tencent
/

HunyuanOCR

Image-Text-to-Text

text-generation

vision-language

Model card Files Files and versions

manaestras commited on 17 days ago

Commit

4be5a16

·

verified ·

1 Parent(s): e6bffef

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -116,7 +116,7 @@ from transformers import AutoProcessor
 model_path = "tencent/HunyuanOCR"
 llm = LLM(model=model_path)
 processor = AutoProcessor.from_pretrained(model_path)
-sampling_params = SamplingParams(temperature=1, max_tokens=16384)
 img_path = "/path/to/image.jpg"
 img = Image.open(img_path)

 model_path = "tencent/HunyuanOCR"
 llm = LLM(model=model_path)
 processor = AutoProcessor.from_pretrained(model_path)
+sampling_params = SamplingParams(temperature=0.0, max_tokens=16384)
 img_path = "/path/to/image.jpg"
 img = Image.open(img_path)