Spaces:
Sleeping
Sleeping
File size: 1,494 Bytes
88a74a0 ffa7858 88a74a0 8d349df 88a74a0 ffa7858 88a74a0 ffa7858 88a74a0 ffa7858 88a74a0 ffa7858 88a74a0 ffa7858 88a74a0 ffa7858 88a74a0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 |
import gradio as gr
from huggingface_hub import InferenceClient, login
from typing import List, Tuple
client = InferenceClient("hackergeek98/gemma-finetuned")
def respond(
message: str,
history: List[Tuple[str, str]],
system_message: str,
max_tokens: int,
temperature: float,
top_p: float,
):
messages = [{"role": "system", "content": system_message}]
for user_msg, assistant_msg in history:
if user_msg:
messages.append({"role": "user", "content": user_msg})
if assistant_msg:
messages.append({"role": "assistant", "content": assistant_msg})
messages.append({"role": "user", "content": message})
response = ""
for msg in client.chat_completion(
messages,
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
token = msg.choices[0].delta.content if msg.choices[0].delta else ""
response += token
yield response
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()
|