
+            "model.layers.15.self_attn.q_b_proj",
+            "model.layers.16.mlp.gate",
+            "model.layers.16.self_attn.kv_a_proj_with_mqa",
+            "model.layers.16.self_attn.kv_b_proj",
+            "model.layers.16.self_attn.o_proj",
+            "model.layers.16.self_attn.q_a_proj",
+            "model.layers.16.self_attn.q_b_proj",
+            "model.layers.17.mlp.gate",
+            "model.layers.17.self_attn.kv_a_proj_with_mqa",
+            "model.layers.17.self_attn.kv_b_proj",
+            "model.layers.17.self_attn.o_proj",
+            "model.layers.17.self_attn.q_a_proj",
+            "model.layers.17.self_attn.q_b_proj",
+            "model.layers.18.mlp.gate",
+            "model.layers.18.self_attn.kv_a_proj_with_mqa",
+            "model.layers.18.self_attn.kv_b_proj",
+            "model.layers.18.self_attn.o_proj",
+            "model.layers.18.self_attn.q_a_proj",
+            "model.layers.18.self_attn.q_b_proj",
+            "model.layers.19.mlp.gate",
+            "model.layers.19.self_attn.kv_a_proj_with_mqa",
+            "model.layers.19.self_attn.kv_b_proj",
+            "model.layers.19.self_attn.o_proj",
+            "model.layers.19.self_attn.q_a_proj",
+            "model.layers.19.self_attn.q_b_proj",
+            "model.layers.2.mlp.gate",
+            "model.layers.2.self_attn.kv_a_proj_with_mqa",
+            "model.layers.2.self_attn.kv_b_proj",
+            "model.layers.2.self_attn.o_proj",
+            "model.layers.2.self_attn.q_a_proj",
+            "model.layers.2.self_attn.q_b_proj",
+            "model.layers.20.mlp.gate",
+            "model.layers.20.self_attn.kv_a_proj_with_mqa",
+            "model.layers.20.self_attn.kv_b_proj",
+            "model.layers.20.self_attn.o_proj",
+            "model.layers.20.self_attn.q_a_proj",
+            "model.layers.20.self_attn.q_b_proj",
+            "model.layers.21.mlp.gate",
+            "model.layers.21.self_attn.kv_a_proj_with_mqa",
+            "model.layers.21.self_attn.kv_b_proj",
+            "model.layers.21.self_attn.o_proj",
+            "model.layers.21.self_attn.q_a_proj",
+            "model.layers.21.self_attn.q_b_proj",
+            "model.layers.22.mlp.gate",
+            "model.layers.22.self_attn.kv_a_proj_with_mqa",
+            "model.layers.22.self_attn.kv_b_proj",
+            "model.layers.22.self_attn.o_proj",
+            "model.layers.22.self_attn.q_a_proj",
+            "model.layers.22.self_attn.q_b_proj",
+            "model.layers.23.mlp.gate",
+            "model.layers.23.self_attn.kv_a_proj_with_mqa",
+            "model.layers.23.self_attn.kv_b_proj",
+            "model.layers.23.self_attn.o_proj",
+            "model.layers.23.self_attn.q_a_proj",
+            "model.layers.23.self_attn.q_b_proj",
+            "model.layers.24.mlp.gate",
+            "model.layers.24.self_attn.kv_a_proj_with_mqa",
+            "model.layers.24.self_attn.kv_b_proj",
+            "model.layers.24.self_attn.o_proj",
+            "model.layers.24.self_attn.q_a_proj",
+            "model.layers.24.self_attn.q_b_proj",
+            "model.layers.25.mlp.gate",
+            "model.layers.25.self_attn.kv_a_proj_with_mqa",
+            "model.layers.25.self_attn.kv_b_proj",
+            "model.layers.25.self_attn.o_proj",
+            "model.layers.25.self_attn.q_a_proj",
+            "model.layers.25.self_attn.q_b_proj",
+            "model.layers.26.mlp.gate",
+            "model.layers.26.self_attn.kv_a_proj_with_mqa",
+            "model.layers.26.self_attn.kv_b_proj",
+            "model.layers.26.self_attn.o_proj",
+            "model.layers.26.self_attn.q_a_proj",
+            "model.layers.26.self_attn.q_b_proj",
+            "model.layers.27.mlp.gate",
+            "model.layers.27.self_attn.kv_a_proj_with_mqa",
+            "model.layers.27.self_attn.kv_b_proj",
+            "model.layers.27.self_attn.o_proj",
+            "model.layers.27.self_attn.q_a_proj",
+            "model.layers.27.self_attn.q_b_proj",
+            "model.layers.28.mlp.gate",
+            "model.layers.28.self_attn.kv_a_proj_with_mqa",
+            "model.layers.28.self_attn.kv_b_proj",
+            "model.layers.28.self_attn.o_proj",
+            "model.layers.28.self_attn.q_a_proj",
+            "model.layers.28.self_attn.q_b_proj",
+            "model.layers.29.mlp.gate",
+            "model.layers.29.self_attn.kv_a_proj_with_mqa",
+            "model.layers.29.self_attn.kv_b_proj",
+            "model.layers.29.self_attn.o_proj",
+            "model.layers.29.self_attn.q_a_proj",
+            "model.layers.29.self_attn.q_b_proj",
+            "model.layers.3.mlp.gate",
+            "model.layers.3.self_attn.kv_a_proj_with_mqa",
+            "model.layers.3.self_attn.kv_b_proj",
+            "model.layers.3.self_attn.o_proj",
+            "model.layers.3.self_attn.q_a_proj",
+            "model.layers.3.self_attn.q_b_proj",
+            "model.layers.30.mlp.gate",
+            "model.layers.30.self_attn.kv_a_proj_with_mqa",
+            "model.layers.30.self_attn.kv_b_proj",
+            "model.layers.30.self_attn.o_proj",
+            "model.layers.30.self_attn.q_a_proj",
+            "model.layers.30.self_attn.q_b_proj",
+            "model.layers.31.mlp.gate",
+            "model.layers.31.self_attn.kv_a_proj_with_mqa",
+            "model.layers.31.self_attn.kv_b_proj",
+            "model.layers.31.self_attn.o_proj",
+            "model.layers.31.self_attn.q_a_proj",
+            "model.layers.31.self_attn.q_b_proj",
+            "model.layers.32.mlp.gate",
+            "model.layers.32.self_attn.kv_a_proj_with_mqa",
+            "model.layers.32.self_attn.kv_b_proj",
+            "model.layers.32.self_attn.o_proj",
+            "model.layers.32.self_attn.q_a_proj",
+            "model.layers.32.self_attn.q_b_proj",
+            "model.layers.33.mlp.gate",
+            "model.layers.33.self_attn.kv_a_proj_with_mqa",
+            "model.layers.33.self_attn.kv_b_proj",
+            "model.layers.33.self_attn.o_proj",
+            "model.layers.33.self_attn.q_a_proj",
+            "model.layers.33.self_attn.q_b_proj",
+            "model.layers.34.mlp.gate",
+            "model.layers.34.self_attn.kv_a_proj_with_mqa",
+            "model.layers.34.self_attn.kv_b_proj",
