README.md

---
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)

```