Create app.py

app.py

@@ -0,0 +1,58 @@
+from flask import Flask, request, jsonify
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+import os
+
+app = Flask(__name__)
+
+model_id = "HuggingFaceH4/zephyr-7b-beta"
+
+print("🚀 Loading model:", model_id)
+
+tokenizer = AutoTokenizer.from_pretrained(model_id, use_fast=False)
+model = AutoModelForCausalLM.from_pretrained(model_id)
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model.to(device)
+
+print("✅ Model Loaded Successfully")
+
+@app.route('/chat', methods=['POST'])
+def chat():
+    try:
+        data = request.get_json()
+        message = data.get("message", "").strip()
+
+        if not message:
+            return jsonify({"error": "Empty message"}), 400
+
+        # Simple clean prompt
+        prompt = f"Human: {message}\nAssistant:"
+
+        inputs = tokenizer(prompt, return_tensors="pt").to(device)
+
+        output = model.generate(
+            inputs.input_ids,
+            max_length=300,
+            do_sample=True,
+            top_k=40,
+            top_p=0.92,
+            temperature=0.72,
+            pad_token_id=tokenizer.eos_token_id
+        )
+
+        full = tokenizer.decode(output[0], skip_special_tokens=True)
+        reply = full.split("Assistant:")[-1].strip()
+
+        return jsonify({"reply": reply})
+
+    except Exception as e:
+        return jsonify({"error": str(e)}), 500
+
+
+@app.route('/')
+def home():
+    return "LLM Space Active."
+
+if __name__ == "__main__":
+    app.run(host="0.0.0.0", port=7860)