+            "model.layers.34.self_attn.o_proj",
+            "model.layers.34.self_attn.q_a_proj",
+            "model.layers.34.self_attn.q_b_proj",
+            "model.layers.35.mlp.gate",
+            "model.layers.35.self_attn.kv_a_proj_with_mqa",
+            "model.layers.35.self_attn.kv_b_proj",
+            "model.layers.35.self_attn.o_proj",
+            "model.layers.35.self_attn.q_a_proj",
+            "model.layers.35.self_attn.q_b_proj",
+            "model.layers.36.mlp.gate",
+            "model.layers.36.self_attn.kv_a_proj_with_mqa",
+            "model.layers.36.self_attn.kv_b_proj",
+            "model.layers.36.self_attn.o_proj",
+            "model.layers.36.self_attn.q_a_proj",
+            "model.layers.36.self_attn.q_b_proj",
+            "model.layers.37.mlp.gate",
+            "model.layers.37.self_attn.kv_a_proj_with_mqa",
+            "model.layers.37.self_attn.kv_b_proj",
+            "model.layers.37.self_attn.o_proj",
+            "model.layers.37.self_attn.q_a_proj",
+            "model.layers.37.self_attn.q_b_proj",
+            "model.layers.38.mlp.gate",
+            "model.layers.38.self_attn.kv_a_proj_with_mqa",
+            "model.layers.38.self_attn.kv_b_proj",
+            "model.layers.38.self_attn.o_proj",
+            "model.layers.38.self_attn.q_a_proj",
+            "model.layers.38.self_attn.q_b_proj",
+            "model.layers.39.mlp.gate",
+            "model.layers.39.self_attn.kv_a_proj_with_mqa",
+            "model.layers.39.self_attn.kv_b_proj",
+            "model.layers.39.self_attn.o_proj",
+            "model.layers.39.self_attn.q_a_proj",
+            "model.layers.39.self_attn.q_b_proj",
+            "model.layers.4.mlp.gate",
+            "model.layers.4.self_attn.kv_a_proj_with_mqa",
+            "model.layers.4.self_attn.kv_b_proj",
+            "model.layers.4.self_attn.o_proj",
+            "model.layers.4.self_attn.q_a_proj",
+            "model.layers.4.self_attn.q_b_proj",
+            "model.layers.40.mlp.gate",
+            "model.layers.40.self_attn.kv_a_proj_with_mqa",
+            "model.layers.40.self_attn.kv_b_proj",
+            "model.layers.40.self_attn.o_proj",
+            "model.layers.40.self_attn.q_a_proj",
+            "model.layers.40.self_attn.q_b_proj",
+            "model.layers.41.mlp.gate",
+            "model.layers.41.self_attn.kv_a_proj_with_mqa",
+            "model.layers.41.self_attn.kv_b_proj",
+            "model.layers.41.self_attn.o_proj",
+            "model.layers.41.self_attn.q_a_proj",
+            "model.layers.41.self_attn.q_b_proj",
+            "model.layers.42.mlp.gate",
+            "model.layers.42.self_attn.kv_a_proj_with_mqa",
+            "model.layers.42.self_attn.kv_b_proj",
+            "model.layers.42.self_attn.o_proj",
+            "model.layers.42.self_attn.q_a_proj",
+            "model.layers.42.self_attn.q_b_proj",
+            "model.layers.43.mlp.gate",
+            "model.layers.43.self_attn.kv_a_proj_with_mqa",
+            "model.layers.43.self_attn.kv_b_proj",
+            "model.layers.43.self_attn.o_proj",
+            "model.layers.43.self_attn.q_a_proj",
+            "model.layers.43.self_attn.q_b_proj",
+            "model.layers.44.mlp.gate",
+            "model.layers.44.self_attn.kv_a_proj_with_mqa",
+            "model.layers.44.self_attn.kv_b_proj",
+            "model.layers.44.self_attn.o_proj",
+            "model.layers.44.self_attn.q_a_proj",
+            "model.layers.44.self_attn.q_b_proj",
+            "model.layers.45.mlp.gate",
+            "model.layers.45.self_attn.kv_a_proj_with_mqa",
+            "model.layers.45.self_attn.kv_b_proj",
+            "model.layers.45.self_attn.o_proj",
+            "model.layers.45.self_attn.q_a_proj",
+            "model.layers.45.self_attn.q_b_proj",
+            "model.layers.46.mlp.gate",
+            "model.layers.46.self_attn.kv_a_proj_with_mqa",
+            "model.layers.46.self_attn.kv_b_proj",
+            "model.layers.46.self_attn.o_proj",
+            "model.layers.46.self_attn.q_a_proj",
+            "model.layers.46.self_attn.q_b_proj",
+            "model.layers.47.mlp.gate",
+            "model.layers.47.self_attn.kv_a_proj_with_mqa",
+            "model.layers.47.self_attn.kv_b_proj",
+            "model.layers.47.self_attn.o_proj",
+            "model.layers.47.self_attn.q_a_proj",
+            "model.layers.47.self_attn.q_b_proj",
+            "model.layers.48.mlp.gate",
+            "model.layers.48.self_attn.kv_a_proj_with_mqa",
+            "model.layers.48.self_attn.kv_b_proj",
+            "model.layers.48.self_attn.o_proj",
+            "model.layers.48.self_attn.q_a_proj",
+            "model.layers.48.self_attn.q_b_proj",
+            "model.layers.49.mlp.gate",
+            "model.layers.49.self_attn.kv_a_proj_with_mqa",
+            "model.layers.49.self_attn.kv_b_proj",
+            "model.layers.49.self_attn.o_proj",
+            "model.layers.49.self_attn.q_a_proj",
+            "model.layers.49.self_attn.q_b_proj",
+            "model.layers.5.mlp.gate",
+            "model.layers.5.self_attn.kv_a_proj_with_mqa",
+            "model.layers.5.self_attn.kv_b_proj",
+            "model.layers.5.self_attn.o_proj",
+            "model.layers.5.self_attn.q_a_proj",
+            "model.layers.5.self_attn.q_b_proj",
+            "model.layers.50.mlp.gate",
+            "model.layers.50.self_attn.kv_a_proj_with_mqa",
+            "model.layers.50.self_attn.kv_b_proj",
+            "model.layers.50.self_attn.o_proj",
+            "model.layers.50.self_attn.q_a_proj",
+            "model.layers.50.self_attn.q_b_proj",
+            "model.layers.51.mlp.gate",
+            "model.layers.51.self_attn.kv_a_proj_with_mqa",
+            "model.layers.51.self_attn.kv_b_proj",
+            "model.layers.51.self_attn.o_proj",
+            "model.layers.51.self_attn.q_a_proj",
+            "model.layers.51.self_attn.q_b_proj",
+            "model.layers.52.mlp.gate",
+            "model.layers.52.self_attn.kv_a_proj_with_mqa",
+            "model.layers.52.self_attn.kv_b_proj",
+            "model.layers.52.self_attn.o_proj",
+            "model.layers.52.self_attn.q_a_proj",
+            "model.layers.52.self_attn.q_b_proj",
