quantize mlp.up_proj, mlp.down_proj, shared_experts

by jiaxwang - opened 14 days ago

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

+822

-142

This view is limited to 50 files because it contains too many changes. See the raw diff here.

Files changed (50) hide show

.gitattributes +1 -0
chat_template.jinja +1 -5
config.json +532 -8
docs/deploy_guidance.md +82 -0
figures/demo_video.mp4 +3 -0
figures/kimi-logo.png +0 -0
model-00001-of-000064.safetensors +2 -2
model-00002-of-000064.safetensors +2 -2
model-00003-of-000064.safetensors +2 -2
model-00004-of-000064.safetensors +2 -2
model-00005-of-000064.safetensors +2 -2
model-00006-of-000064.safetensors +2 -2
model-00007-of-000064.safetensors +2 -2
model-00008-of-000064.safetensors +2 -2
model-00009-of-000064.safetensors +2 -2
model-00010-of-000064.safetensors +2 -2
model-00011-of-000064.safetensors +2 -2
model-00012-of-000064.safetensors +2 -2
model-00013-of-000064.safetensors +2 -2
model-00014-of-000064.safetensors +2 -2
model-00015-of-000064.safetensors +2 -2
model-00016-of-000064.safetensors +2 -2
model-00017-of-000064.safetensors +2 -2
model-00018-of-000064.safetensors +2 -2
model-00019-of-000064.safetensors +2 -2
model-00020-of-000064.safetensors +2 -2
model-00021-of-000064.safetensors +2 -2
model-00022-of-000064.safetensors +2 -2
model-00023-of-000064.safetensors +2 -2
model-00024-of-000064.safetensors +2 -2
model-00025-of-000064.safetensors +2 -2
model-00026-of-000064.safetensors +2 -2
model-00027-of-000064.safetensors +2 -2
model-00028-of-000064.safetensors +2 -2
model-00029-of-000064.safetensors +2 -2
model-00030-of-000064.safetensors +2 -2
model-00031-of-000064.safetensors +2 -2
model-00032-of-000064.safetensors +2 -2
model-00033-of-000064.safetensors +2 -2
model-00034-of-000064.safetensors +2 -2
model-00035-of-000064.safetensors +2 -2
model-00036-of-000064.safetensors +2 -2
model-00037-of-000064.safetensors +2 -2
model-00038-of-000064.safetensors +2 -2
model-00039-of-000064.safetensors +2 -2
model-00040-of-000064.safetensors +2 -2
model-00041-of-000064.safetensors +2 -2
model-00042-of-000064.safetensors +2 -2
model-00043-of-000064.safetensors +2 -2
model-00044-of-000064.safetensors +2 -2

.gitattributes CHANGED Viewed

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text

 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
+figures/demo_video.mp4 filter=lfs diff=lfs merge=lfs -text

chat_template.jinja CHANGED Viewed

@@ -5,7 +5,7 @@
     {%- elif c is not none -%}
       {% for content in c -%}
         {% if content['type'] == 'image' or content['type'] == 'image_url' -%}
-          <|media_start|>image<|media_content|><|media_pad|><|media_end|>
         {% elif content['type'] == 'video' or content['type']== 'video_url'-%}
           <|kimi_k25_video_placeholder|>
         {% else -%}
@@ -57,10 +57,6 @@
     <|im_system|>tool_declare<|im_middle|>{{ tools | tojson(separators=(',', ':')) }}<|im_end|>
   {%- endif -%}
 {%- 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 -%}
   {{set_roles(message)}}

     {%- elif c is not none -%}
       {% for content in c -%}
         {% if content['type'] == 'image' or content['type'] == 'image_url' -%}
+          <|media_begin|>image<|media_content|><|media_pad|><|media_end|>
         {% elif content['type'] == 'video' or content['type']== 'video_url'-%}
           <|kimi_k25_video_placeholder|>
         {% else -%}
     <|im_system|>tool_declare<|im_middle|>{{ tools | tojson(separators=(',', ':')) }}<|im_end|>
   {%- endif -%}
 {%- endif -%}
 {%- for message in hist_msgs -%}
   {{set_roles(message)}}

config.json CHANGED Viewed

@@ -193,12 +193,536 @@
             "target_device": null
         },
         "exclude": [
-        	"lm_head",
-        	"re:.*self_attn.*",
-        	"re:.*shared_experts.*",
-        	"re:.*mlp\\.(gate|up|gate_up|down)_proj.*",
-		"re:mm_projector.*",
-		"re:vision_tower.*"
         ],
         "algo_config": null,
         "softmax_quant_spec": null,
@@ -208,7 +732,7 @@
         "kv_cache_quant_config": {},
         "kv_cache_post_rope": false,
         "quant_mode": "eager_mode",
-        "version": "0.11+4a34634b4a",
         "export": {
             "kv_cache_group": [],
             "min_kv_scale": 0.0,
@@ -217,4 +741,4 @@
             "weight_merge_groups": null
         }
     }
-}

