Spaces:
Running
Running
File size: 2,315 Bytes
f152a90 b207a62 c75f1ad c088d8d b207a62 c088d8d b207a62 c088d8d b90bc2b 64b5005 b207a62 c088d8d b207a62 c088d8d b207a62 c088d8d b207a62 c088d8d b207a62 c088d8d b207a62 f152a90 c088d8d f152a90 b207a62 |
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 67 68 69 70 71 72 73 74 75 |
import gradio as gr
from huggingface_hub import InferenceClient
import os
"""
For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/en/guides/inference
"""
# Retrieve the Hugging Face token
hf_token = os.environ.get("HF_TOKEN")
if not hf_token:
raise ValueError("Please set the HF_TOKEN environment variable with your Hugging Face API token.")
# Initialize the InferenceClient with a correct model
client = InferenceClient("models/meta-llama/Llama-3.2-1B", token=hf_token)
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
messages = [{"role": "system", "content": system_message}]
for user_input, assistant_response in history:
if user_input:
messages.append({"role": "user", "content": user_input})
if assistant_response:
messages.append({"role": "assistant", "content": assistant_response})
messages.append({"role": "user", "content": message})
response = ""
# Start the chat completion
try:
for msg in client.chat_completion(
messages=messages,
max_new_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
token = msg.delta.get("content", "")
response += token
yield response
except Exception as e:
yield f"Error during inference: {e}"
"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
demo = gr.ChatInterface(
fn=respond,
additional_inputs=[
gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
gr.Slider(minimum=1, maximum=1024, value=512, step=1, label="Max new tokens"),
gr.Slider(minimum=0.1, maximum=1.0, value=0.7, step=0.01, label="Temperature"),
gr.Slider(
minimum=0.1,
maximum=1.0,
value=0.95,
step=0.01,
label="Top-p (nucleus sampling)",
),
],
title="Chat with Llama 2",
description="A chat interface using Llama 2 model via Hugging Face Inference API.",
)
if __name__ == "__main__":
demo.launch()
|