+            "model.layers.53.mlp.gate",
+            "model.layers.53.self_attn.kv_a_proj_with_mqa",
+            "model.layers.53.self_attn.kv_b_proj",
+            "model.layers.53.self_attn.o_proj",
+            "model.layers.53.self_attn.q_a_proj",
+            "model.layers.53.self_attn.q_b_proj",
+            "model.layers.54.mlp.gate",
+            "model.layers.54.self_attn.kv_a_proj_with_mqa",
+            "model.layers.54.self_attn.kv_b_proj",
+            "model.layers.54.self_attn.o_proj",
+            "model.layers.54.self_attn.q_a_proj",
+            "model.layers.54.self_attn.q_b_proj",
+            "model.layers.55.mlp.gate",
+            "model.layers.55.self_attn.kv_a_proj_with_mqa",
+            "model.layers.55.self_attn.kv_b_proj",
+            "model.layers.55.self_attn.o_proj",
+            "model.layers.55.self_attn.q_a_proj",
+            "model.layers.55.self_attn.q_b_proj",
+            "model.layers.56.mlp.gate",
+            "model.layers.56.self_attn.kv_a_proj_with_mqa",
+            "model.layers.56.self_attn.kv_b_proj",
+            "model.layers.56.self_attn.o_proj",
+            "model.layers.56.self_attn.q_a_proj",
+            "model.layers.56.self_attn.q_b_proj",
+            "model.layers.57.mlp.gate",
+            "model.layers.57.self_attn.kv_a_proj_with_mqa",
+            "model.layers.57.self_attn.kv_b_proj",
+            "model.layers.57.self_attn.o_proj",
+            "model.layers.57.self_attn.q_a_proj",
+            "model.layers.57.self_attn.q_b_proj",
+            "model.layers.58.mlp.gate",
+            "model.layers.58.self_attn.kv_a_proj_with_mqa",
+            "model.layers.58.self_attn.kv_b_proj",
+            "model.layers.58.self_attn.o_proj",
+            "model.layers.58.self_attn.q_a_proj",
+            "model.layers.58.self_attn.q_b_proj",
+            "model.layers.59.mlp.gate",
+            "model.layers.59.self_attn.kv_a_proj_with_mqa",
+            "model.layers.59.self_attn.kv_b_proj",
+            "model.layers.59.self_attn.o_proj",
+            "model.layers.59.self_attn.q_a_proj",
+            "model.layers.59.self_attn.q_b_proj",
+            "model.layers.6.mlp.gate",
+            "model.layers.6.self_attn.kv_a_proj_with_mqa",
+            "model.layers.6.self_attn.kv_b_proj",
+            "model.layers.6.self_attn.o_proj",
+            "model.layers.6.self_attn.q_a_proj",
+            "model.layers.6.self_attn.q_b_proj",
+            "model.layers.60.mlp.gate",
+            "model.layers.60.self_attn.kv_a_proj_with_mqa",
+            "model.layers.60.self_attn.kv_b_proj",
+            "model.layers.60.self_attn.o_proj",
+            "model.layers.60.self_attn.q_a_proj",
+            "model.layers.60.self_attn.q_b_proj",
+            "model.layers.7.mlp.gate",
+            "model.layers.7.self_attn.kv_a_proj_with_mqa",
+            "model.layers.7.self_attn.kv_b_proj",
+            "model.layers.7.self_attn.o_proj",
+            "model.layers.7.self_attn.q_a_proj",
+            "model.layers.7.self_attn.q_b_proj",
+            "model.layers.8.mlp.gate",
+            "model.layers.8.self_attn.kv_a_proj_with_mqa",
+            "model.layers.8.self_attn.kv_b_proj",
+            "model.layers.8.self_attn.o_proj",
+            "model.layers.8.self_attn.q_a_proj",
+            "model.layers.8.self_attn.q_b_proj",
+            "model.layers.9.mlp.gate",
+            "model.layers.9.self_attn.kv_a_proj_with_mqa",
+            "model.layers.9.self_attn.kv_b_proj",
+            "model.layers.9.self_attn.o_proj",
+            "model.layers.9.self_attn.q_a_proj",
+            "model.layers.9.self_attn.q_b_proj"
         ],
         "algo_config": null,
         "softmax_quant_spec": null,
@@ -113,7 +475,7 @@
         "kv_cache_quant_config": {},
         "kv_cache_post_rope": false,
         "quant_mode": "eager_mode",
-        "version": "0.12+15553c6a61",
+        "version": "0.11.2+e7a61dd5fa8",
         "export": {
             "kv_cache_group": [],
             "min_kv_scale": 0.0,
diff --git a/model-00010-of-00527.safetensors b/model-00010-of-00527.safetensors
index 3bc499ebec3ef4d294dcd4a756114f24241c44a0..3c748b33ecfd2384e11b0deefcb003c25ffdbc9c 100644
--- a/model-00010-of-00527.safetensors
+++ b/model-00010-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a208ad3704aa08ae37e05ff7ed30db7feca9f5f939a3ad5e7cd9f018b3074f99
-size 1270743528
+oid sha256:7fea8119c515eb6adf764232e17b3caf0a51f45128c0d538d3a1b235a625fb17
+size 1206059840
diff --git a/model-00019-of-00527.safetensors b/model-00019-of-00527.safetensors
index d88936fbf733b5e6774f70289b75bb8ab2f39b72..a63d89be5d3c43e713f247e0492abb7c45cf3dc6 100644
--- a/model-00019-of-00527.safetensors
+++ b/model-00019-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb05f728dc85eb0ecc80a241b84e3a48dffb3fb8246e9b7c822a1f7c2c55f49b
-size 1270743456
+oid sha256:9a337c2f2209b908d7f0fee73d579bb2edf806acdbc91c8a6a264fb98df76474
+size 1206059776
diff --git a/model-00027-of-00527.safetensors b/model-00027-of-00527.safetensors
index a865d8faf4e5720478cb417cc74b3e54f82ea5bb..e28084fb91af23a56cb3ffa2311eca0452b7b48c 100644
--- a/model-00027-of-00527.safetensors
+++ b/model-00027-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3270c2d8ff5af3d6d561d6b771307c0f25e831581d294cfd32f3ed0199acd3e7
-size 1270743704
+oid sha256:1751275b155c2aafdc6f407fc2c7e62843b5b02f6b5d6406765d0d40ead51feb
+size 1206060024
diff --git a/model-00036-of-00527.safetensors b/model-00036-of-00527.safetensors
index 7ec119e7a8f0472533affbeffd82b0baec0e49fe..6b755a0ff859f9e1a99e05275f555146601b3ea4 100644
--- a/model-00036-of-00527.safetensors
+++ b/model-00036-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9887e107bf62c39a481dc8f968733ec3e60f72b3cccc372a3b1cf100bd9949c3
-size 1270743592
+oid sha256:74aa2cbbfaa9936c97a6082530123b8afd51ea784eca1de9c7b515d96e27d6cd
+size 1206059904
diff --git a/model-00045-of-00527.safetensors b/model-00045-of-00527.safetensors
index ca49b749b9dddaa22e1a03acc248a5267c400bca..02fc339daa9a7320ec6231f0fa102b3454d73897 100644
--- a/model-00045-of-00527.safetensors
+++ b/model-00045-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85fd29373779cf6b15b8b98d3d8a8427b82b33fb49bb03915f631a9d1d11a2c8
-size 1270743528
+oid sha256:dfd50d9d1ad3608682882f8cb8ef317dc18620130eb3f893796c324f1f5fb8fa
