update preprocessore for supporting vllm

config.json

@@ -25,7 +25,7 @@
       "num_mel_bins": 128,
       "output_dim": 2048,
       "scale_embedding": false,
-      "torch_dtype": "float32"
+      "torch_dtype": "bfloat16"
     },
     "audio_end_token_id": 151648,
     "audio_start_token_id": 151647,
@@ -103,12 +103,12 @@
       },
       "rope_theta": 1000000.0,
       "sliding_window": null,
-      "torch_dtype": "float32",
+      "torch_dtype": "bfloat16",
       "use_cache": true,
       "use_sliding_window": false,
       "vocab_size": 151936
     },
-    "torch_dtype": "float32",
+    "torch_dtype": "bfloat16",
     "transformers_version": "4.53.2",
     "user_token_id": 872,
     "video_token_index": 151656,
@@ -136,7 +136,7 @@
       "spatial_patch_size": 14,
       "temporal_patch_size": 2,
       "tokens_per_second": 25,
-      "torch_dtype": "float32",
+      "torch_dtype": "bfloat16",
       "window_size": 112
     },
     "vision_end_token_id": 151653,

preprocessor_config.json

@@ -15,7 +15,7 @@
     0.26130258,
     0.27577711
   ],
-  "max_pixels": 12845056,
+  "max_pixels": 802816,
   "merge_size": 2,
   "min_pixels": 3136,
   "n_fft": 400,

tokenizer_config.json

@@ -215,6 +215,7 @@
   "processor_class": "ColQwen2_5OmniProcessor",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
+  "chat_template": "{% set audio_count = namespace(value=0) %}{% 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_bos|><|IMAGE|><|vision_eos|>{% elif content['type'] == 'audio' or 'audio' in content or 'audio_url' in content %}{% set audio_count.value = audio_count.value + 1 %}{% if add_audio_id %}Audio {{ audio_count.value }}: {% endif %}<|audio_bos|><|AUDIO|><|audio_eos|>{% 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_bos|><|VIDEO|><|vision_eos|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
   "unk_token": null,
   "video_token": "<|VIDEO|>",
   "vision_bos_token": "<|vision_bos|>",