Spaces:
Sleeping
Sleeping
File size: 1,434 Bytes
068eb68 233c71b 068eb68 4ed6a86 068eb68 4ed6a86 068eb68 4ed6a86 |
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 |
import gradio as gr
from huggingface_hub import InferenceClient
client = InferenceClient("nouamanetazi/hf-ar-134000")
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
# Combine history and new message into a single prompt
prompt = system_message + "\n\n"
for user_msg, assistant_msg in history:
if user_msg:
prompt += f"User: {user_msg}\n"
if assistant_msg:
prompt += f"Assistant: {assistant_msg}\n"
prompt += f"User: {message}\nAssistant:"
response = ""
# Use text-generation instead of chat_completion
for token in client.text_generation(
prompt,
max_new_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
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() |