|
import gradio as gr |
|
from openai import OpenAI |
|
|
|
from optillm.moa import mixture_of_agents |
|
from optillm.mcts import chat_with_mcts |
|
from optillm.bon import best_of_n_sampling |
|
|
|
API_KEY = os.environ.get("HF_TOKEN") |
|
|
|
def respond( |
|
message, |
|
history: list[tuple[str, str]], |
|
model, |
|
approach, |
|
system_message, |
|
max_tokens, |
|
temperature, |
|
top_p, |
|
): |
|
client = OpenAI(api_key=API_KEY, base_url="https://api-inference.huggingface.co/models/"+model+"/v1") |
|
|
|
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}) |
|
|
|
|
|
|
|
final_response = mixture_of_agents(system_message, message, client, model) |
|
return final_response |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
""" |
|
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface |
|
""" |
|
demo = gr.ChatInterface( |
|
respond, |
|
additional_inputs=[ |
|
gr.Dropdown( |
|
["meta-llama/Meta-Llama-3.1-70B-Instruct", "meta-llama/Meta-Llama-3.1-8B-Instruct", "HuggingFaceH4/zephyr-7b-beta"], |
|
value="meta-llama/Meta-Llama-3.1-70B-Instruct", label="Model", info="Choose the base model" |
|
), |
|
gr.Dropdown( |
|
["bon", "mcts", "moa"], value="moa", label="Approach", info="Choose the approach" |
|
), |
|
gr.Textbox(value="", 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() |