             "target_device": null
         },
         "exclude": [
+            "language_model.lm_head",
+            "language_model.model.layers.0.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.0.self_attn.kv_b_proj",
+            "language_model.model.layers.0.self_attn.o_proj",
+            "language_model.model.layers.0.self_attn.q_a_proj",
+            "language_model.model.layers.0.self_attn.q_b_proj",
+            "language_model.model.layers.1.mlp.gate",
+            "language_model.model.layers.1.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.1.self_attn.kv_b_proj",
+            "language_model.model.layers.1.self_attn.o_proj",
+            "language_model.model.layers.1.self_attn.q_a_proj",
+            "language_model.model.layers.1.self_attn.q_b_proj",
+            "language_model.model.layers.10.mlp.gate",
+            "language_model.model.layers.10.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.10.self_attn.kv_b_proj",
+            "language_model.model.layers.10.self_attn.o_proj",
+            "language_model.model.layers.10.self_attn.q_a_proj",
+            "language_model.model.layers.10.self_attn.q_b_proj",
+            "language_model.model.layers.11.mlp.gate",
+            "language_model.model.layers.11.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.11.self_attn.kv_b_proj",
+            "language_model.model.layers.11.self_attn.o_proj",
+            "language_model.model.layers.11.self_attn.q_a_proj",
+            "language_model.model.layers.11.self_attn.q_b_proj",
+            "language_model.model.layers.12.mlp.gate",
+            "language_model.model.layers.12.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.12.self_attn.kv_b_proj",
+            "language_model.model.layers.12.self_attn.o_proj",
+            "language_model.model.layers.12.self_attn.q_a_proj",
+            "language_model.model.layers.12.self_attn.q_b_proj",
+            "language_model.model.layers.13.mlp.gate",
+            "language_model.model.layers.13.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.13.self_attn.kv_b_proj",
+            "language_model.model.layers.13.self_attn.o_proj",
+            "language_model.model.layers.13.self_attn.q_a_proj",
+            "language_model.model.layers.13.self_attn.q_b_proj",
+            "language_model.model.layers.14.mlp.gate",
+            "language_model.model.layers.14.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.14.self_attn.kv_b_proj",
+            "language_model.model.layers.14.self_attn.o_proj",
+            "language_model.model.layers.14.self_attn.q_a_proj",
+            "language_model.model.layers.14.self_attn.q_b_proj",
+            "language_model.model.layers.15.mlp.gate",
+            "language_model.model.layers.15.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.15.self_attn.kv_b_proj",
+            "language_model.model.layers.15.self_attn.o_proj",
+            "language_model.model.layers.15.self_attn.q_a_proj",
+            "language_model.model.layers.15.self_attn.q_b_proj",
+            "language_model.model.layers.16.mlp.gate",
+            "language_model.model.layers.16.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.16.self_attn.kv_b_proj",
+            "language_model.model.layers.16.self_attn.o_proj",
+            "language_model.model.layers.16.self_attn.q_a_proj",
+            "language_model.model.layers.16.self_attn.q_b_proj",
+            "language_model.model.layers.17.mlp.gate",
+            "language_model.model.layers.17.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.17.self_attn.kv_b_proj",
+            "language_model.model.layers.17.self_attn.o_proj",
+            "language_model.model.layers.17.self_attn.q_a_proj",
+            "language_model.model.layers.17.self_attn.q_b_proj",
+            "language_model.model.layers.18.mlp.gate",
+            "language_model.model.layers.18.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.18.self_attn.kv_b_proj",
+            "language_model.model.layers.18.self_attn.o_proj",
+            "language_model.model.layers.18.self_attn.q_a_proj",
+            "language_model.model.layers.18.self_attn.q_b_proj",
+            "language_model.model.layers.19.mlp.gate",
+            "language_model.model.layers.19.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.19.self_attn.kv_b_proj",
+            "language_model.model.layers.19.self_attn.o_proj",
+            "language_model.model.layers.19.self_attn.q_a_proj",
+            "language_model.model.layers.19.self_attn.q_b_proj",
+            "language_model.model.layers.2.mlp.gate",
+            "language_model.model.layers.2.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.2.self_attn.kv_b_proj",
+            "language_model.model.layers.2.self_attn.o_proj",
+            "language_model.model.layers.2.self_attn.q_a_proj",
+            "language_model.model.layers.2.self_attn.q_b_proj",
+            "language_model.model.layers.20.mlp.gate",
+            "language_model.model.layers.20.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.20.self_attn.kv_b_proj",
+            "language_model.model.layers.20.self_attn.o_proj",
+            "language_model.model.layers.20.self_attn.q_a_proj",
+            "language_model.model.layers.20.self_attn.q_b_proj",
+            "language_model.model.layers.21.mlp.gate",
+            "language_model.model.layers.21.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.21.self_attn.kv_b_proj",
+            "language_model.model.layers.21.self_attn.o_proj",
+            "language_model.model.layers.21.self_attn.q_a_proj",
+            "language_model.model.layers.21.self_attn.q_b_proj",
+            "language_model.model.layers.22.mlp.gate",
+            "language_model.model.layers.22.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.22.self_attn.kv_b_proj",
+            "language_model.model.layers.22.self_attn.o_proj",
+            "language_model.model.layers.22.self_attn.q_a_proj",
+            "language_model.model.layers.22.self_attn.q_b_proj",
+            "language_model.model.layers.23.mlp.gate",
+            "language_model.model.layers.23.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.23.self_attn.kv_b_proj",
+            "language_model.model.layers.23.self_attn.o_proj",
+            "language_model.model.layers.23.self_attn.q_a_proj",
+            "language_model.model.layers.23.self_attn.q_b_proj",
+            "language_model.model.layers.24.mlp.gate",
+            "language_model.model.layers.24.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.24.self_attn.kv_b_proj",
+            "language_model.model.layers.24.self_attn.o_proj",
+            "language_model.model.layers.24.self_attn.q_a_proj",
+            "language_model.model.layers.24.self_attn.q_b_proj",
+            "language_model.model.layers.25.mlp.gate",
+            "language_model.model.layers.25.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.25.self_attn.kv_b_proj",
+            "language_model.model.layers.25.self_attn.o_proj",
+            "language_model.model.layers.25.self_attn.q_a_proj",
+            "language_model.model.layers.25.self_attn.q_b_proj",
+            "language_model.model.layers.26.mlp.gate",
+            "language_model.model.layers.26.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.26.self_attn.kv_b_proj",
+            "language_model.model.layers.26.self_attn.o_proj",
+            "language_model.model.layers.26.self_attn.q_a_proj",
+            "language_model.model.layers.26.self_attn.q_b_proj",
+            "language_model.model.layers.27.mlp.gate",
+            "language_model.model.layers.27.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.27.self_attn.kv_b_proj",
+            "language_model.model.layers.27.self_attn.o_proj",
+            "language_model.model.layers.27.self_attn.q_a_proj",
+            "language_model.model.layers.27.self_attn.q_b_proj",
+            "language_model.model.layers.28.mlp.gate",
