llm-chat / app.py
Andybeyond's picture
Update app.py
e51cef7 verified
import gradio as gr
from huggingface_hub import InferenceClient
# Define a dictionary of pre-defined LLMs
# To add a new LLM:
# 1. Go to https://huggingface.co/models
# 2. Find an open-source LLM that supports the chat completion task
# 3. Copy the model's name (e.g., "mistralai/Mistral-7B-Instruct-v0.1")
# 4. Add it to this dictionary with a user-friendly name as the key
MODELS = {
"Zephyr 7B Beta": "HuggingFaceH4/zephyr-7b-beta",
"Mistral 7B Instruct": "mistralai/Mistral-7B-Instruct-v0.1",
"Llama 2 7B": "meta-llama/Llama-2-7b-chat-hf",
"FLAN-T5 XXL": "google/flan-t5-xxl",
# Add more models here as needed
}
def respond(
message,
history: list[tuple[str, str]],
model_name,
system_message,
max_tokens,
temperature,
top_p,
):
client = InferenceClient(MODELS[model_name])
messages = [{"role": "system", "content": system_message}]
for val in history:
if val[0]:
messages.append({"role": "user", "content": val[0]})
if val[1]:
messages.append({"role": "assistant", "content": val[1]})
messages.append({"role": "user", "content": message})
response = ""
try:
for message in client.chat_completion(
messages,
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
token = message.choices[0].delta.content
response += token
yield response
except Exception as e:
yield f"Error: {str(e)}"
demo = gr.ChatInterface(
respond,
additional_inputs=[
gr.Dropdown(choices=list(MODELS.keys()), label="Select LLM", value=list(MODELS.keys())[0]),
gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
gr.Slider(
minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"
),
],
)
if __name__ == "__main__":
demo.launch(share=True)