app.py

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

# Load model and tokenizer from Hugging Face directly
model_name = "deepseek-ai/deepseek-7b-instruct"  
tokenizer = AutoTokenizer.from_pretrained(model_name)  
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")  

# Create a simple chat function  
def chat_function(prompt):  
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)  
    outputs = model.generate(**inputs, max_length=200)  
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)  
    return response  

# Build a simple Gradio interface  
iface = gr.Interface(fn=chat_function, inputs="text", outputs="text")  
iface.launch()