Update README.md

README.md

@@ -1,3 +1,60 @@
----
-license: mit
----
+---
+license: mit
+---
+## Usage
+
+### Chat format
+
+> **IMPORTANT**: This model is **sensitive** to the chat template used. Ensure you use the correct template:
+```
+<s>system
+[System message]</s>
+<s>user
+[Your question or message]</s> 
+<s>assistant
+[The model's response]</s>
+```
+
+### Example Usage with HuggingFace Transformers
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# Determine the device to use (GPU if available, otherwise CPU)
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+# Load the model and tokenizer, then move the model to the appropriate device
+model = AutoModelForCausalLM.from_pretrained("adi2606/MenstrualQA").to(device)
+tokenizer = AutoTokenizer.from_pretrained("adi2606/MenstrualQA")
+
+# Function to generate a response from the chatbot
+def generate_response(message: str, temperature: float = 0.4, repetition_penalty: float = 1.1) -> str:
+    # Apply the chat template and convert to PyTorch tensors
+    messages = [
+        {"role": "system", "content": "You are a helpful assistant."},
+        {"role": "user", "content": message}
+    ]
+    input_ids = tokenizer.apply_chat_template(
+        messages, add_generation_prompt=True, return_tensors="pt"
+    ).to(device)
+
+    # Generate the response
+    output = model.generate(
+        input_ids,
+        max_length=512,
+        temperature=temperature,
+        repetition_penalty=repetition_penalty,
+        do_sample=True
+    ) 
+
+    # Decode the generated output
+    generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
+    return generated_text
+
+# Example usage
+message = "how to stop pain during menstruation?"
+response = generate_response(message)
+print(response)
+
+```