123

README.md

@@ -4,7 +4,7 @@ license: apache-2.0
 # Diagram Formalizer
 Model Structure: 
 
-<img src="sample/diagram_formalizer.png" alt="Alt text" width="80%" height="auto">
+<img src="sample/diagram_formalizer.png" alt="Alt text" width="50%" height="auto">
 
 - **Diagram Encoder**: [siglip-so400m-patch14-384](https://huggingface.co/google/siglip-so400m-patch14-384)
 
@@ -47,7 +47,7 @@ tokenizer = AutoTokenizer.from_pretrained(
 # text prompt
 img_path = 'sample/4927.png'
 prompt = 'Based on the image, first describe what you see in the figure, then predict the construction_cdl and image_cdl and calibrate it.'
-text = f"<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n<|im_start|>user\n<image>\n{prompt}<|im_end|>\n<|im_start|>assistant\n"
+text = f'<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n<|im_start|>user\n<image>\n{prompt}<|im_end|>\n<|im_start|>assistant\n'
 
 def tokenizer_image_token(prompt, tokenizer, image_token_index, return_tensors=None):
     prompt_chunks = [tokenizer(chunk).input_ids for chunk in prompt.split('<image>')]