|
import gradio as gr |
|
from huggingface_hub import InferenceClient |
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
|
|
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-2b") |
|
model = AutoModelForCausalLM.from_pretrained("google/gemma-2-2b") |
|
""" |
|
For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference |
|
""" |
|
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta") |
|
|
|
|
|
def respond( |
|
message, |
|
history: list[tuple[str, str]], |
|
system_message, |
|
max_tokens, |
|
temperature, |
|
top_p, |
|
): |
|
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 = "" |
|
inputs = tokenizer(message, return_tensors="pt") |
|
|
|
generate_ids = model.generate(inputs.input_ids, max_length=30) |
|
response = tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0] |
|
|
|
yield 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.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() |