MLAdaptiveIntelligence
/

LLaVAction-0.5B

Video-Text-to-Text

text-generation

text-generation-inference

Model card Files Files and versions

shaokaiye commited on Mar 24, 2025

Commit

f7e786c

·

verified ·

1 Parent(s): e3b2b5e

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -78,7 +78,7 @@ model.eval()
 video_path = "XXXX"
 max_frames_num = 64
 video,frame_time,video_time = load_video(video_path, max_frames_num, 1, force_sample=True)
-video = image_processor.preprocess(video, return_tensors="pt")["pixel_values"].cuda().half()
 video = [video]
 conv_template = "qwen_1_5"  # Make sure you use correct chat template for different models
 time_instruction = f"The video lasts for {video_time:.2f} seconds, and {len(video[0])} frames are uniformly sampled from it. "

 video_path = "XXXX"
 max_frames_num = 64
 video,frame_time,video_time = load_video(video_path, max_frames_num, 1, force_sample=True)
+video = image_processor.preprocess(video, return_tensors="pt")["pixel_values"].cuda().to(torch.bfloat16)
 video = [video]
 conv_template = "qwen_1_5"  # Make sure you use correct chat template for different models
 time_instruction = f"The video lasts for {video_time:.2f} seconds, and {len(video[0])} frames are uniformly sampled from it. "