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

model = AutoModelForCausalLM.from_pretrained("deepseek-ai/deepseek-llm-7b-chat", device_map="auto", torch_dtype=torch.float16)
tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/deepseek-llm-7b-chat")

def chat(prompt):
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
    outputs = model.generate(**inputs, max_new_tokens=256, do_sample=True)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

gr.Interface(fn=chat, inputs="text", outputs="text").launch()