OpenGVLab
/

VideoChat-Flash-Qwen2-7B_res224

Video-Text-to-Text

videochat_flash_qwen

feature-extraction

Model card Files Files and versions Community

lixinhao commited on 10 days ago

Commit

0018d81

·

verified ·

1 Parent(s): acc0a16

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -120,7 +120,7 @@ if mm_llm_compress:
     model.config.llm_compress_layer_list = [4, 18]
     model.config.llm_image_token_ratio_list = [1, 0.75, 0.25]
 else:
-    model.config.mm_llm_compress = True
 # evaluation setting
 max_num_frames = 512

     model.config.llm_compress_layer_list = [4, 18]
     model.config.llm_image_token_ratio_list = [1, 0.75, 0.25]
 else:
+    model.config.mm_llm_compress = False
 # evaluation setting
 max_num_frames = 512