app.py

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

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

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.float16,
    device_map="auto",
    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)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

gr.Interface(
    fn=chat,
    inputs="text",
    outputs="text",
    title="DeepSeek Coder 1.3B",
    description="Free coding assistant running on Hugging Face CPU"
).launch()