Spaces:
Running
Running
File size: 2,069 Bytes
dfe3145 89d1535 460789a dfe3145 89d1535 dfe3145 89d1535 dfe3145 d45c88d 89d1535 d45c88d 89d1535 dfe3145 4fd345c c335bb0 dfe3145 c335bb0 dfe3145 a479786 dfe3145 89d1535 dfe3145 |
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 |
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("Qwen/Qwen2.5-1.5b-Instruct")
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})
# ストリーミングを無効にして、単一の応答を取得
response = client.chat_completion(
messages,
max_tokens=max_tokens,
temperature=temperature,
top_p=top_p,
)
return response.choices[0].message.content
"""
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="ユーザーの質問や依頼にのみ答えてください。ポジティブに答えてください", label="System message"),
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="新規トークン最大"),
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="温度"),
gr.Slider(
minimum=0.1,
maximum=1.0,
value=0.95,
step=0.05,
label="Top-p (核 sampling)",
),
],
examples=[
["日本で有名なものと言えば"],
["レポートを書いてくれる？"],
["C#で素数を判定するコードを書いて"],
["250の約数は？"],
],
concurrency_limit=30 # 例: 同時に4つのリクエストを処理
)
if __name__ == "__main__":
demo.launch() |