Upload 2 files

app.py

@@ -0,0 +1,118 @@
+import streamlit as st
+import torch
+import time
+from threading import Thread
+from transformers import (
+    AutoTokenizer,
+    AutoModelForCausalLM,
+    TextIteratorStreamer
+)
+
+
+# App title
+st.set_page_config(page_title="😶‍🌫️ FuseChat Model")
+
+root_path = "FuseAI"
+
+@st.cache_resource
+def load_model(model_name):
+    tokenizer = AutoTokenizer.from_pretrained(
+        f"{root_path}/{model_name}",
+        trust_remote_code=True,
+    )
+
+    if tokenizer.pad_token_id is None:
+            if tokenizer.eos_token_id is not None:
+                tokenizer.pad_token_id = tokenizer.eos_token_id
+            else:
+                tokenizer.pad_token_id = 0
+
+    model = AutoModelForCausalLM.from_pretrained(
+        f"{root_path}/{model_name}",
+        device_map="auto",
+        torch_dtype=torch.bfloat16,
+        load_in_4bit=True,
+        trust_remote_code=True,
+    )
+
+    model.eval()
+    return model, tokenizer
+
+
+with st.sidebar:
+    st.title('😶‍🌫️ FuseChat')
+    st.write('This chatbot is created using FuseChat, a model developed by FuseAI')
+    st.subheader('Models and parameters')
+    selected_model = st.sidebar.selectbox('Choose a FuseChat model', ['FuseChat-7B-VaRM', 'FuseChat-7B-Slerp', 'FuseChat-7B-TA'], key='selected_model')
+    temperature = st.sidebar.slider('temperature', min_value=0.01, max_value=5.0, value=0.1, step=0.01)
+    top_p = st.sidebar.slider('top_p', min_value=0.01, max_value=1.0, value=0.9, step=0.01)
+    top_k = st.sidebar.slider('top_k', min_value=1, max_value=1000, value=50, step=1)
+    repetition_penalty = st.sidebar.slider('repetition penalty', min_value=1., max_value=2., value=1.2, step=0.05)
+    max_length = st.sidebar.slider('max new tokens', min_value=32, max_value=2000, value=240, step=8)
+
+with st.spinner('loading model..'):
+    model, tokenizer = load_model(selected_model)
+
+# Store LLM generated responses
+if "messages" not in st.session_state.keys():
+    st.session_state.messages = [{"role": "assistant", "content": "How may I assist you today?"}]
+
+# Display or clear chat messages
+for message in st.session_state.messages:
+    with st.chat_message(message["role"]):
+        st.write(message["content"])
+
+def clear_chat_history():
+    st.session_state.messages = [{"role": "assistant", "content": "How may I assist you today?"}]
+st.sidebar.button('Clear Chat History', on_click=clear_chat_history)
+
+
+def generate_fusechat_response():
+    string_dialogue = "You are a helpful and harmless assistant."
+    for dict_message in st.session_state.messages:
+        if dict_message["role"] == "user":
+            string_dialogue += "GPT4 Correct User: " + dict_message["content"] + "<|end_of_turn|>"
+        else:
+            string_dialogue += "GPT4 Correct Assistant: " + dict_message["content"] + "<|end_of_turn|>"
+
+    input_ids = tokenizer(f"{string_dialogue}GPT4 Correct Assistant: ", return_tensors="pt").input_ids
+    streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
+    generate_kwargs = dict(
+        {"input_ids": input_ids},
+        streamer=streamer,
+        max_new_tokens=max_length,
+        do_sample=True,
+        top_p=top_p,
+        top_k=top_k,
+        temperature=temperature,
+        num_beams=1,
+        repetition_penalty=repetition_penalty,
+    )
+    t = Thread(target=model.generate, kwargs=generate_kwargs)
+    t.start()
+
+    outputs = []
+    for text in streamer:
+        outputs.append(text)
+    return "".join(outputs)
+
+# User-provided prompt
+if prompt := st.chat_input("Hello there! How are you doing?"):
+    st.session_state.messages.append({"role": "user", "content": prompt})
+    with st.chat_message("user"):
+        st.write(prompt)
+
+# Generate a new response if last message is not from assistant
+if st.session_state.messages[-1]["role"] != "assistant":
+    with st.chat_message("assistant"):
+        with st.spinner("Thinking..."):
+            response = generate_fusechat_response()
+            placeholder = st.empty()
+            full_response = ''
+            for item in response:
+                full_response += item
+                time.sleep(0.05)
+                placeholder.markdown(full_response + "▌")
+            placeholder.markdown(full_response)
+    message = {"role": "assistant", "content": full_response}
+    st.session_state.messages.append(message)

requirements.txt

@@ -0,0 +1,8 @@
+streamlit==1.29.0
+bitsandbytes==0.42.0
+accelerate==0.25.0
+transformers==4.34.0
+torch==2.1.2
+protobuf==4.25.1
+scipy==1.11.4
+sentencepiece==0.1.99