app.py

import streamlit as st
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Initialize the text generation pipeline
@st.cache_resource
def load_model():
    model_name = "deepseek-ai/DeepSeek-R1"
    tokenizer = AutoTokenizer.from_pretrained(model_name)
    model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float32, trust_remote_code=True)
    return model, tokenizer

model, tokenizer = load_model()

def generate_response(prompt):
    inputs = tokenizer(prompt, return_tensors="pt")
    output = model.generate(**inputs, max_length=100)
    return tokenizer.decode(output[0], skip_special_tokens=True)

# Set the title of the app
st.title("Chat with DeepSeek-R1-Distill-Qwen-1.5B")

# Initialize session state to store chat history
if "messages" not in st.session_state:
    st.session_state.messages = []

# Display chat messages from history
for message in st.session_state.messages:
    with st.chat_message(message["role"]):
        st.markdown(message["content"])

# User input
if prompt := st.chat_input("You:"):
    # Display user message in chat message container
    st.chat_message("user").markdown(prompt)
    # Append user message to chat history
    st.session_state.messages.append({"role": "user", "content": prompt})

    # Generate response
    response = generate_response(prompt)

    # Display assistant response in chat message container
    st.chat_message("assistant").markdown(response)
    # Append assistant response to chat history
    st.session_state.messages.append({"role": "assistant", "content": response})