+size 1206059840
diff --git a/model-00054-of-00527.safetensors b/model-00054-of-00527.safetensors
index 0e7dd57c0e722a0631e3d372600323700ab8f261..b68cffde5021caaf58ccb39e184303e3cf6e6262 100644
--- a/model-00054-of-00527.safetensors
+++ b/model-00054-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0bc371206285fc604e1c354ccf3be50210aca911ab65b947cd6a5e0addffe2d
-size 1270743456
+oid sha256:2fb2d322c665e3e90eca9857b8353903ad75f55d85f774614fd2cb741605a075
+size 1206059776
diff --git a/model-00062-of-00527.safetensors b/model-00062-of-00527.safetensors
index 17de6a89a5254c85aa19f4f7b2a4fdcbada780ad..fb646a795e63f60603933c79cb5fc60efb9d165f 100644
--- a/model-00062-of-00527.safetensors
+++ b/model-00062-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29958391f60ccc22aa9437926b44f888ff49cd1dd4eb86636c4ca33b4e5c08e4
-size 1270743712
+oid sha256:264e1e679146c9c30a4ec21354a15ffbc29645332038ee44bb40af02cdef80f0
+size 1206060032
diff --git a/model-00071-of-00527.safetensors b/model-00071-of-00527.safetensors
index fc2e78cf5e174c6cf1d06b72e356ce20efc34e25..921fb08a6ba9e81ec3ca5a6dfb7eb08babfd98bc 100644
--- a/model-00071-of-00527.safetensors
+++ b/model-00071-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3970230f532821daf40a422ccdf7e2b16e39417eb9cf10e6ed2e66e60779abe2
-size 1270743600
+oid sha256:780f8d238c583a7336491e4a7b38f9c66e549c507e19e32ac8094985f37b6eb1
+size 1206059912
diff --git a/model-00080-of-00527.safetensors b/model-00080-of-00527.safetensors
index 0bf0eed388405ab95ef3bf01aa7304a61195272c..9b320640d7d9018213fbccc3cbfc71b0ab7cf2f3 100644
--- a/model-00080-of-00527.safetensors
+++ b/model-00080-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3aea3f757b8c757aee66fa5991ce797561c4a9530db1db477499d4201b079c6
-size 1270743688
+oid sha256:3969fc6920d5bac1435606235c54d1711f0dd5f3cda89f9b408fec514a022386
+size 1206060008
diff --git a/model-00089-of-00527.safetensors b/model-00089-of-00527.safetensors
index 807b8550f0fef0ffe6909376b1f614b18f60233c..7f89e7c1e8f8adc893c82a7f902b1e0f2145b8ac 100644
--- a/model-00089-of-00527.safetensors
+++ b/model-00089-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ea39f037c74b8c1464a8483b22af99a8c77b4e4862a42821504d8101d43523a
-size 1270743728
+oid sha256:bbce3096af7b461411a8e17dc9501ce3cdcca16c33c1e87aa55c63ba1cd8825c
+size 1206060048
diff --git a/model-00097-of-00527.safetensors b/model-00097-of-00527.safetensors
index da928000aeaa6d42eac509e0a9c057c5b21f1aa9..0146db02f36ed0099dd0d7fabc2ae84427b6a5bd 100644
--- a/model-00097-of-00527.safetensors
+++ b/model-00097-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de0c5dded8df7ba93c08344fdd7d4e07174b1786a47475c1f355d76cee7838aa
-size 1270743976
+oid sha256:cb36c8a0c00d24ed2cbc11632b01d172f2d5ece63f3b3fd67d7fc416c6b6f4a4
+size 1206060296
diff --git a/model-00106-of-00527.safetensors b/model-00106-of-00527.safetensors
index 977e84f4502d94390f2d3885b5d6c9f38f6f969a..6a803b5564387e713bb9892f471e2a9a3472cd42 100644
--- a/model-00106-of-00527.safetensors
+++ b/model-00106-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6a596ebdb97a336a872927d6ee805bc0b24a0635eb9203613bb6e2cea05ddad
-size 1270743864
+oid sha256:c6f8e685364d434db2ff99191504cb463d0e89ce4b8286596a75643f6708d99b
+size 1206060176
diff --git a/model-00115-of-00527.safetensors b/model-00115-of-00527.safetensors
index 85b3c022d67021b2f99b92158fb6366d99268dd3..d0eac05bae60f67d9f758f61cdb899ee0584b95d 100644
--- a/model-00115-of-00527.safetensors
+++ b/model-00115-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2fbc44a46b592565c4556d66baf74bd6f008a7cfc556c6503f3e4d7d6c4a57e
-size 1270743792
+oid sha256:56775aa2844909bffe22ccd1864176bd6d0ddb532b6f7875641d0be1d5f058a3
+size 1206060112
diff --git a/model-00124-of-00527.safetensors b/model-00124-of-00527.safetensors
index ca81073aeabfd023f79649194802c5e7ce391e29..b5adc6b86a3702af983e6b8ab4f72c6c6e656b74 100644
--- a/model-00124-of-00527.safetensors
+++ b/model-00124-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89221a2e36738fba5c493111faf3ee322d40d8902efe9da81729e2625fa82d3c
-size 1270743728
+oid sha256:495065129673395e30c45c8d7f8f6bf025e0e6d909e82313517802bcd2162f37
+size 1206060048
diff --git a/model-00132-of-00527.safetensors b/model-00132-of-00527.safetensors
index ea9fef48fde3cbd1a6e6a58a616ab1bdf8004561..1e04de4c75fdd3a1386e6ef4b301945b5e1d65f8 100644
--- a/model-00132-of-00527.safetensors
+++ b/model-00132-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a89a3b454b5d1d476150fa6d372ce7f5f60f285b92f071e2c6b053fd707f544
-size 1270743976
+oid sha256:64c8011432d14d54bf8ca50eccda8b4e4802c532319656b7986cffaa0c5a1d69
+size 1206060296
diff --git a/model-00141-of-00527.safetensors b/model-00141-of-00527.safetensors
index 2f3545ffd3dabb291e0b1cffbb1aca1979536781..80f492b146605c535c737addf493b4bc89faf2db 100644
--- a/model-00141-of-00527.safetensors
+++ b/model-00141-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad9bd65f2281656707ffccd6c9804871927177158cc1749df13bbe24de22aa29
-size 1270743856
+oid sha256:cce968bbd4037158861af19a6cc280f58681a10244be7f9355b250afc5a19a0a
+size 1206060176
diff --git a/model-00150-of-00527.safetensors b/model-00150-of-00527.safetensors
index 32cdca35838e60eabf86f22f7317b4c5790e38bd..2212b7a9833ac9ff16766b62d633c1286a3de973 100644
--- a/model-00150-of-00527.safetensors
+++ b/model-00150-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:582cd87d4190d3753b5aa32d5eefe4657981d7446e132b882d61cf41d028546f
-size 1270743792
+oid sha256:cff72343fc973ae27fbe7eaadccd36d36583a59399fb6372d3f044159a77283a
+size 1206060112
diff --git a/model-00159-of-00527.safetensors b/model-00159-of-00527.safetensors
index 9499fa2063972aed9e83be601b15065e36b2ef52..d058d01556cefe5a218900a4696c05d31dd6c03d 100644
--- a/model-00159-of-00527.safetensors
+++ b/model-00159-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c067d353f6fb754b12232b3bd3accd3c4694b915a0eea7cf1ff96edd38095c1e
-size 1270743728
+oid sha256:1ab096528970a2810a7f2f1acb764182e251db6f1d4807d3f9c2f6e9add3c8bb
+size 1206060048
diff --git a/model-00167-of-00527.safetensors b/model-00167-of-00527.safetensors
index 94c9a20818dba7972735ae56591d484e56734c68..d32691b4ce566979a6a1fc609b3e288b3700645d 100644
--- a/model-00167-of-00527.safetensors