+            "language_model.model.layers.28.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.28.self_attn.kv_b_proj",
+            "language_model.model.layers.28.self_attn.o_proj",
+            "language_model.model.layers.28.self_attn.q_a_proj",
+            "language_model.model.layers.28.self_attn.q_b_proj",
+            "language_model.model.layers.29.mlp.gate",
+            "language_model.model.layers.29.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.29.self_attn.kv_b_proj",
+            "language_model.model.layers.29.self_attn.o_proj",
+            "language_model.model.layers.29.self_attn.q_a_proj",
+            "language_model.model.layers.29.self_attn.q_b_proj",
+            "language_model.model.layers.3.mlp.gate",
+            "language_model.model.layers.3.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.3.self_attn.kv_b_proj",
+            "language_model.model.layers.3.self_attn.o_proj",
+            "language_model.model.layers.3.self_attn.q_a_proj",
+            "language_model.model.layers.3.self_attn.q_b_proj",
+            "language_model.model.layers.30.mlp.gate",
+            "language_model.model.layers.30.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.30.self_attn.kv_b_proj",
+            "language_model.model.layers.30.self_attn.o_proj",
+            "language_model.model.layers.30.self_attn.q_a_proj",
+            "language_model.model.layers.30.self_attn.q_b_proj",
+            "language_model.model.layers.31.mlp.gate",
+            "language_model.model.layers.31.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.31.self_attn.kv_b_proj",
+            "language_model.model.layers.31.self_attn.o_proj",
+            "language_model.model.layers.31.self_attn.q_a_proj",
+            "language_model.model.layers.31.self_attn.q_b_proj",
+            "language_model.model.layers.32.mlp.gate",
+            "language_model.model.layers.32.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.32.self_attn.kv_b_proj",
+            "language_model.model.layers.32.self_attn.o_proj",
+            "language_model.model.layers.32.self_attn.q_a_proj",
+            "language_model.model.layers.32.self_attn.q_b_proj",
+            "language_model.model.layers.33.mlp.gate",
+            "language_model.model.layers.33.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.33.self_attn.kv_b_proj",
+            "language_model.model.layers.33.self_attn.o_proj",
+            "language_model.model.layers.33.self_attn.q_a_proj",
+            "language_model.model.layers.33.self_attn.q_b_proj",
+            "language_model.model.layers.34.mlp.gate",
+            "language_model.model.layers.34.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.34.self_attn.kv_b_proj",
+            "language_model.model.layers.34.self_attn.o_proj",
+            "language_model.model.layers.34.self_attn.q_a_proj",
+            "language_model.model.layers.34.self_attn.q_b_proj",
+            "language_model.model.layers.35.mlp.gate",
+            "language_model.model.layers.35.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.35.self_attn.kv_b_proj",
+            "language_model.model.layers.35.self_attn.o_proj",
+            "language_model.model.layers.35.self_attn.q_a_proj",
+            "language_model.model.layers.35.self_attn.q_b_proj",
+            "language_model.model.layers.36.mlp.gate",
+            "language_model.model.layers.36.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.36.self_attn.kv_b_proj",
+            "language_model.model.layers.36.self_attn.o_proj",
+            "language_model.model.layers.36.self_attn.q_a_proj",
+            "language_model.model.layers.36.self_attn.q_b_proj",
+            "language_model.model.layers.37.mlp.gate",
+            "language_model.model.layers.37.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.37.self_attn.kv_b_proj",
+            "language_model.model.layers.37.self_attn.o_proj",
+            "language_model.model.layers.37.self_attn.q_a_proj",
+            "language_model.model.layers.37.self_attn.q_b_proj",
+            "language_model.model.layers.38.mlp.gate",
+            "language_model.model.layers.38.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.38.self_attn.kv_b_proj",
+            "language_model.model.layers.38.self_attn.o_proj",
+            "language_model.model.layers.38.self_attn.q_a_proj",
+            "language_model.model.layers.38.self_attn.q_b_proj",
+            "language_model.model.layers.39.mlp.gate",
+            "language_model.model.layers.39.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.39.self_attn.kv_b_proj",
+            "language_model.model.layers.39.self_attn.o_proj",
+            "language_model.model.layers.39.self_attn.q_a_proj",
+            "language_model.model.layers.39.self_attn.q_b_proj",
+            "language_model.model.layers.4.mlp.gate",
+            "language_model.model.layers.4.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.4.self_attn.kv_b_proj",
+            "language_model.model.layers.4.self_attn.o_proj",
+            "language_model.model.layers.4.self_attn.q_a_proj",
+            "language_model.model.layers.4.self_attn.q_b_proj",
+            "language_model.model.layers.40.mlp.gate",
+            "language_model.model.layers.40.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.40.self_attn.kv_b_proj",
+            "language_model.model.layers.40.self_attn.o_proj",
+            "language_model.model.layers.40.self_attn.q_a_proj",
+            "language_model.model.layers.40.self_attn.q_b_proj",
+            "language_model.model.layers.41.mlp.gate",
+            "language_model.model.layers.41.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.41.self_attn.kv_b_proj",
+            "language_model.model.layers.41.self_attn.o_proj",
+            "language_model.model.layers.41.self_attn.q_a_proj",
+            "language_model.model.layers.41.self_attn.q_b_proj",
+            "language_model.model.layers.42.mlp.gate",
+            "language_model.model.layers.42.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.42.self_attn.kv_b_proj",
+            "language_model.model.layers.42.self_attn.o_proj",
+            "language_model.model.layers.42.self_attn.q_a_proj",
+            "language_model.model.layers.42.self_attn.q_b_proj",
+            "language_model.model.layers.43.mlp.gate",
+            "language_model.model.layers.43.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.43.self_attn.kv_b_proj",
+            "language_model.model.layers.43.self_attn.o_proj",
+            "language_model.model.layers.43.self_attn.q_a_proj",
+            "language_model.model.layers.43.self_attn.q_b_proj",
+            "language_model.model.layers.44.mlp.gate",
+            "language_model.model.layers.44.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.44.self_attn.kv_b_proj",
+            "language_model.model.layers.44.self_attn.o_proj",
+            "language_model.model.layers.44.self_attn.q_a_proj",
+            "language_model.model.layers.44.self_attn.q_b_proj",
+            "language_model.model.layers.45.mlp.gate",
+            "language_model.model.layers.45.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.45.self_attn.kv_b_proj",
+            "language_model.model.layers.45.self_attn.o_proj",
+            "language_model.model.layers.45.self_attn.q_a_proj",
+            "language_model.model.layers.45.self_attn.q_b_proj",
+            "language_model.model.layers.46.mlp.gate",
+            "language_model.model.layers.46.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.46.self_attn.kv_b_proj",
+            "language_model.model.layers.46.self_attn.o_proj",
+            "language_model.model.layers.46.self_attn.q_a_proj",
+            "language_model.model.layers.46.self_attn.q_b_proj",
+            "language_model.model.layers.47.mlp.gate",
+            "language_model.model.layers.47.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.47.self_attn.kv_b_proj",
