File size: 1,748 Bytes
5fd0c28 b2af35c d67d04a b2af35c 8a91905 f613acc 5fd0c28 408d189 b2af35c 408d189 b2af35c 5fd0c28 b2af35c 408d189 b2af35c 5fd0c28 b2af35c 5fd0c28 408d189 5fd0c28 f613acc b2af35c |
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 |
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("Mat17892/llama_lora_G14")
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
# Combine the system message and chat history into a single string
prompt = system_message + "\n"
for user_input, assistant_reply in history:
if user_input:
prompt += f"User: {user_input}\n"
if assistant_reply:
prompt += f"Assistant: {assistant_reply}\n"
prompt += f"User: {message}\nAssistant:"
# Send the request to the model
response = ""
for token in client.text_generation(
prompt,
max_new_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
response += token.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,
type="messages",
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() |