Visual Question Answering
Transformers
Safetensors
llava
image-text-to-text
AIGC
LLaVA
Inference Endpoints
ponytail commited on
Commit
3d262b5
1 Parent(s): 8f56020

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -57,8 +57,8 @@ processor = AutoProcessor.from_pretrained(model_id,trust_remote_code=True)
57
  text = "Please describe this picture"
58
  prompt = "USER: <image>\n" + text + "\nASSISTANT:"
59
  image_file = "./test1.jpg"
60
- # raw_image = Image.open(image_file)
61
- raw_image = Image.open(requests.get(image_file, stream=True).raw)
62
  inputs = processor(images=raw_image, text=prompt, return_tensors='pt').to(cuda, torch.float16)
63
 
64
  output = model.generate(**inputs, max_new_tokens=400, do_sample=False)
@@ -66,7 +66,7 @@ predict = processor.decode(output[0][:], skip_special_tokens=True)
66
  print(predict)
67
  ```
68
 
69
- Our training code will be published publicly on github.[ddw2AIGROUP2CQUPT/Human-LLaVA-8B(github.com)]https://github.com/ddw2AIGROUP2CQUPT/Human-LLaVA-8B]
70
  ## Get the Dataset
71
  #### Dataset Example
72
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64259db7d3e6fdf87e4792d0/vRojQxm8IMybBV0X5CKbf.png)
 
57
  text = "Please describe this picture"
58
  prompt = "USER: <image>\n" + text + "\nASSISTANT:"
59
  image_file = "./test1.jpg"
60
+ raw_image = Image.open(image_file)
61
+ # raw_image = Image.open(requests.get(image_file, stream=True).raw)
62
  inputs = processor(images=raw_image, text=prompt, return_tensors='pt').to(cuda, torch.float16)
63
 
64
  output = model.generate(**inputs, max_new_tokens=400, do_sample=False)
 
66
  print(predict)
67
  ```
68
 
69
+ Our training code have been released publicly on github.[ddw2AIGROUP2CQUPT/Human-LLaVA-8B(github.com)]https://github.com/ddw2AIGROUP2CQUPT/Human-LLaVA-8B]
70
  ## Get the Dataset
71
  #### Dataset Example
72
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64259db7d3e6fdf87e4792d0/vRojQxm8IMybBV0X5CKbf.png)