app.py

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

model_id = "deepseek-ai/deepseek-coder-1.3b-base"  # change to your choice
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto"
)

pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)

def chat(prompt):
    result = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.2)
    return result[0]['generated_text']

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