Spaces:
Sleeping
Sleeping
File size: 1,985 Bytes
4320901 8facfef 4320901 bdf3fd2 4320901 76d357d b81c1d8 61ca3bd 4320901 5b24305 169e4da 8e24bb0 4320901 9943267 4320901 |
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 |
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("wannaphong/tongyi-model-v2.0-1b-th")
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,
# presence_penalty=1.1,
# stop=["<|im_end|>"]
):
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
"""
demo = gr.ChatInterface(
respond,
additional_inputs=[
gr.Textbox(value="You are an AI assistant named TongYip (ทองหยิบ), created by PyThaiNLP. As an AI assistant, you can answer questions in Thai and English. Your responses should be friendly, unbiased, informative, detailed, and faithful.", label="System message"),
gr.Slider(minimum=1, maximum=2048, value=1024, step=1, label="Max new tokens"),
gr.Slider(minimum=0.1, maximum=4.0, value=0.2, step=0.1, label="Temperature"),
gr.Slider(
minimum=0.1,
maximum=1.0,
value=0.80,
step=0.05,
label="Top-p (nucleus sampling)",
),
],
)
if __name__ == "__main__":
demo.launch()
|