app.py

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

model_id = "deepseek-ai/deepseek-coder-6.7b-instruct"

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

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

gr.Interface(fn=chat, inputs="text", outputs="text", title="DeepSeek Coder 6.7B Chatbot").launch()