+            "language_model.model.layers.47.self_attn.o_proj",
+            "language_model.model.layers.47.self_attn.q_a_proj",
+            "language_model.model.layers.47.self_attn.q_b_proj",
+            "language_model.model.layers.48.mlp.gate",
+            "language_model.model.layers.48.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.48.self_attn.kv_b_proj",
+            "language_model.model.layers.48.self_attn.o_proj",
+            "language_model.model.layers.48.self_attn.q_a_proj",
+            "language_model.model.layers.48.self_attn.q_b_proj",
+            "language_model.model.layers.49.mlp.gate",
+            "language_model.model.layers.49.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.49.self_attn.kv_b_proj",
+            "language_model.model.layers.49.self_attn.o_proj",
+            "language_model.model.layers.49.self_attn.q_a_proj",
+            "language_model.model.layers.49.self_attn.q_b_proj",
+            "language_model.model.layers.5.mlp.gate",
+            "language_model.model.layers.5.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.5.self_attn.kv_b_proj",
+            "language_model.model.layers.5.self_attn.o_proj",
+            "language_model.model.layers.5.self_attn.q_a_proj",
+            "language_model.model.layers.5.self_attn.q_b_proj",
+            "language_model.model.layers.50.mlp.gate",
+            "language_model.model.layers.50.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.50.self_attn.kv_b_proj",
+            "language_model.model.layers.50.self_attn.o_proj",
+            "language_model.model.layers.50.self_attn.q_a_proj",
+            "language_model.model.layers.50.self_attn.q_b_proj",
+            "language_model.model.layers.51.mlp.gate",
+            "language_model.model.layers.51.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.51.self_attn.kv_b_proj",
+            "language_model.model.layers.51.self_attn.o_proj",
+            "language_model.model.layers.51.self_attn.q_a_proj",
+            "language_model.model.layers.51.self_attn.q_b_proj",
+            "language_model.model.layers.52.mlp.gate",
+            "language_model.model.layers.52.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.52.self_attn.kv_b_proj",
+            "language_model.model.layers.52.self_attn.o_proj",
+            "language_model.model.layers.52.self_attn.q_a_proj",
+            "language_model.model.layers.52.self_attn.q_b_proj",
+            "language_model.model.layers.53.mlp.gate",
+            "language_model.model.layers.53.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.53.self_attn.kv_b_proj",
+            "language_model.model.layers.53.self_attn.o_proj",
+            "language_model.model.layers.53.self_attn.q_a_proj",
+            "language_model.model.layers.53.self_attn.q_b_proj",
+            "language_model.model.layers.54.mlp.gate",
+            "language_model.model.layers.54.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.54.self_attn.kv_b_proj",
+            "language_model.model.layers.54.self_attn.o_proj",
+            "language_model.model.layers.54.self_attn.q_a_proj",
+            "language_model.model.layers.54.self_attn.q_b_proj",
+            "language_model.model.layers.55.mlp.gate",
+            "language_model.model.layers.55.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.55.self_attn.kv_b_proj",
+            "language_model.model.layers.55.self_attn.o_proj",
+            "language_model.model.layers.55.self_attn.q_a_proj",
+            "language_model.model.layers.55.self_attn.q_b_proj",
+            "language_model.model.layers.56.mlp.gate",
+            "language_model.model.layers.56.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.56.self_attn.kv_b_proj",
+            "language_model.model.layers.56.self_attn.o_proj",
+            "language_model.model.layers.56.self_attn.q_a_proj",
+            "language_model.model.layers.56.self_attn.q_b_proj",
+            "language_model.model.layers.57.mlp.gate",
+            "language_model.model.layers.57.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.57.self_attn.kv_b_proj",
+            "language_model.model.layers.57.self_attn.o_proj",
+            "language_model.model.layers.57.self_attn.q_a_proj",
+            "language_model.model.layers.57.self_attn.q_b_proj",
+            "language_model.model.layers.58.mlp.gate",
+            "language_model.model.layers.58.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.58.self_attn.kv_b_proj",
+            "language_model.model.layers.58.self_attn.o_proj",
+            "language_model.model.layers.58.self_attn.q_a_proj",
+            "language_model.model.layers.58.self_attn.q_b_proj",
+            "language_model.model.layers.59.mlp.gate",
+            "language_model.model.layers.59.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.59.self_attn.kv_b_proj",
+            "language_model.model.layers.59.self_attn.o_proj",
+            "language_model.model.layers.59.self_attn.q_a_proj",
+            "language_model.model.layers.59.self_attn.q_b_proj",
+            "language_model.model.layers.6.mlp.gate",
+            "language_model.model.layers.6.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.6.self_attn.kv_b_proj",
+            "language_model.model.layers.6.self_attn.o_proj",
+            "language_model.model.layers.6.self_attn.q_a_proj",
+            "language_model.model.layers.6.self_attn.q_b_proj",
+            "language_model.model.layers.60.mlp.gate",
+            "language_model.model.layers.60.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.60.self_attn.kv_b_proj",
+            "language_model.model.layers.60.self_attn.o_proj",
+            "language_model.model.layers.60.self_attn.q_a_proj",
+            "language_model.model.layers.60.self_attn.q_b_proj",
+            "language_model.model.layers.7.mlp.gate",
+            "language_model.model.layers.7.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.7.self_attn.kv_b_proj",
+            "language_model.model.layers.7.self_attn.o_proj",
+            "language_model.model.layers.7.self_attn.q_a_proj",
+            "language_model.model.layers.7.self_attn.q_b_proj",
+            "language_model.model.layers.8.mlp.gate",
+            "language_model.model.layers.8.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.8.self_attn.kv_b_proj",
+            "language_model.model.layers.8.self_attn.o_proj",
+            "language_model.model.layers.8.self_attn.q_a_proj",
+            "language_model.model.layers.8.self_attn.q_b_proj",
+            "language_model.model.layers.9.mlp.gate",
+            "language_model.model.layers.9.self_attn.kv_a_proj_with_mqa",
+            "language_model.model.layers.9.self_attn.kv_b_proj",
+            "language_model.model.layers.9.self_attn.o_proj",
+            "language_model.model.layers.9.self_attn.q_a_proj",
+            "language_model.model.layers.9.self_attn.q_b_proj",
+            "mm_projector.proj.0",
+            "mm_projector.proj.2",
+            "vision_tower.encoder.blocks.0.mlp.fc0",
+            "vision_tower.encoder.blocks.0.mlp.fc1",
+            "vision_tower.encoder.blocks.0.norm0",
+            "vision_tower.encoder.blocks.0.norm1",
+            "vision_tower.encoder.blocks.0.wo",
+            "vision_tower.encoder.blocks.0.wqkv",
+            "vision_tower.encoder.blocks.1.mlp.fc0",
+            "vision_tower.encoder.blocks.1.mlp.fc1",
+            "vision_tower.encoder.blocks.1.norm0",
+            "vision_tower.encoder.blocks.1.norm1",
+            "vision_tower.encoder.blocks.1.wo",
+            "vision_tower.encoder.blocks.1.wqkv",
+            "vision_tower.encoder.blocks.10.mlp.fc0",
+            "vision_tower.encoder.blocks.10.mlp.fc1",
+            "vision_tower.encoder.blocks.10.norm0",
+            "vision_tower.encoder.blocks.10.norm1",
+            "vision_tower.encoder.blocks.10.wo",
+            "vision_tower.encoder.blocks.10.wqkv",
