Create app.py

app.py

@@ -0,0 +1,63 @@
+from flask import Flask, request, jsonify
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+
+app = Flask(__name__)
+
+# モデルロード（起動時1回）
+torch.random.manual_seed(0)
+
+model = AutoModelForCausalLM.from_pretrained(
+    "microsoft/Phi-3-mini-4k-instruct",
+    device_map="cuda",
+    torch_dtype="auto",
+    trust_remote_code=True
+)
+
+tokenizer = AutoTokenizer.from_pretrained(
+    "microsoft/Phi-3-mini-4k-instruct"
+)
+
+pipe = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer
+)
+
+generation_args = {
+    "max_new_tokens": 500,
+    "return_full_text": False,
+    "temperature": 0.0,
+    "do_sample": False,
+}
+
+
+@app.route("/v1/chat/completions", methods=["POST"])
+def chat_completions():
+    data = request.json
+
+    messages = data.get("messages", [])
+
+    result = pipe(messages, **generation_args)
+    text = result[0]["generated_text"]
+
+    response = {
+        "id": "chatcmpl-local",
+        "object": "chat.completion",
+        "choices": [
+            {
+                "index": 0,
+                "message": {
+                    "role": "assistant",
+                    "content": text
+                },
+                "finish_reason": "stop"
+            }
+        ]
+    }
+
+    return jsonify(response)
+
+
+if __name__ == "__main__":
+    app.run(host="0.0.0.0", port=7860)