+++ b/model-00167-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e59cf0e3f3476097053ac09f10664e6cc35ceab52837c80c7aaa612eec989a32
-size 1270743976
+oid sha256:cc2efdb3eeab410ef7e24a1194d6ca58af12b7244056333a8a505fb073fc3236
+size 1206060296
diff --git a/model-00176-of-00527.safetensors b/model-00176-of-00527.safetensors
index 60e19788db12af5823afd545b4eb0c8c41beb449..2d70ed347b8aa2145a8fb51d05ea26fe84cd6dac 100644
--- a/model-00176-of-00527.safetensors
+++ b/model-00176-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1e0f9b8bf25f8f17d3c54ac683ed8c94b274f39ba166fe56616348582fc8fc3
-size 1270743856
+oid sha256:deb6f27b9fe2468cbafdb9aab9b520478a408249df60bf673f15287d45682225
+size 1206060176
diff --git a/model-00185-of-00527.safetensors b/model-00185-of-00527.safetensors
index a019fa6a889f237abd80a928141ddd93f0e4ac48..d83cded68f47f9f0d4151792a5f8ebad08f9f773 100644
--- a/model-00185-of-00527.safetensors
+++ b/model-00185-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c818abd2d661cf5d10a42a357c5bd97c34876b07583f6667e30d1741ae888f68
-size 1270743792
+oid sha256:a05673b9afc75f7421ad5b2985c58398c4a6f3e440f647ca43c1c7d16a2ffcc0
+size 1206060112
diff --git a/model-00194-of-00527.safetensors b/model-00194-of-00527.safetensors
index e071078658aa25e7e7edc635f091a3ca272c09e4..2e91e4c904f384d2817a982e99f3334a10ba38f0 100644
--- a/model-00194-of-00527.safetensors
+++ b/model-00194-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5700c9ff171a0c84758c7746fddf941a8170c9369e358e54b597265c963163a
-size 1270743728
+oid sha256:01e9969864658b0ac91ff38c502db516f75581016417a8532567e7267a3d3692
+size 1206060048
diff --git a/model-00202-of-00527.safetensors b/model-00202-of-00527.safetensors
index cb40ad0bd3c83de91e2282b058f99e7cf7eb17c2..41e75408d47dc8a1268d0d276cdf23c3808c0a44 100644
--- a/model-00202-of-00527.safetensors
+++ b/model-00202-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6b9b15b72b0a8169abd9975dcffe3ce843445632dda8b85e5ab90d2255f871a
-size 1270743984
+oid sha256:c9f790f10c5a63528d1ff8083b3faeb9d2deca8926fb4a209660e2557b7253bb
+size 1206060304
diff --git a/model-00211-of-00527.safetensors b/model-00211-of-00527.safetensors
index 462a6e221070e7262a4a38449217a5877d37af3e..82a4589da7141863c84d9deac9221302c49d421f 100644
--- a/model-00211-of-00527.safetensors
+++ b/model-00211-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2f28dfee7c7aab25752d36bde3a4a0c8314dbef44d3a2b1d1bc207e2294491a
-size 1270743864
+oid sha256:f9fd01ce686e2e68e4fd3ae725622e31281df5b17975dce7cf74bcd166b5db15
+size 1206060176
diff --git a/model-00220-of-00527.safetensors b/model-00220-of-00527.safetensors
index 1ff1ef2660db37b2c38b35b0bd9510e314a59314..d784369a54b391218207738064a3a05a80205fbe 100644
--- a/model-00220-of-00527.safetensors
+++ b/model-00220-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fd0e163c94fc8c427d7b4118c15466c73aadb4d5d06d0a2a69a8b2b23acafd9
-size 1270743792
+oid sha256:0c58497fd5cfc58f5b781ab4be0cc7639acd9be8a925f06ac3abd882e9ab40bc
+size 1206060112
diff --git a/model-00229-of-00527.safetensors b/model-00229-of-00527.safetensors
index 0a9b4af04cc88a4a7e6a4cad6b3dad3c8755a3f8..c6f01463e0811f4b9886ad9824222918118f2884 100644
--- a/model-00229-of-00527.safetensors
+++ b/model-00229-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a81bcbcdd8bd3c20d9d79d2af543b136d4d9ecb95e9fc92ddcc70b128dfccb0a
-size 1270743728
+oid sha256:9941ca2b869708dd7e26e47ceceae79a7f4bbe7fae0bf83760174cb151b9d754
+size 1206060048
diff --git a/model-00237-of-00527.safetensors b/model-00237-of-00527.safetensors
index 91b414b1d796b1287e0d044d2ee866cc8dc43c7c..26051de049a0c046b4a03a3d580346fd3b47773f 100644
--- a/model-00237-of-00527.safetensors
+++ b/model-00237-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e776cb48d02f1d849d0b7890982667608ea143c69a77288592f7bc89455fc49
-size 1270743984
+oid sha256:2a70e5e6f9208bf8422f63bb8c63e94170a1db8d5076e61843a41cf09363adba
+size 1206060304
diff --git a/model-00246-of-00527.safetensors b/model-00246-of-00527.safetensors
index db538ba48e13a6eedec6a7b6dff1cb0f81802f30..877d406723e21e3b59a05231feba1e8919795c85 100644
--- a/model-00246-of-00527.safetensors
+++ b/model-00246-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80382f7e8133ef17f944f1e6c3dc9f0a3a353b4152ec0ecb3072bb1fd467776d
-size 1270743864
+oid sha256:a28f676de7990497ef29ca74753169b6b1efffb156d9d3feae674d2161b7dc96
+size 1206060176
diff --git a/model-00255-of-00527.safetensors b/model-00255-of-00527.safetensors
index 124bb35ba233411f52230f9229bb86036fd28bf6..c320a6a04cd62d722f7422720f6e45bf9b95fced 100644
--- a/model-00255-of-00527.safetensors
+++ b/model-00255-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5a803d662180cbac1ea24f930cd4145f19c55749d3b4a11fd6ef5f7a989bb0c
-size 1270743792
+oid sha256:1ddbea33feb0741fc55c1a7be1e24e708ef743d472bbc722b29179c8c1296806
+size 1206060112
diff --git a/model-00264-of-00527.safetensors b/model-00264-of-00527.safetensors
index babc6db0dc28113834280aab51bbe775a335438b..45cd1a487b7144b6a5b342de57dcd05c0c6b1120 100644
--- a/model-00264-of-00527.safetensors
+++ b/model-00264-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8956381bf22b284f9771a10968809592e1e1b70ac3e0593b80ec4003076cbed
-size 1270743728
+oid sha256:be3f448eb206ba6db2099e6cfe9f87ea4048e0340e30ba0ba5e17c7bd6bede19
+size 1206060048
diff --git a/model-00272-of-00527.safetensors b/model-00272-of-00527.safetensors
index 29bd84eaea4ca253cf23035beaba2a1e8b1ca6e6..50fb8a5cd8392af43018a3d4c855071a93e7bf0e 100644
--- a/model-00272-of-00527.safetensors
+++ b/model-00272-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15068d119f24cfeeebd7130c6a133ae6812e4d850406448b13aa040a08173b37
-size 1270743992
+oid sha256:94a5678a472a8fcdff0e879ae733ebabb0f7445df72c12899243bfeb3659e433
+size 1206060312
diff --git a/model-00281-of-00527.safetensors b/model-00281-of-00527.safetensors
index a0ec944cce7dd5486a7edd21c3153468c11eceb7..052cbed96dec79cac7c16990aa49d9dcdbb1f84a 100644
--- a/model-00281-of-00527.safetensors
+++ b/model-00281-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcaa224a3908c7333c6cc6c5fbe881fc1acaf96888d65d53f26babf6ebefdaa4
-size 1270743864
+oid sha256:d93b34205b8a849a248e3bf0a08039833afefc21828ae96f693d31c83d52ab23
+size 1206060184
