Upload README.md with huggingface_hub

README.md

@@ -7,6 +7,7 @@ datasets:
 base_model:
 - Qwen/Qwen2.5-VL-7B-Instruct
 library_name: transformers
+pipeline_tag: image-text-to-text
 ---
 
 <img alt="olmOCR Logo" src="https://huggingface.co/datasets/allenai/blog-images/resolve/main/olmocr/olmocr.png" width="242px" style="margin-left:'auto' margin-right:'auto' display:'block'">
@@ -37,7 +38,7 @@ A simple way to infer using transformers is as follows:
 ```python
 import torch from transformers import AutoModelForImageTextToText, AutoProcessor 
 
-model_id = "allenai/olmOCR-7B-0725" 
+model_id = "allenai/olmOCR-7B-0825" 
 processor = AutoProcessor.from_pretrained(model_id)
 model = AutoModelForImageTextToText.from_pretrained(model_id, torch_dtype=torch.float16 ).to("cuda").eval()
 
@@ -68,7 +69,7 @@ messages = [
                 "type": "image",
                 "image": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/smolvlm_table.png",
             },
-            {"type": "text", "text": "OCR"},
+            {"type": "text", "text": PROMPT},
         ],
     }
 ]
@@ -78,7 +79,6 @@ text = processor.apply_chat_template(
 )
 inputs = processor.apply_chat_template(
     messages,
-    video_fps=1,
     add_generation_prompt=True,
     tokenize=True,
     return_dict=True,