weizhiwang
/

Open-Qwen2VL

Image-Text-to-Text

Model card Files Files and versions

weizhiwang commited on Apr 3

Commit

c4db037

·

verified ·

1 Parent(s): 51c6cbd

Update README.md

Files changed (1) hide show

README.md +1 -2

README.md CHANGED Viewed

@@ -44,8 +44,7 @@ vlm.to(device, dtype=torch.bfloat16)
 image_url = "https://huggingface.co/adept/fuyu-8b/resolve/main/bus.png"
 # image = Image.open(requests.get(image_url, stream=True).raw).convert("RGB")
 image = [vlm.vision_backbone.image_transform(Image.open(requests.get(image_url, stream=True).raw).convert("RGB")).unsqueeze(0)]
-user_prompt = '<image>' + '
-' + "Describe the image."
 # Generate!
 generated_text = vlm.generate_batch(

 image_url = "https://huggingface.co/adept/fuyu-8b/resolve/main/bus.png"
 # image = Image.open(requests.get(image_url, stream=True).raw).convert("RGB")
 image = [vlm.vision_backbone.image_transform(Image.open(requests.get(image_url, stream=True).raw).convert("RGB")).unsqueeze(0)]
+user_prompt = '<image>\nDescribe the image."
 # Generate!
 generated_text = vlm.generate_batch(