diff --git a/model-00290-of-00527.safetensors b/model-00290-of-00527.safetensors
index 8e956c76ba4af795a25bfd3b21ad6f8879c62be1..c4161a595bd605ebec3c7fd7b872a1e4d723f7ad 100644
--- a/model-00290-of-00527.safetensors
+++ b/model-00290-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cbe7bcf77098ff7dfc069007058f89e2543ed7f73bc8c6b5ab9c136d0600a2d
-size 1270743800
+oid sha256:fcc3881ec8dc52140b0961558d2d53e1782c2abba2241a0c96e26c4c10d7ed83
+size 1206060120
diff --git a/model-00299-of-00527.safetensors b/model-00299-of-00527.safetensors
index e0283e9f72ae662dfbc76019b10049df8e1cad4e..30d179f39a411f732ab32e74f930aff873a43120 100644
--- a/model-00299-of-00527.safetensors
+++ b/model-00299-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc346ffe1c20208fbab8eee612816ab9015ba8452e8babe4d0db10e85f1943bc
-size 1270743736
+oid sha256:8ea8a15a11c4b97aff9100bd63fb9a2f3f4d342572e6fd8387c93813ea8ab94d
+size 1206060056
diff --git a/model-00307-of-00527.safetensors b/model-00307-of-00527.safetensors
index 89b97a942c8b6a5b3b79630a4a5af4a50ed4662f..d57b5757c9bfb036944351135005772ea1372b40 100644
--- a/model-00307-of-00527.safetensors
+++ b/model-00307-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab0ed64d2b869dfad1096d1330331140022de1f99a08b66e00d407616a4573e5
-size 1270743992
+oid sha256:ed61aaba8ebade05b4de020eb4c76aa8c4cb8d4dffa8a810a13f273dfbbbdfb7
+size 1206060312
diff --git a/model-00316-of-00527.safetensors b/model-00316-of-00527.safetensors
index 1f957eebcd8164fd1fd5f66596a4384ae7a0fbd1..c6c12fd9ddbca837d5b10dd1054daea392bf22a9 100644
--- a/model-00316-of-00527.safetensors
+++ b/model-00316-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c5a9bed1e671e739db8235f57cbdbb462feeef9e49711759aa849e466460c1f
-size 1270743864
+oid sha256:93c5fe0da1a19fa85e8faefb0e323d00da19dac3ca61e513776aed08a9f35f4f
+size 1206060184
diff --git a/model-00325-of-00527.safetensors b/model-00325-of-00527.safetensors
index d7d69a00796c29d29117ebc4789a2327f70963d6..c0407e71f94fbad34c76039bf75ced3cfe88d16f 100644
--- a/model-00325-of-00527.safetensors
+++ b/model-00325-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6d1fa0386570b15053344e357312ba088f030476c664563f3c8700086654034
-size 1270743800
+oid sha256:ac95094e54577ff487b6ae3cd279ee6e1750d85401fb5acc2aaa2144ea2a68dd
+size 1206060120
diff --git a/model-00334-of-00527.safetensors b/model-00334-of-00527.safetensors
index 96309017933875118dd3c4d1dc1a6408139ef1ac..da5d6bcf6e8517d9efc3137bdca2cdb618320d33 100644
--- a/model-00334-of-00527.safetensors
+++ b/model-00334-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea45e6b1a7e6a653bf028c79fd3597c992703d9111cc6efca7dbb9875a90a52d
-size 1270743736
+oid sha256:75be5b64b4ace92c4a869afbb02671e3c9841f74d3832806506b769147d09d0b
+size 1206060056
diff --git a/model-00342-of-00527.safetensors b/model-00342-of-00527.safetensors
index a55e90caa738ad6ad749e50b25a43f874dfe7d32..419e3a95e064ed555839e2349889fba99b5dfed9 100644
--- a/model-00342-of-00527.safetensors
+++ b/model-00342-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70d58c612e9c02f9415c295bdf6071e0714ca3b707a2e841645bc5eff5ba801e
-size 1270743992
+oid sha256:5cdf79f728e0d097547998a5f6b2c15ca729b4d90fb809650552d3c99eb88150
+size 1206060312
diff --git a/model-00351-of-00527.safetensors b/model-00351-of-00527.safetensors
index 0c5978aebe4eb82f32f864366367c8bd9d3e572e..48b7d93b20de99c0cc517d739a474a65786e1557 100644
--- a/model-00351-of-00527.safetensors
+++ b/model-00351-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:642d30d676c184c8851f9cf76b2cbc916b0830382aa218637c074ccfec55b527
-size 1270743864
+oid sha256:0c8b75033d9170344561ce074f1ecdc8e603dcb12c614ca12868285518a0bc1e
+size 1206060184
diff --git a/model-00360-of-00527.safetensors b/model-00360-of-00527.safetensors
index 30084cf2cd964f671038f8a845d46cd53af5075f..de163631402c25bb6f642305c432ad54b787ab73 100644
--- a/model-00360-of-00527.safetensors
+++ b/model-00360-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd67fee1f4585c2233ef67f9ec76d58142b073d4e3674703853452234c3f0d27
-size 1270743800
+oid sha256:fa9927c7fb51b66323c8cf01be4e03c7557d7fe0c9d445262e322f7aeb57c62f
+size 1206060120
diff --git a/model-00369-of-00527.safetensors b/model-00369-of-00527.safetensors
index 06b88e1e1283eea142f2456405146d404ec5fc01..723f4a942ace9ff933460608883a7fff24141ce7 100644
--- a/model-00369-of-00527.safetensors
+++ b/model-00369-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cf258481db2ca93b3f1e8bae206d10f2b84c052bdb7c96858043390aebe56ff
-size 1270743736
+oid sha256:fd30770f1ba29e7cb5a66ec3f6a60c53f5c5628f966b5c43f3761d19bbcd649f
+size 1206060048
diff --git a/model-00377-of-00527.safetensors b/model-00377-of-00527.safetensors
index 7cbb8f32a4d3c0ddfa14b32fd66830fb10df6b16..10485eaf198d410c0259732ff13ba7644028c401 100644
--- a/model-00377-of-00527.safetensors
+++ b/model-00377-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:853cf195a1d3e249f63e9c6abb4b791638cf49a11503c8ec0c539470e7e0b329
-size 1270743992
+oid sha256:f9be28ddab9e6ac9457c8a506608bbc91cc36cfb66bb960ba62b7fdd28a56cb5
+size 1206060312
diff --git a/model-00386-of-00527.safetensors b/model-00386-of-00527.safetensors
index d253a979473cb586c2fbadf45eddb7f9c97c4df7..7fee6e53778673edc5269bf95d98efed7286cdc0 100644
--- a/model-00386-of-00527.safetensors
+++ b/model-00386-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87a44b87d830fd4fc1476b388c81fba46fa44c683d6dd53d26de68ca177dc380
-size 1270743864
+oid sha256:dc4864728b5b184e1344141bfb9dd9a3d0cfce92b4d08d467ff7ffbdc8c5fdcb
+size 1206060184
diff --git a/model-00395-of-00527.safetensors b/model-00395-of-00527.safetensors
index 7c278efafdececb929c4272058faa1500990295a..75a309069a7254f6aeb20f01b7d41b64622ba77a 100644
--- a/model-00395-of-00527.safetensors
+++ b/model-00395-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f0ccb918f23a370e00d55f6f217a103f2e2acf2aeb4b7cf897debe815a81e4e
-size 1270743800
+oid sha256:71a28a512328c678f506c0398bde093d70d7e8959f51f93e52766056adf98179
+size 1206060120
diff --git a/model-00404-of-00527.safetensors b/model-00404-of-00527.safetensors
index 0c3eab5d2f3e912421eed4afaa4297263f17e6b5..71c445f28e6a8d4cdfc017cb1a96e1353e6c2193 100644
--- a/model-00404-of-00527.safetensors
+++ b/model-00404-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1250cb87f1746ec6a75780d3604a900f1618c31ea9fd2964bc554f730df040d3
