app.py

import gradio as gr
import os
from huggingface_hub import InferenceClient



HF_TOKEN = os.getenv("HUGGINGFACEHUB_API_TOKEN")
client = InferenceClient(model="HuggingFaceH4/zephyr-7b-beta", token=HF_TOKEN)


def respond(message):
    for response in client.chat_completion(messages=[{"role": "user", "content": message}]):
        yield response["choices"][0]["message"]["content"]



def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    messages = [{"role": "system", "content": system_message}]

    for val in history:
        if val[0]:
            messages.append({"role": "user", "content": val[0]})
        if val[1]:
            messages.append({"role": "assistant", "content": val[1]})

    messages.append({"role": "user", "content": message})

    response = ""

    for message in client.chat_completion(
        messages,
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        token = message.choices[0].delta.content

        response += token
        yield response


"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
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()





import os
from transformers import AutoModelForCasualLM, AutoTokenizer
from peft import PeftModel
import torch

if not api_token:
    api_token = os.getenv("HUGGINGFACEHUB_API_TOKEN")
    raise ValueError("❌ ERROR: Hugging Face API token is not set. Please set it as an environment variable.")

# Define model names
base_model_name = "mistralai/Mistral-7B-Instruct-v0.3"
peft_model_name = "prempranavreddy/MP1"

# Load base model with authentication
base_model = AutoModelForCausalLM.from_pretrained(
    base_model_name, 
    torch_dtype=torch.float16, 
    device_map="auto",
    use_auth_token=api_token  # ✅ Correct
)


# Load fine-tuned model
model = PeftModel.from_pretrained(base_model, peft_model_name, token=api_token)

# Load tokenizer
tokenizer = AutoTokenizer.from_pretrained(base_model_name, token=api_token)