File size: 2,255 Bytes
47a7cf1
47a38f9
47a7cf1
 
 
47a38f9
47a7cf1
 
 
 
 
 
 
 
47a38f9
47a7cf1
 
47a38f9
 
 
 
47a7cf1
 
 
 
47a38f9
 
47a7cf1
47a38f9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47a7cf1
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
import streamlit as st
from transformers import AutoModelForCausalLM, AutoTokenizer

# Page config
st.set_page_config(
    page_title="Zephyr Chat",
    page_icon="🤖",
    layout="wide"
)

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

# Load model and tokenizer
@st.cache_resource
def load_model():
    model_name = "HuggingFaceH4/zephyr-7b-beta"
    tokenizer = AutoTokenizer.from_pretrained(model_name)
    model = AutoModelForCausalLM.from_pretrained(model_name)
    return model, tokenizer

# Main chat interface
st.title("Zephyr Chatbot 🤖")

try:
    model, tokenizer = load_model()
    
    # Display chat messages
    for message in st.session_state.messages:
        with st.chat_message(message["role"]):
            st.markdown(message["content"])

    # Chat input
    if prompt := st.chat_input("What's on your mind?"):
        # Add user message to chat history
        st.session_state.messages.append({"role": "user", "content": prompt})
        with st.chat_message("user"):
            st.markdown(prompt)
        
        # Generate response
        with st.chat_message("assistant"):
            with st.spinner("Thinking..."):
                # Prepare input
                input_text = f"User: {prompt}\nAssistant:"
                inputs = tokenizer(input_text, return_tensors="pt")
                
                # Generate response
                outputs = model.generate(
                    inputs.input_ids,
                    max_length=200,
                    num_return_sequences=1,
                    temperature=0.7,
                    pad_token_id=tokenizer.eos_token_id
                )
                
                # Decode and display response
                response = tokenizer.decode(outputs[0], skip_special_tokens=True)
                response = response.split("Assistant:")[-1].strip()
                
                st.markdown(response)
                st.session_state.messages.append({"role": "assistant", "content": response})

except Exception as e:
    st.error(f"Error: {str(e)}")
    st.info("Note: This app requires significant computational resources. Consider using a smaller model or upgrading your Space's resources.")