Update app.py

app.py

@@ -1,64 +1,27 @@
-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("HuggingFaceH4/zephyr-7b-beta")
-
-
-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,
-    ):
-        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 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)",
-        ),
-    ],
+from fastapi import FastAPI
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+
+# FastAPI アプリを作成
+app = FastAPI()
+
+# モデルのロード（4bit量子化）
+model_name = "Qwen/Qwen2.5-0.5B"
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    load_in_4bit=True,  # 4bit量子化
+    device_map="auto"
 )
-
-
-if __name__ == "__main__":
-    demo.launch()
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+# API エンドポイント
+@app.get("/")
+def home():
+    return {"message": "Qwen2.5-0.5B API is running with 4-bit quantization"}
+
+@app.post("/generate")
+def generate_text(prompt: str, max_length: int = 50):
+    text = pipeline("text-generation", model=model, tokenizer=tokenizer)(
+        prompt, max_length=max_length, do_sample=True, pad_token_id=tokenizer.pad_token_id
+    )
+    return {"generated_text": text[0]["generated_text"]}