+            "vision_tower.encoder.blocks.11.mlp.fc0",
+            "vision_tower.encoder.blocks.11.mlp.fc1",
+            "vision_tower.encoder.blocks.11.norm0",
+            "vision_tower.encoder.blocks.11.norm1",
+            "vision_tower.encoder.blocks.11.wo",
+            "vision_tower.encoder.blocks.11.wqkv",
+            "vision_tower.encoder.blocks.12.mlp.fc0",
+            "vision_tower.encoder.blocks.12.mlp.fc1",
+            "vision_tower.encoder.blocks.12.norm0",
+            "vision_tower.encoder.blocks.12.norm1",
+            "vision_tower.encoder.blocks.12.wo",
+            "vision_tower.encoder.blocks.12.wqkv",
+            "vision_tower.encoder.blocks.13.mlp.fc0",
+            "vision_tower.encoder.blocks.13.mlp.fc1",
+            "vision_tower.encoder.blocks.13.norm0",
+            "vision_tower.encoder.blocks.13.norm1",
+            "vision_tower.encoder.blocks.13.wo",
+            "vision_tower.encoder.blocks.13.wqkv",
+            "vision_tower.encoder.blocks.14.mlp.fc0",
+            "vision_tower.encoder.blocks.14.mlp.fc1",
+            "vision_tower.encoder.blocks.14.norm0",
+            "vision_tower.encoder.blocks.14.norm1",
+            "vision_tower.encoder.blocks.14.wo",
+            "vision_tower.encoder.blocks.14.wqkv",
+            "vision_tower.encoder.blocks.15.mlp.fc0",
+            "vision_tower.encoder.blocks.15.mlp.fc1",
+            "vision_tower.encoder.blocks.15.norm0",
+            "vision_tower.encoder.blocks.15.norm1",
+            "vision_tower.encoder.blocks.15.wo",
+            "vision_tower.encoder.blocks.15.wqkv",
+            "vision_tower.encoder.blocks.16.mlp.fc0",
+            "vision_tower.encoder.blocks.16.mlp.fc1",
+            "vision_tower.encoder.blocks.16.norm0",
+            "vision_tower.encoder.blocks.16.norm1",
+            "vision_tower.encoder.blocks.16.wo",
+            "vision_tower.encoder.blocks.16.wqkv",
+            "vision_tower.encoder.blocks.17.mlp.fc0",
+            "vision_tower.encoder.blocks.17.mlp.fc1",
+            "vision_tower.encoder.blocks.17.norm0",
+            "vision_tower.encoder.blocks.17.norm1",
+            "vision_tower.encoder.blocks.17.wo",
+            "vision_tower.encoder.blocks.17.wqkv",
+            "vision_tower.encoder.blocks.18.mlp.fc0",
+            "vision_tower.encoder.blocks.18.mlp.fc1",
+            "vision_tower.encoder.blocks.18.norm0",
+            "vision_tower.encoder.blocks.18.norm1",
+            "vision_tower.encoder.blocks.18.wo",
+            "vision_tower.encoder.blocks.18.wqkv",
+            "vision_tower.encoder.blocks.19.mlp.fc0",
+            "vision_tower.encoder.blocks.19.mlp.fc1",
+            "vision_tower.encoder.blocks.19.norm0",
+            "vision_tower.encoder.blocks.19.norm1",
+            "vision_tower.encoder.blocks.19.wo",
+            "vision_tower.encoder.blocks.19.wqkv",
+            "vision_tower.encoder.blocks.2.mlp.fc0",
+            "vision_tower.encoder.blocks.2.mlp.fc1",
+            "vision_tower.encoder.blocks.2.norm0",
+            "vision_tower.encoder.blocks.2.norm1",
+            "vision_tower.encoder.blocks.2.wo",
+            "vision_tower.encoder.blocks.2.wqkv",
+            "vision_tower.encoder.blocks.20.mlp.fc0",
+            "vision_tower.encoder.blocks.20.mlp.fc1",
+            "vision_tower.encoder.blocks.20.norm0",
+            "vision_tower.encoder.blocks.20.norm1",
+            "vision_tower.encoder.blocks.20.wo",
+            "vision_tower.encoder.blocks.20.wqkv",
+            "vision_tower.encoder.blocks.21.mlp.fc0",
+            "vision_tower.encoder.blocks.21.mlp.fc1",
+            "vision_tower.encoder.blocks.21.norm0",
+            "vision_tower.encoder.blocks.21.norm1",
+            "vision_tower.encoder.blocks.21.wo",
+            "vision_tower.encoder.blocks.21.wqkv",
+            "vision_tower.encoder.blocks.22.mlp.fc0",
+            "vision_tower.encoder.blocks.22.mlp.fc1",
+            "vision_tower.encoder.blocks.22.norm0",
+            "vision_tower.encoder.blocks.22.norm1",
+            "vision_tower.encoder.blocks.22.wo",
+            "vision_tower.encoder.blocks.22.wqkv",
+            "vision_tower.encoder.blocks.23.mlp.fc0",
+            "vision_tower.encoder.blocks.23.mlp.fc1",
+            "vision_tower.encoder.blocks.23.norm0",
+            "vision_tower.encoder.blocks.23.norm1",
+            "vision_tower.encoder.blocks.23.wo",
+            "vision_tower.encoder.blocks.23.wqkv",
+            "vision_tower.encoder.blocks.24.mlp.fc0",
+            "vision_tower.encoder.blocks.24.mlp.fc1",
+            "vision_tower.encoder.blocks.24.norm0",
+            "vision_tower.encoder.blocks.24.norm1",
+            "vision_tower.encoder.blocks.24.wo",
+            "vision_tower.encoder.blocks.24.wqkv",
+            "vision_tower.encoder.blocks.25.mlp.fc0",
+            "vision_tower.encoder.blocks.25.mlp.fc1",
+            "vision_tower.encoder.blocks.25.norm0",
+            "vision_tower.encoder.blocks.25.norm1",
+            "vision_tower.encoder.blocks.25.wo",
+            "vision_tower.encoder.blocks.25.wqkv",
+            "vision_tower.encoder.blocks.26.mlp.fc0",
+            "vision_tower.encoder.blocks.26.mlp.fc1",
+            "vision_tower.encoder.blocks.26.norm0",
+            "vision_tower.encoder.blocks.26.norm1",
+            "vision_tower.encoder.blocks.26.wo",
+            "vision_tower.encoder.blocks.26.wqkv",
+            "vision_tower.encoder.blocks.3.mlp.fc0",
+            "vision_tower.encoder.blocks.3.mlp.fc1",
+            "vision_tower.encoder.blocks.3.norm0",
+            "vision_tower.encoder.blocks.3.norm1",
+            "vision_tower.encoder.blocks.3.wo",
+            "vision_tower.encoder.blocks.3.wqkv",
+            "vision_tower.encoder.blocks.4.mlp.fc0",
+            "vision_tower.encoder.blocks.4.mlp.fc1",
+            "vision_tower.encoder.blocks.4.norm0",
+            "vision_tower.encoder.blocks.4.norm1",
+            "vision_tower.encoder.blocks.4.wo",
+            "vision_tower.encoder.blocks.4.wqkv",
+            "vision_tower.encoder.blocks.5.mlp.fc0",
+            "vision_tower.encoder.blocks.5.mlp.fc1",
+            "vision_tower.encoder.blocks.5.norm0",
+            "vision_tower.encoder.blocks.5.norm1",
+            "vision_tower.encoder.blocks.5.wo",
+            "vision_tower.encoder.blocks.5.wqkv",
+            "vision_tower.encoder.blocks.6.mlp.fc0",
+            "vision_tower.encoder.blocks.6.mlp.fc1",
+            "vision_tower.encoder.blocks.6.norm0",
+            "vision_tower.encoder.blocks.6.norm1",
+            "vision_tower.encoder.blocks.6.wo",
+            "vision_tower.encoder.blocks.6.wqkv",
+            "vision_tower.encoder.blocks.7.mlp.fc0",
+            "vision_tower.encoder.blocks.7.mlp.fc1",
+            "vision_tower.encoder.blocks.7.norm0",
+            "vision_tower.encoder.blocks.7.norm1",
+            "vision_tower.encoder.blocks.7.wo",
+            "vision_tower.encoder.blocks.7.wqkv",
+            "vision_tower.encoder.blocks.8.mlp.fc0",
+            "vision_tower.encoder.blocks.8.mlp.fc1",
+            "vision_tower.encoder.blocks.8.norm0",
+            "vision_tower.encoder.blocks.8.norm1",
+            "vision_tower.encoder.blocks.8.wo",
+            "vision_tower.encoder.blocks.8.wqkv",
+            "vision_tower.encoder.blocks.9.mlp.fc0",
+            "vision_tower.encoder.blocks.9.mlp.fc1",
+            "vision_tower.encoder.blocks.9.norm0",
+            "vision_tower.encoder.blocks.9.norm1",
+            "vision_tower.encoder.blocks.9.wo",
+            "vision_tower.encoder.blocks.9.wqkv"
         ],
         "algo_config": null,
         "softmax_quant_spec": null,
         "kv_cache_quant_config": {},
         "kv_cache_post_rope": false,
         "quant_mode": "eager_mode",
+        "version": "0.11.2+b560ff9e7f9",
         "export": {
             "kv_cache_group": [],
             "min_kv_scale": 0.0,
             "weight_merge_groups": null
         }
     }
+}

