Create app.py

app.py

@@ -0,0 +1,32 @@
+from flask import Flask, request, jsonify
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import os
+
+app = Flask(__name__)
+
+# Load model and tokenizer
+MODEL_NAME = "bigscience/bloomz-1b1"  # Replace with your model name
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+model = AutoModelForCausalLM.from_pretrained(MODEL_NAME)
+
+@app.route("/api/chat", methods=["POST"])
+def chat():
+    try:
+        # Get user message from the POST request
+        user_message = request.json.get("message", "")
+        
+        # Tokenize user input
+        inputs = tokenizer(user_message, return_tensors="pt", truncation=True, max_length=512)
+        
+        # Generate response
+        outputs = model.generate(inputs["input_ids"], max_length=150, num_return_sequences=1, pad_token_id=tokenizer.eos_token_id)
+        response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+        
+        # Return the response as JSON
+        return jsonify({"response": response})
+    except Exception as e:
+        return jsonify({"error": str(e)}), 500
+
+if __name__ == "__main__":
+    # Use the default port for Hugging Face Spaces
+    app.run(host="0.0.0.0", port=int(os.environ.get("PORT", 7860)))