Spaces:
Sleeping
Sleeping
File size: 2,412 Bytes
9c7e22f 0ffcc97 70e229a 5fc4fcc 58b011a 9334c42 5fc4fcc 29d374a 58b011a f8496a1 70e229a 53635ec 70e229a 53635ec 70e229a f8496a1 70e229a |
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 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 |
import streamlit as st
from llama_cpp import Llama
st.set_page_config(page_title="Chat with AI", page_icon="🤖")
# Custom CSS for better styling
st.markdown("""
<style>
.stTextInput > div > div > input {
background-color: #f0f2f6;
}
.chat-message {
padding: 1.5rem; border-radius: 0.5rem; margin-bottom: 1rem; display: flex
}
.chat-message.user {
background-color: #2b313e
}
.chat-message.bot {
background-color: #475063
}
.chat-message .avatar {
width: 20%;
}
.chat-message .avatar img {
max-width: 78px;
max-height: 78px;
border-radius: 50%;
object-fit: cover;
}
.chat-message .message {
width: 80%;
padding: 0 1.5rem;
color: #fff;
}
</style>
""", unsafe_allow_html=True)
@st.cache_resource
def load_model():
return Llama.from_pretrained(
repo_id="Mykes/med_phi3-mini-4k-GGUF",
filename="*Q4_K_M.gguf",
verbose=False,
n_ctx=256,
n_batch=256,
n_threads=4
)
llm = load_model()
basic_prompt = "Q: {question}\nA:"
# Initialize chat history
if "messages" not in st.session_state:
st.session_state.messages = []
# Display chat messages from history on app rerun
for message in st.session_state.messages:
with st.chat_message(message["role"]):
st.markdown(message["content"])
# React to user input
if prompt := st.chat_input("What is your question?"):
# Display user message in chat message container
st.chat_message("user").markdown(prompt)
# Add user message to chat history
st.session_state.messages.append({"role": "user", "content": prompt})
model_input = basic_prompt.format(question=prompt)
# Display assistant response in chat message container
with st.chat_message("assistant"):
message_placeholder = st.empty()
full_response = ""
for token in llm(
model_input,
max_tokens=None,
stop=["<end_of_turn>"],
echo=True,
stream=True
):
full_response += token['choices'][0]['text']
message_placeholder.markdown(full_response + "▌")
message_placeholder.markdown(full_response)
# Add assistant response to chat history
st.session_state.messages.append({"role": "assistant", "content": full_response})
st.sidebar.title("Chat with AI")
st.sidebar.markdown("This is a simple chat interface using Streamlit and an AI model.") |