Add files using upload-large-folder tool

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "Qwen/Qwen2.5-VL-7B-Instruct",
   "architectures": [
     "Qwen2_5_VLForConditionalGeneration"
   ],
@@ -51,7 +50,7 @@
       }
     },
     "format": "float-quantized",
-    "global_compression_ratio": 1.205861541169936,
+    "global_compression_ratio": null,
     "ignore": [
       "visual.blocks.0.attn.qkv",
       "visual.blocks.0.attn.proj",
@@ -235,16 +234,32 @@
   "sliding_window": 32768,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.49.0",
+  "transformers_version": "4.51.3",
   "use_cache": true,
   "use_sliding_window": false,
   "video_token_id": 151656,
   "vision_config": {
+    "depth": 32,
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "hidden_act": "silu",
     "hidden_size": 1280,
+    "in_channels": 3,
     "in_chans": 3,
+    "intermediate_size": 3420,
     "model_type": "qwen2_5_vl",
+    "num_heads": 16,
+    "out_hidden_size": 3584,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
     "spatial_patch_size": 14,
-    "tokens_per_second": 2
+    "temporal_patch_size": 2,
+    "tokens_per_second": 2,
+    "window_size": 112
   },
   "vision_end_token_id": 151653,
   "vision_start_token_id": 151652,

generation_config.json

@@ -7,8 +7,6 @@
   ],
   "pad_token_id": 151643,
   "repetition_penalty": 1.05,
-  "temperature": 0.1,
-  "top_k": 1,
-  "top_p": 0.001,
-  "transformers_version": "4.49.0"
+  "temperature": 1e-06,
+  "transformers_version": "4.51.3"
 }

preprocessor_config.json

@@ -1,19 +1,29 @@
 {
-  "min_pixels": 3136,
-  "max_pixels": 12845056,
-  "patch_size": 14,
-  "temporal_patch_size": 2,
-  "merge_size": 2,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
   "image_mean": [
     0.48145466,
     0.4578275,
     0.40821073
   ],
+  "image_processor_type": "Qwen2VLImageProcessor",
   "image_std": [
     0.26862954,
     0.26130258,
     0.27577711
   ],
-  "image_processor_type": "Qwen2VLImageProcessor",
-  "processor_class": "Qwen2_5_VLProcessor"
-}
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

recipe.yaml

@@ -1,6 +1,6 @@
-DEFAULT_stage:
-  DEFAULT_modifiers:
+default_stage:
+  default_modifiers:
     QuantizationModifier:
-      ignore: [lm_head, 're:visual.*']
+      ignore: ['re:.*lm_head', 're:visual.*']
       targets: [Linear]
       scheme: FP8_DYNAMIC

tokenizer_config.json

@@ -195,13 +195,14 @@
     "<|video_pad|>"
   ],
   "bos_token": null,
-  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",
   "extra_special_tokens": {},
   "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen2_5_VLProcessor",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null