Spaces:
Sleeping
Sleeping
File size: 1,409 Bytes
0c03f9e 1f107ec 9fa8e4e 1f107ec cff74fc 1f107ec 5740a17 8febce8 ef332e0 5740a17 ef332e0 8febce8 cff74fc 8febce8 1f107ec 8febce8 cff74fc ef332e0 cff74fc 8febce8 5740a17 8febce8 1f107ec 8febce8 9fa8e4e 1f107ec 8febce8 |
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 |
import gradio as gr
from huggingface_hub import InferenceClient
import os
system_message = os.environ["SYSTEM_MESSAGE"]
HF_TOKEN = os.environ["HF_TOKEN"]
MODEL_NAME = os.environ["MODEL_NAME"]
client = InferenceClient(token=HF_TOKEN)
def respond(message, history, max_tokens, temperature, top_p):
prompt = [{"role": "system", "content": system_message}]
for user_msg, assistant_msg in history:
prompt.append({"role": "user", "content": user_msg})
prompt.append({"role": "assistant", "content": assistant_msg})
prompt.append({"role": "user", "content": message})
response = []
stream = client.chat.completions.create(
model=MODEL_NAME,
messages=prompt,
max_tokens=max_tokens,
temperature=temperature,
top_p=top_p,
stream=True
)
for chunk in stream:
if not chunk.choices:
continue
delta = chunk.choices[0].delta
token = getattr(delta, "content", None)
if token:
response.append(token)
yield "".join(response)
app = gr.ChatInterface(
fn=respond,
additional_inputs=[
gr.Slider(16, 2048, value=512, step=1, label="Max Tokens"),
gr.Slider(0.1, 2.0, value=0.7, step=0.1, label="Temperature"),
gr.Slider(0.1, 1.0, value=0.95, step=0.05, label="Top-p"),
],
)
if __name__ == "__main__":
app.launch()
|