Update app.py

app.py

@@ -4,7 +4,7 @@ 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("HuggingFaceH4/zephyr-7b-beta")
+client = InferenceClient("HuggingfaceH4/zephyr-7b-beta")
 
 
 def respond(
@@ -25,19 +25,15 @@ def respond(
 
     messages.append({"role": "user", "content": message})
 
-    response = ""
-
-    for message in client.chat_completion(
+    # 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,
-        stream=True,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+    )
 
-        response += token
-        yield response
+    return response.choices[0].message.content
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
@@ -45,17 +41,24 @@ For information on how to customize the ChatInterface, peruse the gradio docs: h
 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.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 (nucleus sampling)",
+            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
 )