Create app.py

app.py

@@ -0,0 +1,46 @@
+from flask import Flask, request, jsonify
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+# Initialize the model and tokenizer
+model = AutoModelForCausalLM.from_pretrained("anto18671/lumenspark", trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained("anto18671/lumenspark", trust_remote_code=True)
+
+# Set up Flask application
+app = Flask(__name__)
+
+# Define inference endpoint
+@app.route("/generate", methods=["POST"])
+def generate_text():
+    data = request.get_json()
+
+    # Extract the input text
+    text = data.get("text", "")
+    if not text:
+        return jsonify({"error": "Input text is required"}), 400
+
+    # Tokenize input text
+    encoded_input = tokenizer(text, return_tensors='pt')
+
+    # Generate text using the model
+    output = model.generate(
+        input_ids=encoded_input["input_ids"],
+        attention_mask=encoded_input["attention_mask"],
+        max_length=100,
+        min_length=20,
+        temperature=0.6,
+        top_k=50,
+        top_p=0.9,
+        repetition_penalty=1.1,
+        do_sample=True
+    )
+
+    # Decode the generated text
+    decoded_text = tokenizer.decode(output[0], skip_special_tokens=True)
+
+    # Return generated text as JSON response
+    return jsonify({"generated_text": decoded_text})
+
+# Run the Flask app
+if __name__ == "__main__":
+    app.run(host="0.0.0.0", port=5000)