Create app.py

app.py

@@ -0,0 +1,37 @@
+from flask import Flask, request, jsonify
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+MODEL_ID = "Qwen/Qwen2.5-Coder-1.0B-Instruct"
+
+print("Loading tokenizer...")
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
+
+print("Loading model...")
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_ID,
+    device_map="cpu"
+)
+print("Model loaded successfully")
+
+app = Flask(__name__)
+
+@app.route("/generate", methods=["POST"])
+def generate():
+    data = request.json
+    prompt = data.get("prompt", "")
+    max_tokens = int(data.get("max_tokens", 256))
+    if not prompt:
+        return jsonify({"error": "Prompt required"}), 400
+
+    inputs = tokenizer(prompt, return_tensors="pt")
+    outputs = model.generate(**inputs, max_new_tokens=max_tokens)
+    text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return jsonify({"response": text})
+
+@app.route("/", methods=["GET"])
+def health():
+    return jsonify({"status": "ok", "model": MODEL_ID})
+
+if __name__ == "__main__":
+    app.run(host="0.0.0.0", port=8000)