dedekind-gradio-chat / gradio_module.py
Sathishkumartheta's picture
Update gradio_module.py
d0a907a verified
import gradio as gr
from huggingface_hub import InferenceClient
import llama_huggingface
import prompts
"""
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")
client = InferenceClient("meta-llama/Llama-3.2-1B-Instruct")
chat_model=''
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 = ""
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
def respond2(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
prompt=prompts.compose_prompt(
system_message='You are a friendly Chatbot.',
human_message=message
)
reply=chat_model.invoke(prompt)
yield reply.content
def init_gradio(repo_id):
global chat_model
chat_model=llama_huggingface.init_llama_chatmodel(repo_id=repo_id)
def get_gradio_interface():
demo = gr.ChatInterface(
respond2,
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)",
),
],
)
return demo