-size 1270743736
+oid sha256:440c3066c08e516967f6cf5896064ef83351230f635e0fae9b415f513a1b05e4
+size 1206060048
diff --git a/model-00412-of-00527.safetensors b/model-00412-of-00527.safetensors
index b7ac60624669f03e3da11b798236be7bf8841a16..c138e2f13816d0e224810713230a6147d3592298 100644
--- a/model-00412-of-00527.safetensors
+++ b/model-00412-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfd070374a55c42994883ec0a97131bf53e49597a992979720cef09b6c30a26b
-size 1161102344
+oid sha256:9fa84e05fc48b27a0aabd15ea993787b290ffa2b1fa4441a79a55b4b9f976250
+size 1096418648
diff --git a/model-00421-of-00527.safetensors b/model-00421-of-00527.safetensors
index 5e3c15b72e40c078a4be3b451946e5daa24f8fc2..2202f1c9a9f3bf2370773c0f636488cf5f8c5f25 100644
--- a/model-00421-of-00527.safetensors
+++ b/model-00421-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5a396dfe5a41c34a7125aff72641a0740faf7d203a41bb16d8c8f8e15953c4a
-size 1270743872
+oid sha256:02a9c10c34d19537eb5fe8a55403f4b097cdc2cea34a1232cb5c392cc312fd0e
+size 1206060192
diff --git a/model-00430-of-00527.safetensors b/model-00430-of-00527.safetensors
index 044b5ebebb433de8325df4b30cee3b7c9bd41d2c..9d0d82c8824d6da32e89c3a77e0c9dd0939dd1c2 100644
--- a/model-00430-of-00527.safetensors
+++ b/model-00430-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a48c1bffcb8d60e2fe794518fd5f6aef91bb7a104a339f243ac0dab64c28b784
-size 1270743808
+oid sha256:d5fff83089c92ef9fcd691ec7a560f6f821a9a83e97fe66d2fddbdcbd4d451a7
+size 1206060120
diff --git a/model-00439-of-00527.safetensors b/model-00439-of-00527.safetensors
index bfe983b5fa182e5c193131531ac5518379cd0c0a..44ee831beeb44b5d1e48743210417c527c744cc8 100644
--- a/model-00439-of-00527.safetensors
+++ b/model-00439-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e33fdfdcc67044eccaf9152d2d722f73676b074afd40d2e360e123ecd1c330b
-size 1270743736
+oid sha256:8d0cdda10927e5fabe3a1101c3c686f34eaafa9cddeee3e7b82b0940b29a9722
+size 1206060056
diff --git a/model-00447-of-00527.safetensors b/model-00447-of-00527.safetensors
index 80cb24ab751d6b738a6b6d8040519a6b5f67a5c8..cba2c3cb92bb4c2222a6b1c038a65e67efe1c274 100644
--- a/model-00447-of-00527.safetensors
+++ b/model-00447-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff992275cfad94be0f0d0571a3b40c582118a5a5cb9cf41af3037dc3b63a881e
-size 1159463304
+oid sha256:02ee9da91d20a054fd0c8a85d571bbf5bea75785760fb1ab1b056ad25edc56d1
+size 1094779600
diff --git a/model-00456-of-00527.safetensors b/model-00456-of-00527.safetensors
index efda52ca2d2b9de62a8a34bb83880cf9617d0f3f..210db151ffdfe2bed47aba2d225569b2a5b14b2e 100644
--- a/model-00456-of-00527.safetensors
+++ b/model-00456-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3edc944fbe70af30d64cc72dce4f91dbe0fab342b7e55c94cb59129ed2461d77
-size 1270743872
+oid sha256:223c104c725576356672d43ea3a5a0b0ae97f645a4ffd57307a2d225ba8d14fd
+size 1206060192
diff --git a/model-00465-of-00527.safetensors b/model-00465-of-00527.safetensors
index aff7f8f44c0dc54de5c4c913eb43b71485689700..41f24ead0ebc6bc83d9e2fa13a35a37e195c912a 100644
--- a/model-00465-of-00527.safetensors
+++ b/model-00465-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aed45a66cc09819937614bb94e87047e0aef09a4ecf6126b36fd5115f0290417
-size 1270743808
+oid sha256:12a3d8b4a242f51f373760d675cb17694160e7447bc23b843352d4faa48c80aa
+size 1206060128
diff --git a/model-00474-of-00527.safetensors b/model-00474-of-00527.safetensors
index 8956ee72665c5fc09aa388ca06b9b91df2267771..758f05201c7f7fb0c38aa568ea1cffb16d0247a2 100644
--- a/model-00474-of-00527.safetensors
+++ b/model-00474-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:685b7f886074acdc2198ebb919995a03d7025c2b97116a0308a9808b5ce4d031
-size 1270743744
+oid sha256:2cd92d9bb2aefb5aa2c427f565e5228d993098ae327b8d7f64007aaeb785b05b
+size 1206060056
diff --git a/model-00482-of-00527.safetensors b/model-00482-of-00527.safetensors
index 3ace644345f51a2ef051e16b7073b26a0142fd2b..caa4a86fcbe9c9db6e995b230be079fee9000bb4 100644
--- a/model-00482-of-00527.safetensors
+++ b/model-00482-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cb97b538c0534c5f79070d6d85d31ac69e6de15117904022574c3c8ce0a0aac
-size 1121714424
+oid sha256:81ecd6537f9f953484ad26f7e9d12e9bb4b716afbbb79c98d9138faed8827323
+size 1057030712
diff --git a/model-00491-of-00527.safetensors b/model-00491-of-00527.safetensors
index ed1214e15396faccb4d8990c3a3bcce730002a78..d4fa18832a6bf7014d2e14bed8fe902a7d12ded9 100644
--- a/model-00491-of-00527.safetensors
+++ b/model-00491-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad0b87c57c973cbc7230b7a2521c0bbecc3d6a7d242ea1326489bb23173f2c07
-size 1270743880
+oid sha256:97f4f4d85f5b6cc8444d43766bd8ec2be28efa44ef99da3b1b2254deb85cc8d9
+size 1206060200
diff --git a/model-00500-of-00527.safetensors b/model-00500-of-00527.safetensors
index 1a008930dbc39bf9aa23b4742e5f573659248777..a91cf55a7fb7257ec95765dae599f7b38d57bac9 100644
--- a/model-00500-of-00527.safetensors
+++ b/model-00500-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de310a674d7bc0c9b555111c1595e5d37e8e4788c77ddd8fe29055b0bfdda9d5
-size 1270743816
+oid sha256:35a35397701fd1f2e49d77a491975c6b74005cf604f7f98916c6f94d7f0ca7f3
+size 1206060128
diff --git a/model-00509-of-00527.safetensors b/model-00509-of-00527.safetensors
index 2920169fb30233db651231ff235a8ab3c8744bb5..0018da0a52b887cf836502e888a62dbcc7e61841 100644
--- a/model-00509-of-00527.safetensors
+++ b/model-00509-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdf925a0c6fe062426383633cb8d1c9bf2c5950d64add027b523ff7b4ca1071f
-size 1270743744
+oid sha256:48383d9b6a68a56ba084bf298c8443af27ec4d5cf70b1166781879ca91ea2760
+size 1206060064
diff --git a/model-00517-of-00527.safetensors b/model-00517-of-00527.safetensors
index 974644ae46345a6a1dd6328353225ff3d5ec6ae9..2ec3ac7f12f3cd382772a2b9a641cd0964c17a03 100644
--- a/model-00517-of-00527.safetensors
+++ b/model-00517-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a338d729a1012b38cbda260d0f5f9e866019631b657433fa296422876d60c7c6
-size 1107490048
+oid sha256:6bceed7c72c0a478df3b735b3fc7ec23446792c0ebb52e6368c6969c3e144314
+size 1042806328
diff --git a/model-00526-of-00527.safetensors b/model-00526-of-00527.safetensors
