File size: 3,082 Bytes
32161b2 2d8b72c 32161b2 2d8b72c 7ee16c9 7e7729e af9ddfc 2d8b72c 7e7729e 2d8b72c 7e7729e 2d8b72c af9ddfc 32161b2 af9ddfc 2d8b72c 32161b2 af9ddfc |
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 76 77 78 79 80 81 82 83 84 85 86 87 88 |
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
"""
client = InferenceClient("Grandediw/lora_model")
def respond(message, history: list[tuple[str, str]], system_message, max_tokens, temperature, top_p):
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 = ""
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
"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
with gr.Blocks(title="Enhanced LORA Chat Interface") as demo:
gr.Markdown(
"""
# LORA Chat Assistant
Welcome! This is a demo of a LORA-based Chat Assistant.
Start by entering your prompt in the chat box below.
"""
)
with gr.Row():
# Left column: Chat interface
with gr.Column():
chat = gr.ChatInterface(
fn=respond,
additional_inputs=[],
height=500
)
# Right column: Settings and System Message
with gr.Column():
gr.Markdown("### Configuration")
system_message = gr.Textbox(
value="You are a friendly Chatbot.",
label="Initial Behavior (System Message)",
lines=3,
placeholder="Describe how the assistant should behave..."
)
with gr.Accordion("Advanced Settings", open=False):
max_tokens = gr.Slider(
minimum=1, maximum=2048, value=512, step=1,
label="Max new tokens",
info="Controls the maximum number of tokens in the response."
)
temperature = gr.Slider(
minimum=0.1, maximum=4.0, value=0.7, step=0.1,
label="Temperature",
info="Higher values produce more random outputs."
)
top_p = gr.Slider(
minimum=0.1, maximum=1.0, value=0.95, step=0.05,
label="Top-p (nucleus sampling)",
info="Limits the tokens considered to the top portion by cumulative probability."
)
# Link parameters to the chat interface's function
chat.configure(
additional_inputs=[system_message, max_tokens, temperature, top_p]
)
if __name__ == "__main__":
demo.launch()
|