Added usage instructions

README.md

@@ -50,6 +50,98 @@ metrics:
 
 ---
 
+## Usage
+### Using transformers
+```python
+from PIL import Image
+from transformers import AutoTokenizer, AutoProcessor, AutoModelForImageTextToText
+
+model_path = "krutrim-ai-labs/Chitrapathak-2"
+
+model = AutoModelForImageTextToText.from_pretrained(
+    model_path, 
+    torch_dtype="auto", 
+    device_map="auto", 
+    attn_implementation="flash_attention_2"
+)
+model.eval()
+
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+processor = AutoProcessor.from_pretrained(model_path)
+
+
+def perform_ocr(image_path, model, processor, max_new_tokens=4096):
+    image = Image.open(image_path)
+    messages = [
+        {"role": "system", "content": "You are a helpful assistant."},
+        {"role": "user", "content": [
+            {"type": "image", "image": f"file://{image_path}"},
+            {"type": "text", "text": "Perform OCR on this image and transcribe all visible text exactly as it appears."},
+        ]},
+    ]
+    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+    inputs = processor(text=[text], images=[image], padding=True, return_tensors="pt")
+    inputs = inputs.to(model.device)
+    
+    output_ids = model.generate(**inputs, max_new_tokens=max_new_tokens, do_sample=False)
+    generated_ids = [output_ids[len(input_ids):] for input_ids, output_ids in zip(inputs.input_ids, output_ids)]
+    
+    output_text = processor.batch_decode(generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=True)
+    return output_text[0]
+
+image_path = "/path/to/your/document.jpg"
+result = perform_ocr(image_path, model, processor, max_new_tokens=15000)
+print(result)
+```
+
+### Using vLLM
+1. Start the vLLM server.
+```bash
+vllm serve krutrim-ai-labs/Chitrapathak-2
+```
+2. Predict with the model
+```python
+from openai import OpenAI
+import base64
+
+client = OpenAI(api_key="123", base_url="http://localhost:8000/v1")
+
+model = "krutrim-ai-labs/Chitrapathak-2"
+
+def encode_image(image_path):
+    with open(image_path, "rb") as image_file:
+        return base64.b64encode(image_file.read()).decode("utf-8")
+
+def perform_ocr(img_base64):
+    response = client.chat.completions.create(
+        model=model,
+        messages=[
+            {
+                "role": "user",
+                "content": [
+                    {
+                        "type": "image_url",
+                        "image_url": {"url": f"data:image/png;base64,{img_base64}"},
+                    },
+                    {
+                        "type": "text",
+                        "text": "Perform OCR on this image and transcribe all visible text exactly as it appears.",
+                    },
+                ],
+            }
+        ],
+        temperature=0.0,
+        max_tokens=15000
+    )
+    return response.choices[0].message.content
+
+test_img_path = "/path/to/your/document.jpg"
+img_base64 = encode_image(test_img_path)
+print(perform_ocr(img_base64))
+```
+
+---
+
 ## Evaluation Results
 
 ### **Indic OCR Performance**
@@ -117,9 +209,9 @@ Note that the above latency values are calculated assuming the size of the input
 
 ### Observations
 
-- 🕒 **TTFT (Time-to-First-Token):** ~125 ms  
-- ⚙️ **Inter-token latency:** ~4 ms per token  
-- 🧮 **Language impact:** Latency varies with tokenization efficiency.  
+- **TTFT (Time-to-First-Token):** ~125 ms  
+- **Inter-token latency:** ~4 ms per token  
+- **Language impact:** Latency varies with tokenization efficiency.  
   - **English** and **Hindi** → Lower latency due to **compact token-to-word ratios**.  
   - **Telugu** and **Malayalam** → Higher latency due to **fragmented tokenization** (larger number of tokens per word).