Use lazy import for flash_attn

README.md

@@ -1,17 +1,7 @@
 ---
-pipeline_tag: image-text-to-text
+pipeline_tag: visual-question-answering
 datasets:
 - openbmb/RLAIF-V-Dataset
-library_name: transformers
-language:
-- multilingual
-tags:
-- minicpm-v
-- vision
-- ocr
-- multi-image
-- video
-- custom_code
 ---
 
 <h1>A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone</h1>
@@ -73,8 +63,7 @@ Note: For proprietary models, we calculate token density based on the image enco
 <summary>Click to view video results on Video-MME and Video-ChatGPT.</summary>
 <div align="center">
 
-<!-- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64abc4aa6cadc7aca585dddf/_T1mw5yhqNCqVdYRTQOGu.png) -->
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/64abc4aa6cadc7aca585dddf/jmrjoRr8SFLkrstjDmpaV.png)
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64abc4aa6cadc7aca585dddf/_T1mw5yhqNCqVdYRTQOGu.png)
 
 </div>
 
@@ -281,7 +270,7 @@ def encode_video(video_path):
     print('num frames:', len(frames))
     return frames
 
-video_path ="video_test.mp4"
+video_path="video_test.mp4"
 frames = encode_video(video_path)
 question = "Describe the video"
 msgs = [