Spaces:
Sleeping
Sleeping
File size: 1,822 Bytes
f08cdaa 9f94dcc f08cdaa 9f94dcc 056a41c 9f94dcc c54ab00 f08cdaa 65b49e4 f08cdaa 6f782c2 f08cdaa 6f782c2 f08cdaa 056a41c f08cdaa 056a41c f08cdaa 65b49e4 15c10e8 f08cdaa |
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 |
import gradio as gr
from huggingface_hub import InferenceClient,login
from os import getenv
import random
# Login to Hugging Face
login(getenv("Token"))
client = InferenceClient( provider="nebius",model="meta-llama/Llama-3.2-3B-Instruct")
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
print('system prompt',system_message)
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]})
messages.append({"role": "user", "content": message})
response = ""
seed = random.randint(1, 10000)
for message in client.chat_completion(
messages,
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
seed=seed
):
token = message.choices[0].delta.content
response += token
yield response
print("the history", messages, "response",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()
|