Spaces:
Sleeping
Sleeping
File size: 2,081 Bytes
2817176 e56158c 4f33e12 2817176 e56158c 2817176 e56158c 2817176 e56158c 2817176 e56158c 2817176 e56158c 2817176 e56158c 2817176 e56158c 2817176 e56158c 2817176 e56158c 2817176 |
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 60 61 62 63 64 65 66 |
import gradio as gr
from huggingface_hub import InferenceClient
"""
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
"""
# Initialize the inference client with the model repo
client = InferenceClient("cognitivecomputations/TinyDolphin-2.8.2-1.1b-laser")
def respond(
message: str,
history: list[tuple[str, str]],
system_message: str,
max_tokens: int,
temperature: float,
top_p: float,
):
"""Generate a response for the chatbot using the InferenceClient."""
# Prepare the messages in the correct format for the API
messages = [{"role": "system", "content": system_message}]
for user_input, assistant_reply in history:
if user_input:
messages.append({"role": "user", "content": user_input})
if assistant_reply:
messages.append({"role": "assistant", "content": assistant_reply})
messages.append({"role": "user", "content": message})
response = ""
# Stream response tokens from the chat completion API
for message in client.chat_completion(
messages=messages,
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
token = message["choices"][0]["delta"].get("content", "")
response += token
yield response
"""
For information on how to customize the ChatInterface, peruse the Gradio docs: https://www.gradio.app/docs/chatinterface
"""
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()
|