app.py

    import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load the model and tokenizer
model_name = 'FridayMaster/fine_tune_embedding'
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)  # Use the appropriate class

# Define a function to generate responses
def generate_response(prompt):
    # Tokenize the input prompt
    inputs = tokenizer(prompt, return_tensors="pt", padding=True, truncation=True, max_length=512)
    with torch.no_grad():
        # Generate a response using the model
        outputs = model.generate(inputs['input_ids'], max_length=150, num_return_sequences=1)
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return response

# Create a Gradio interface
iface = gr.Interface(
    fn=generate_response,
    inputs=gr.Textbox(label="Enter your message", placeholder="Type something here..."),
    outputs=gr.Textbox(label="Response"),
    title="Chatbot Interface",
    description="Interact with the fine-tuned chatbot model."
)

# Launch the Gradio app
if __name__ == "__main__":
    iface.launch()