docs/deploy_guidance.md ADDED Viewed

	@@ -0,0 +1,82 @@

+# Kimi-K2.5 Deployment Guide
+> [!Note]
+> This guide only provides some examples of deployment commands for Kimi-K2.5, which may not be the optimal configuration. Since inference engines are still being updated frequenty,  please continue to follow the guidance from their homepage if you want to achieve better inference performance.
+> kimi_k2 reasoning parser and other related features have been merged into vLLM/sglang and will be available in the next release. For now, please use the nightly build Docker image.
+## vLLM Deployment
+This model is available in nightly vLLM wheel:
+```
+uv pip install -U vllm \
+    --torch-backend=auto \
+    --extra-index-url https://wheels.vllm.ai/nightly
+```
+Here is the example to serve this model on a H200 single node with TP8 via vLLM:
+```bash
+vllm serve $MODEL_PATH -tp 8 --mm-encoder-tp-mode data --trust-remote-code --tool-call-parser kimi_k2 --reasoning-parser kimi_k2
+```
+**Key notes**
+- `--tool-call-parser kimi_k2`: Required for enabling tool calling
+- `--reasoning-parser kimi_k2`: Kimi-K2.5 enables thinking mode by default. Make sure to pass this for correct reasoning processing.
+## SGLang Deployment
+This model is available in SGLang latest main:
+```
+pip install "sglang @ git+https://github.com/sgl-project/sglang.git#subdirectory=python"
+pip install nvidia-cudnn-cu12==9.16.0.29
+```
+Similarly, here is the example for it to run with TP8 on H200 in a single node via SGLang:
+``` bash
+sglang serve --model-path $MODEL_PATH --tp 8 --trust-remote-code --tool-call-parser kimi_k2 --reasoning-parser kimi_k2
+```
+**Key parameter notes:**
+- `--tool-call-parser kimi_k2`: Required when enabling tool usage.
+- `--reasoning-parser kimi_k2`: Required for correctly processing reasoning content.
+## KTransformers Deployment
+### KTransformers+SGLang Inference Deployment
+Launch with KTransformers + SGLang for CPU+GPU heterogeneous inference:
+```
+python -m sglang.launch_server \
+  --model path/to/Kimi-K2.5/ \
+  --kt-amx-weight-path path/to/Kimi-K2.5/ \
+  --kt-cpuinfer 64 \
+  --kt-threadpool-count 2 \
+  --kt-num-gpu-experts 180 \
+  --kt-amx-method AMXINT4 \
+  --trust-remote-code \
+  --mem-fraction-static 0.98 \
+  --chunked-prefill-size 16384 \
+  --max-running-requests 48 \
+  --max-total-tokens 50000 \
+  --tensor-parallel-size 8 \
+  --enable-p2p-check \
+  --disable-shared-experts-fusion
+```
+Achieves 640.12 tokens/s Prefill and 24.51 tokens/s Decode (48-way concurrency) on 8× NVIDIA L20 + 2× Intel 6454S.
+More details: https://github.com/kvcache-ai/ktransformers/blob/main/doc/en/Kimi-K2.5.md .
+### KTransformers+LLaMA-Factory Fine-tuning Deployment
+You can use below command to run LoRA SFT with KT+llamafactory.
+```
+# For LoRA SFT
+USE_KT=1 llamafactory-cli train examples/train_lora/kimik2_lora_sft_kt.yaml
+# For Chat with model after LoRA SFT
+llamafactory-cli chat examples/inference/kimik2_lora_sft_kt.yaml
+# For API with model after LoRA SFT
+llamafactory-cli api examples/inference/kimik2_lora_sft_kt.yaml
+```
+This achieves end-to-end LoRA SFT Throughput: 44.55 token/s on 2× NVIDIA 4090 + Intel 8488C with 1.97T RAM and 200G swap memory.
+More details refer to https://github.com/kvcache-ai/ktransformers/blob/main/doc/en/SFT_Installation_Guide_KimiK2.5.md .

figures/demo_video.mp4 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:09b4d925aa0a7c712feef50765355f0625d8f6d46ea302fd98db9609e9070047
+size 270100

figures/kimi-logo.png ADDED Viewed

model-00001-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18daf53a15070b9c70d8bb63420dbd39764af9118af67982eeb60749f5453233
-size 995001888

 version https://git-lfs.github.com/spec/v1
+oid sha256:14c37abfedf2540344d9c088f8394358ac06c6409809e7ccea10e6a792d25124
+size 412845960

model-00002-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b80fdcfe1617d02fd492347cd8d21f2722087720264f02a344d0d923d0914f1
-size 9280387888

 version https://git-lfs.github.com/spec/v1
+oid sha256:792a1c34d7039f97a22bbe331210186a1efe648b217394033cd788c09f547c25
+size 9215704248

model-00003-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d9e99bdea44c88c3fc99b74167f9072c41c84a33e1b42d9e3771aa390c97eeb
-size 9280387888

 version https://git-lfs.github.com/spec/v1
+oid sha256:fda96a9661fdda6853f2bc5514978d21b8176e9ac423f6da6dde4e5ab39d3e17
+size 9215704248

