Update README.md

README.md

@@ -11,4 +11,76 @@ This repository contains the reinforcement learning (RL) model based on **TexOCR
 
 - **Base Model**: TexOCR_OCR  
 - **Training Method**: GRPO (Reinforcement Learning)  
-- **Task**: Compilable Page-to-LaTeX Reconstruction  
+- **Task**: Compilable Page-to-LaTeX Reconstruction
+
+## Inference
+
+You can use the following code to run inference with the fine-tuned TexOCR model.
+
+```python
+import torch
+from transformers import Qwen3VLForConditionalGeneration, AutoProcessor
+
+# Load the fine-tuned model
+model = Qwen3VLForConditionalGeneration.from_pretrained(
+    "chengyewang/TexOCR-RL",
+    dtype="auto",
+    device_map="auto"
+)
+
+
+processor = AutoProcessor.from_pretrained("Qwen/Qwen3-VL-2B-Instruct")
+
+# Input document page image
+image_path = "path/to/your/document_page.png"
+
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "image",
+                "image": image_path,
+            },
+            {
+                "type": "text",
+                "text": (
+                    "Convert this document page image into compilable LaTeX code. "
+                ),
+            },
+        ],
+    }
+]
+
+# Preparation for inference
+inputs = processor.apply_chat_template(
+    messages,
+    tokenize=True,
+    add_generation_prompt=True,
+    return_dict=True,
+    return_tensors="pt"
+)
+inputs = inputs.to(model.device)
+
+# Inference: generate LaTeX output
+generated_ids = model.generate(
+    **inputs,
+    max_new_tokens=2048,
+    do_sample=False
+)
+
+# Remove input tokens from the generated sequence
+generated_ids_trimmed = [
+    out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
+]
+
+# Decode the generated LaTeX
+latex_output = processor.batch_decode(
+    generated_ids_trimmed,
+    skip_special_tokens=True,
+    clean_up_tokenization_spaces=False
+)
+
+print(latex_output[0])
+```
+