Update app.py

app.py

@@ -1,13 +1,17 @@
+import os
 import gradio as gr
 from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForImageTextToText
 
-"""
-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
-"""
+# ── ① Hugging Face トークンを環境変数にセット（ご自身のトークンを設定してください）
+os.environ["HUGGINGFACE_TOKEN"] = "YOUR_HF_TOKEN"
 
-processor = AutoProcessor.from_pretrained("mlabonne/gemma-3-27b-it-abliterated")
-model = AutoModelForImageTextToText.from_pretrained("mlabonne/gemma-3-27b-it-abliterated")
+# ── ② InferenceClient を生成
+client = InferenceClient(api_key=os.environ["HUGGINGFACE_TOKEN"])
 
+# （※ローカル推論は使わない場合、以下のモデルロードは不要です）
+tokenizer = AutoTokenizer.from_pretrained("mlabonne/gemma-3-27b-it-abliterated")
+model = AutoModelForImageTextToText.from_pretrained("mlabonne/gemma-3-27b-it-abliterated")
 
 def respond(
     message,
@@ -17,50 +21,41 @@ def respond(
     temperature,
     top_p,
 ):
+    # システムプロンプトを先頭に
     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]})
-
+    # 過去のやり取りを追加
+    for u, a in history:
+        if u:
+            messages.append({"role": "user", "content": u})
+        if a:
+            messages.append({"role": "assistant", "content": a})
+    # 最新ユーザー入力
     messages.append({"role": "user", "content": message})
 
     response = ""
-
-    for message in client.chat_completion(
-        messages,
+    # ── ③ モデル指定で chat_completion を呼び出し
+    for chunk in client.chat_completion(
+        model="mlabonne/gemma-3-27b-it-abliterated",
+        messages=messages,
         max_tokens=max_tokens,
-        stream=True,
         temperature=temperature,
         top_p=top_p,
+        stream=True,
     ):
-        token = message.choices[0].delta.content
-
-        response += token
+        delta = chunk.choices[0].delta.content
+        response += delta
         yield response
 
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# ── ④ Gradio の ChatInterface 定義
 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.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
     ],
 )
 
-
 if __name__ == "__main__":
     demo.launch()