model-00004-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:485d3d217728d45507a2fdfde8f9600f3bc06d418ed55e4f7443ac1c2304f256
-size 9280387888

 version https://git-lfs.github.com/spec/v1
+oid sha256:1d7fdbd62d7e6e80c01957217c233c397a6e7311646d9083a8fa715331c08587
+size 9215704248

model-00005-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a91f6c484c960703a9a0f9366db10ae6fc28fb1c1de84f5c5fd910d1a984a6b
-size 9280387888

 version https://git-lfs.github.com/spec/v1
+oid sha256:0faf42d63e96cc159d1aeea33b704f5e9377e56c87db6f102bb88d2ec923f1d7
+size 9215704248

model-00006-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03bf67c02fe04d31ce317041ba9c3ae2d2d6804c2da7180a0890335979ed92b3
-size 9280387888

 version https://git-lfs.github.com/spec/v1
+oid sha256:10c9da3f02f978a504c12d12b9bd5d9b67264bd9b8e55eed3a6f691fff589f7e
+size 9215704248

model-00007-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d376e7fe9d75b924986501db22b2e402a85f33031f271bf0d49edd32b28093de
-size 9280387888

 version https://git-lfs.github.com/spec/v1
+oid sha256:9a65675206a855250093b68c9fcf5423dac4847b874df67d9cce8e98305402f1
+size 9215704248

model-00008-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae5dd2a875a0ddc3a6de77f14adb608adb553213899a667f74594a08540307e3
-size 9280387888

 version https://git-lfs.github.com/spec/v1
+oid sha256:0045cc5f47eca2266d4e6610226a69bfd2175a3dfc4334250a0acd9899f4eb43
+size 9215704248

model-00009-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2a1b0c0d06cbdc03715c65c05f64f9ecf1705d8c2ec7f4a42b064c513a00d72
-size 9280387888

 version https://git-lfs.github.com/spec/v1
+oid sha256:14115c4305225f6c65f74a8bec71efd26fb7326a8ea1058f675f8530596b4186
+size 9215704248

model-00010-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff40390d24131d0d9c210bf03b5bb48d42d5105887ea8f20348573a313db9897
-size 9280387888

 version https://git-lfs.github.com/spec/v1
+oid sha256:f424523790a658bbb7a4ec62bcbd5310add58b755ece211bb0c0dd82a15e745d
+size 9215704248

model-00011-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d28d28bbb697f45dde07299aa881b35239704e5f91cdb77609f468934a3ef37
-size 9280390208

 version https://git-lfs.github.com/spec/v1
+oid sha256:15f8b1b9457361aa7f2a9e34db370f8f287c233b15fa5e428602e35bb8f5db2c
+size 9215706568

model-00012-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efe3b96284fac1b594944e9801726d84f71d7247b6a195c77ec8d98f1e582376
-size 9280390208

 version https://git-lfs.github.com/spec/v1
+oid sha256:226a876a929af9c38ca586f7661045552d86aff02d8a43880f0ccc78c274c938
+size 9215706568

model-00013-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb29f46107bc4221fc3a16d76f61e348b9f96f5054ac2a1736f7a5be65800601
-size 9280390208

 version https://git-lfs.github.com/spec/v1
+oid sha256:ccd7616d80bc16837103e64d7fd2d020393001e5e59a43f416822c14afdef65c
+size 9215706568

model-00014-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2408502c83b4498998cff1fe6c5c5e940fbdead1652d9dd81459df0c89eeea1
-size 9280390208

 version https://git-lfs.github.com/spec/v1
+oid sha256:2dba0172ab2774268198058cd689a66d39e21fbd149730d315f0aef891119672
+size 9215706568

model-00015-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22d9760a5997e71fedb17919636d1637992b05f90bcf6ba9872352bc328f9e93
-size 9280390208

 version https://git-lfs.github.com/spec/v1
+oid sha256:93346f577c4a9d44016a2829372c98c3b7f2c3567423202ac0550f51dde116b7
+size 9215706568

model-00016-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f6065fc376cd1750db9ea6ec0e86f2b43d22605a59c8c19dabb465da9d6598b
-size 9280390208

 version https://git-lfs.github.com/spec/v1
+oid sha256:1ff3a6fcf528980439f8b2c24b74d8ed5abe3790db678132f46d9043319030bb
+size 9215706568

model-00017-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5adf83a3c83d6ae280603a4d17a83e331e927f667208dfa72872ff0878f158f0
-size 9280390208

 version https://git-lfs.github.com/spec/v1
+oid sha256:77d4caa81cc735aed439a0c294413ba33fe78e1f7a5fc0bd81ecebd6261de255
+size 9215706568

model-00018-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bbd89e36450acaddf6baaeddf38b7cc71155077fbe5159e0c190de62eb8fcbd
-size 9280390208

 version https://git-lfs.github.com/spec/v1
+oid sha256:6a84f144d2b12e81f3f0bfb4f950b6dbcd5c987eea8f2fce4d775cff04450408
+size 9215706568

model-00019-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5058f1819d4e323a44d86e45d761d6bf7991895880b2d84cfe073d5ec2dda008
-size 9280390208

 version https://git-lfs.github.com/spec/v1
+oid sha256:12095b71eccd3826b28ed63a45865697311291c5b4bed53b8ae8bd0756f1e803
+size 9215706568

model-00020-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1477c77ea661bf6ac315eb69f557e1c7a24fff9e889774897755f761fa5cc74e
-size 9280390208

 version https://git-lfs.github.com/spec/v1
+oid sha256:2d07e2ccfa9feabd932b67ef4c8d6a8c8379c9787b499dccba1ad5a5e91191ca
+size 9215706568

model-00021-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:812a9a13dd1ef9b772baeaad8427cbd5431840c07fbc07551fb635dc679d6e6c
-size 9280390208

 version https://git-lfs.github.com/spec/v1
+oid sha256:9a12dbcc606047811678759674f081f7bf5560a4e6098e1167c81088c4044635
+size 9215706568

model-00022-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74b3748f8a0e7350e243da84debc4da7e9e8bb00e6211f052be6c5c7cee6234f
-size 9280390208

 version https://git-lfs.github.com/spec/v1
+oid sha256:51d6bf38338af0d117ce67e499b1b7eac35be599e1718484b71cb3a9feadfc5f
+size 9215706568

model-00023-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51f865ab4390fb736c1c064f63bd35a6ad1ead04567ace27bccb178f6d8dde94
-size 9280390208

 version https://git-lfs.github.com/spec/v1
+oid sha256:39fb888657d4005b5abc8eb13d2edfea0d2c18dbcc3b56374b198e0894cbf94e
+size 9215706568

model-00024-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07af75e2f4a76d0be4484dcdf466507c0f2b23ab599294ea5e8fe3e30de8436c
-size 9280390208

