app.py

import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load the tokenizer and model
model_name = "Aksh1t/mistral-7b-oig-unsloth-merged"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")

def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    # Construct the prompt
    prompt = system_message + "\n"
    for user_msg, assistant_msg in history:
        if user_msg:
            prompt += f"User: {user_msg}\n"
        if assistant_msg:
            prompt += f"Assistant: {assistant_msg}\n"
    prompt += f"User: {message}\nAssistant:"

    # Encode the prompt and generate a response
    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(
        inputs.input_ids,
        max_new_tokens=max_tokens,
        temperature=temperature,
        top_p=top_p,
        do_sample=True
    )

    # Decode the generated response
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)

    # Extract the assistant's reply
    assistant_reply = response.split("Assistant:")[-1].strip()
    yield assistant_reply

demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
        gr.Slider(
            minimum=0.1,
            maximum=1.0,
            value=0.95,
            step=0.05,
            label="Top-p (nucleus sampling)",
        ),
    ],
)

if __name__ == "__main__":
    demo.launch()