app.py

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

model_id = "linjc16/Panacea-7B-Chat"

# Load tokenizer and model
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.float16,
    device_map="auto",
    trust_remote_code=True
)
streamer = TextStreamer(tokenizer)

# Chat function
def chat(message, history=[]):
    prompt = message
    input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(model.device)
    with torch.no_grad():
        output = model.generate(
            input_ids,
            max_new_tokens=512,
            do_sample=True,
            temperature=0.7,
            top_p=0.9
        )
    reply = tokenizer.decode(output[0], skip_special_tokens=True)
    return reply

# Gradio Interface
iface = gr.Interface(
    fn=chat,
    inputs=gr.Textbox(lines=2, placeholder="Type your message here..."),
    outputs="text",
    title="Panacea-7B-Chat"
)

iface.launch()