Spaces:
Sleeping
Sleeping
File size: 1,655 Bytes
1031d05 055366b 1031d05 02c027c 1031d05 60b402d 1031d05 b11239c 1031d05 6f04663 1031d05 b11239c 1031d05 6f04663 1031d05 60b402d 1031d05 6f04663 1031d05 6f04663 1031d05 6f04663 b11239c |
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 57 58 59 |
import gradio as gr
import asyncio
from huggingface_hub import InferenceClient
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
# Ensure history is in OpenAI-style 'role' and 'content' format
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]})
# Add the user's latest message
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
demo = gr.ChatInterface(
fn=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)",
),
],
chatbot=gr.Chatbot(type="messages"), # Specify the 'messages' format
)
if __name__ == "__main__":
demo.queue().launch() # Simply call queue without `concurrency_count`
|