 version https://git-lfs.github.com/spec/v1
+oid sha256:d685dbe4e1676b1ce53baf95adc2e62870a74628526baa05281cea48306610fe
+size 9215706568

model-00025-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dee177ef397da45da7f81fd42aee2058d9e14ce00d0df7a5f19caef6230e419
-size 9280390208

 version https://git-lfs.github.com/spec/v1
+oid sha256:f147528633e61d1e97a0604df23688838d071bf86d05dbb5dcdbb995ac349a88
+size 9215706568

model-00026-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6410f9b5ae0fa36c28dc70a4d86f9da0ba0628bf5bcc695afa6181279a478890
-size 9280390208

 version https://git-lfs.github.com/spec/v1
+oid sha256:3404d1c7e76a17486454749e46eca43aa8d6a78a7500507e62cef1db5539ebc5
+size 9215706568

model-00027-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10fbd4f42708d8e40217b3d805192237d258b13c14e8a10f7b303e20390a5656
-size 9280390208

 version https://git-lfs.github.com/spec/v1
+oid sha256:775e12da35274b8183a976c1e486ba9c183a9fb1a758e5474fc41d4d5de4ecce
+size 9215706568

model-00028-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:406fa91d7b312c028687e061f76e5aefc5ce642a48f039838b11f0544acee727
-size 9280390208

 version https://git-lfs.github.com/spec/v1
+oid sha256:c42babe21f267986aae253cc57533ba8030b92c91d7bfa0cf5f8d57b28ec0403
+size 9215706568

model-00029-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef406584f8afbd1b6d28fbe5a96a852375c6e3506296193face05dd3cdd1e6e8
-size 9280390208

 version https://git-lfs.github.com/spec/v1
+oid sha256:55ca5f77b82588917ba10755953f438c6904da4796dfbda6ee2e75df99990b88
+size 9215706568

model-00030-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f593e541d77102b6948cf7ad8c1aa7894587d06ec8607922a1821dbf9e1ddb1
-size 9280390208

 version https://git-lfs.github.com/spec/v1
+oid sha256:7107c97607726f7b2be725e76cf8bc4499684f6ae99e1c6077f4752bf6b9608d
+size 9215706568

model-00031-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0a898fc052c039ee66416c3a03a86ad4a242b6cd10601386be13c6524bce1d4
-size 9280390208

 version https://git-lfs.github.com/spec/v1
+oid sha256:f2cb6862d16b9f9989528a0521ef008ed2abb4d2ff519d126bff74c2086d6596
+size 9215706568

model-00032-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f5078fd742de320f492d9c9f7c380844a33660b8f8f0205eeaf374957e7ade3
-size 9280390208

 version https://git-lfs.github.com/spec/v1
+oid sha256:c7e9071b8f60c1ef742cb61b3cfe6bfc4d753c6a1ea3dc69287a556e049fb968
+size 9215706568

model-00033-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:099e832cfb44be1400e3cb6c6da7337e71ded14662993782215c23d42b80dcb7
-size 9280390208

 version https://git-lfs.github.com/spec/v1
+oid sha256:e94bafff4fd281a993de205b542ce10110e93850e6c65c61d03be6c364a222a2
+size 9215706568

model-00034-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c418ab2f416a664dc4624e74e498bd8bf131ec95a106f3c514699daba6c74dc
-size 9280390208

 version https://git-lfs.github.com/spec/v1
+oid sha256:9d17e014b26c65a9154a45957111a08fed38000084b8930a9a28c6b0a7ff0c83
+size 9215706568

model-00035-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc2e3664fa3e816abf3d38743e436aac089bbd22d73b5c5d26837c4d0c112aa0
-size 9280390208

 version https://git-lfs.github.com/spec/v1
+oid sha256:229857de9029e67ee27dbe60e2f248ec46c105fa08bf76f80e60de6d6411c8f5
+size 9215706568

model-00036-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b19c8b026f97ff1d10d6cf71a4de178537f5e71dde682ab3beb3cd12a7334d7e
-size 9280390208

 version https://git-lfs.github.com/spec/v1
+oid sha256:95b0a3e5ae595ea2550c99042795130493e3b7d5421cb2ecf6af97c7a55c4f4e
+size 9215706568

model-00037-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:775702ce0a1e5f015f2089ec556f7bf962e1a147eb99b4cd71c564a98bc4b6d4
-size 9280390208

 version https://git-lfs.github.com/spec/v1
+oid sha256:f2611ef97858d1d6b09cc6e429839e727d3d15d967abe3da8bfad655079fedb5
+size 9215706568

model-00038-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ea29d9ccd21191a1a8c13d9139b498334099ad342ab0703c692db989e54dd2b
-size 9280390208

 version https://git-lfs.github.com/spec/v1
+oid sha256:3bf1afe774559fa6718b2a4f1c485f3460ac74ca63ead287c473c5f7053e0ccc
+size 9215706568

model-00039-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd091f20926b11a58428c6cc9c67bb4b842a2182eb5d8173af087eac86d99aad
-size 9280390208

 version https://git-lfs.github.com/spec/v1
+oid sha256:90c1709b2436b892bf319128a3880f9ad660381c0254136928698e94d4cc7454
+size 9215706568

model-00040-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25b11a04fbdedecd19ec047e597ac82be1172807f93f03f137c23bc0eac7a76f
-size 9280390208

 version https://git-lfs.github.com/spec/v1
+oid sha256:a9ac158f4752b092b37ce4cf51d7a11640caa24faa72e4e96028b6da1400d88e
+size 9215706568

model-00041-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ae5719fe28bac0dd17677e67861bd632930877ce0d8a0b15b11a624b0aba69f
-size 9280390208

 version https://git-lfs.github.com/spec/v1
+oid sha256:7dfcac8e04b9e71fdbc875dbd8b7d633df49b1ba8fc096adf040fce451a51970
+size 9215706568

model-00042-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f7bf4f3aea3bf79d9c1744b16134974db972a4dd7e0afe2b48ee48aedeb4e4a
-size 9280390208

 version https://git-lfs.github.com/spec/v1
+oid sha256:d688b5dd61818c24d75c8f28ba28516ec7247eb850fad0db107d4dc9153e3a7d
+size 9215706568

model-00043-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de4d7f327b6926f1b6640023ed631ad5484ec76bf58b3d368f6a73e2b9cbb1e9
-size 9280390208

 version https://git-lfs.github.com/spec/v1
+oid sha256:c0b768d9a9cef432800fbb488542c3e27dfce7795ebe6a0eb058dfc2d0919525
+size 9215706568

model-00044-of-000064.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b8137f44508adaf77d60413549baab93218515b3bc7ba4036cd92fee45a89c7
-size 9280390208

 version https://git-lfs.github.com/spec/v1
+oid sha256:2181b8e7841f13727fe71d23a38ecd790be3a838592a96293de5e784bb6225e9
+size 9215706568