app.py

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

# Load the tokenizer and model from Hugging Face
model_name = "waterdrops0/mistral-nouns600"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype=torch.float16)

def generate_text(prompt, max_length=50, temperature=0.7):
    inputs = tokenizer.encode(prompt, return_tensors="pt").to(model.device)
    outputs = model.generate(
        inputs,
        max_length=max_length,
        temperature=temperature,
        do_sample=True,
        top_p=0.95,
        top_k=60
    )
    text = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return text

iface = gr.Interface(
    fn=generate_text,
    inputs=[
        gr.inputs.Textbox(lines=2, placeholder="Enter your prompt here..."),
        gr.inputs.Slider(10, 200, step=10, default=50, label="Max Length"),
        gr.inputs.Slider(0.1, 1.0, step=0.1, default=0.7, label="Temperature")
    ],
    outputs="text",
    title="Mistral 7B Nouns Model",
    description="Generate text using the fine-tuned Mistral 7B model."
)

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