app.py

import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
 # Load DeepSeek model
model_id = "deepseek-ai/deepseek-llm-7b-chat"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")


def generate_response(prompt):
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
    outputs = model.generate(
        **inputs,
        do_sample=True,
        temperature=1.0,
        top_p=0.9
    )

    return tokenizer.decode(outputs[0], skip_special_tokens=True)
    # return "Hello " + name + "!!"

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