index c178cd8d105cbf160a27d4ba3af0798ca20abcad..5ff78e8228f1ac51ba122a041e1f147e8a4b6631 100644
--- a/model-00526-of-00527.safetensors
+++ b/model-00526-of-00527.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:768e484a811e3c067214e061993ea9541a0128b66b88bf37be64055f2eedf477
-size 850136320
+oid sha256:dee5380b95f81f424a557749ffe8ce34800ed629ba065182f8a8bf5064f3d072
+size 785452624
diff --git a/model.safetensors.index.json b/model.safetensors.index.json
index c492d9a3a19cae9cf39315f861c5a939e1f0e505..b84a8d75dc986d39cb9bcd04275b47e617b2c4e4 100644
--- a/model.safetensors.index.json
+++ b/model.safetensors.index.json
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97e465ad6bd89777a0ebb70137cf0382db9e48a473ab29120426892bec6bfe96
-size 13612128
+oid sha256:7b227c188c4632a360ddf1dd20fa0ae961b8b359eb58ff3f28a9733206225e2e
+size 13630881
diff --git a/quark_profile.yaml b/quark_profile.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..f3e7c2e07f28c023007f4e462351117f85932461
--- /dev/null
+++ b/quark_profile.yaml
@@ -0,0 +1,78 @@
+# Quark Profiling Results
+
+memory_usage:
+- step: "Start"
+  timestamp: 1775558616.0383444
+  relative_time_secs: 0.0
+  cpu_memory_mb: 4298.65
+  gpu_memory_mb: 920.8
+  disk_read_mb: 0.0
+  disk_write_mb: 0.0
+- step: "File-to-File Quantization Start"
+  timestamp: 1775558616.1580837
+  relative_time_secs: 0.11973929405212402
+  cpu_memory_mb: 4298.65
+  gpu_memory_mb: 920.8
+  disk_read_mb: 0.0
+  disk_write_mb: 0.0
+- step: "File-to-File Quantization Start"
+  timestamp: 1775558616.296224
+  relative_time_secs: 0.25787973403930664
+  cpu_memory_mb: 4298.65
+  gpu_memory_mb: 920.8
+  disk_read_mb: 0.0
+  disk_write_mb: 0.0
+- step: "File-to-File Quantization End"
+  timestamp: 1775558618.6665556
+  relative_time_secs: 2.628211259841919
+  cpu_memory_mb: 4787.26
+  gpu_memory_mb: 920.89
+  disk_read_mb: 50.13
+  disk_write_mb: 193.75
+- step: "File-to-File Quantization End"
+  timestamp: 1775558618.7877855
+  relative_time_secs: 2.749441146850586
+  cpu_memory_mb: 4787.26
+  gpu_memory_mb: 920.89
+  disk_read_mb: 50.13
+  disk_write_mb: 193.75
+- step: "End"
+  timestamp: 1775558618.9069457
+  relative_time_secs: 2.8686013221740723
+  cpu_memory_mb: 4787.26
+  gpu_memory_mb: 920.89
+  disk_read_mb: 50.13
+  disk_write_mb: 193.75
+
+# Summary Metrics
+total_quantization_time_seconds: 2.8686
+peak_memory_mb: 9218.02
+peak_gpu_memory_mb: 920.89
+total_disk_read_mb: 50.13
+total_disk_write_mb: 193.75
+
+# Metric Definitions:
+#
+# Checkpoint Metrics (per record):
+# - step: Name of the profiling checkpoint. Common steps include:
+#    - "Start": Initial state when profiling begins
+#    - "Model Loaded": After loading the ONNX model into memory
+#    - "Pre-process Start/End": Before and after model preprocessing
+#    - "Calibration Start/End": Before and after calibration data collection
+#    - "Quantization (MatMulNBits) Start/End": MatMulNBits quantization phase
+#    - "Quantization (Static) Start/End": Static quantization phase
+#    - "Post-process Start/End": Before and after post-processing
+#    - "Fast Finetune Start/End": Before and after fast finetuning (if enabled)
+# - timestamp: Unix timestamp (seconds since epoch) when this measurement was taken. Useful for correlating with external logs or events.
+# - relative_time_secs: Time elapsed (in seconds) since the "Start" step. Useful for understanding the duration of each phase relative to the beginning of profiling.
+# - cpu_memory_mb: Current Resident Set Size (RSS) in megabytes at this step. This includes memory from the main process and all child processes. RSS represents the portion of memory held in RAM (not swapped out).
+# - gpu_memory_mb: Current GPU memory usage in megabytes. This represents actual GPU memory used by the process, including allocations from PyTorch, ONNX Runtime, TensorRT, and other frameworks. Only available when PyTorch with CUDA/ROCm is installed and GPU is available.
+# - disk_read_mb: Cumulative disk bytes read (in megabytes) since the start of profiling. Measured relative to the baseline captured at the 'Start' checkpoint, including I/O from the main process and all child processes. Only available when psutil is installed and the OS exposes per-process I/O counters (Linux /proc/<pid>/io, Windows; not available on macOS without root).
+# - disk_write_mb: Cumulative disk bytes written (in megabytes) since the start of profiling. Measured relative to the baseline captured at the 'Start' checkpoint, including I/O from the main process and all child processes. Only available when psutil is installed and the OS exposes per-process I/O counters (Linux /proc/<pid>/io, Windows; not available on macOS without root).
+#
+# Summary Metrics (overall):
+# - total_quantization_time_seconds: Total elapsed time (in seconds) from the start of profiling to the end of the quantization process.
+# - peak_memory_mb: Peak resident set size (RSS) in megabytes for the main process during the entire profiling session. On Linux, this is read from VmHWM (high water mark) in /proc/<pid>/status. On Windows, this is the peak working set size. This metric may not be available on all platforms.
+# - peak_gpu_memory_mb: Peak GPU memory usage in megabytes during the entire profiling session. This is the maximum GPU memory used, including allocations from PyTorch, ONNX Runtime, TensorRT, and other frameworks. Only available when PyTorch with CUDA/ROCm is installed and GPU is available.
+# - total_disk_read_mb: Total disk bytes read (in megabytes) during the entire profiling session. Computed as the difference between the final and baseline cumulative read counters, including I/O from the main process and all child processes. Only available when psutil is installed and the OS exposes per-process I/O counters (Linux /proc/<pid>/io, Windows; not available on macOS without root).
+# - total_disk_write_mb: Total disk bytes written (in megabytes) during the entire profiling session. Computed as the difference between the final and baseline cumulative write counters, including I/O from the main process and all child processes. Only available when psutil is installed and the OS exposes per-process I/O counters (Linux /proc/<pid>/io, Windows; not available on macOS without root).