Update app.py

app.py

@@ -1,7 +1,9 @@
+from flask import Flask, request, jsonify
 from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
 
-# Load the model
-model_name = "Qwen/Qwen2.5-0.5B-Instruct"  # Or 1.5B, 3B, 7B
+# 1️⃣ Load model and tokenizer
+model_name = "Qwen/Qwen2.5-0.5B-Instruct"  # Change to 1.5B, 3B, 7B if needed
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(
     model_name,
@@ -9,7 +11,7 @@ model = AutoModelForCausalLM.from_pretrained(
     device_map="auto"
 )
 
-# Chat function
+# 2️⃣ Define chat function
 def chat(prompt):
     messages = [{"role": "user", "content": prompt}]
     text = tokenizer.apply_chat_template(
@@ -24,5 +26,21 @@ def chat(prompt):
     
     return response
 
-# Test it
-print(chat("Hello, how are you?"))
+# 3️⃣ Create Flask app
+app = Flask(__name__)
+
+@app.route("/chat", methods=["GET"])
+def chat_route():
+    user_message = request.args.get("message")  # Get message from query string
+    if not user_message:
+        return jsonify({"error": "No message provided"}), 400
+    
+    try:
+        response = chat(user_message)
+        return jsonify({"response": response})
+    except Exception as e:
+        return jsonify({"error": str(e)}), 500
+
+# 4️⃣ Run Flask on port 7860
+if __name__ == "__main__":
+    app.run(host="0.0.0.0", port=7860)