app.py

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

# Load model
model_id = "htigenai/finetune_test"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.float16,
    device_map="auto"
)

def generate_text(prompt):
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
    outputs = model.generate(
        **inputs,
        max_new_tokens=100,
        temperature=0.7,
        top_p=0.95,
        do_sample=True
    )
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

# Create the interface
iface = gr.Interface(
    fn=generate_text,
    inputs=gr.Textbox(lines=2, placeholder="Enter your prompt here..."),
    outputs=gr.Textbox(),
    title="Text Generation",
    description="Generate text using the fine-tuned model"
)

iface.launch()