runtime error fixes

app.py

@@ -5,45 +5,44 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
 import logging
 import os
 
-MIN_TRANSFORMERS_VERSION = '4.25.1'
-
-# Check transformers version
-import transformers
-assert transformers.__version__ >= MIN_TRANSFORMERS_VERSION, f'Please upgrade transformers to version {MIN_TRANSFORMERS_VERSION} or higher.'
+# Initialize logger
+logging.basicConfig(level=logging.DEBUG)
 
-# Initialize tokenizer and model from local directory
-model_dir = "hsb06/toghetherAi-model"
-tokenizer = AutoTokenizer.from_pretrained(model_dir)
-model = AutoModelForCausalLM.from_pretrained(model_dir, torch_dtype=torch.bfloat16)
+# Load tokenizer and model
+logging.info("Loading model...")
+model_repo = "hsb06/toghetherAi-model"
+tokenizer = AutoTokenizer.from_pretrained(model_repo, use_auth_token=True)
+model = AutoModelForCausalLM.from_pretrained(model_repo, torch_dtype=torch.float16, use_auth_token=True).to("cuda" if torch.cuda.is_available() else "cpu")
+logging.info("Model loaded successfully.")
 
+# Initialize Flask app
 app = Flask(__name__)
-CORS(app)  # Enable CORS
-
-logging.basicConfig(level=logging.DEBUG)
+CORS(app)
 
 def generate_response(prompt):
-    inputs = tokenizer(prompt, return_tensors='pt').to(model.device)
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
     input_length = inputs.input_ids.shape[1]
     outputs = model.generate(
-        **inputs, max_new_tokens=128, do_sample=True, temperature=0.7, top_p=0.7, top_k=50, return_dict_in_generate=True
+        **inputs,
+        max_new_tokens=128,
+        do_sample=True,
+        temperature=0.7,
+        top_p=0.7,
+        top_k=50,
+        return_dict_in_generate=True,
     )
     token = outputs.sequences[0, input_length:]
-    output_str = tokenizer.decode(token, skip_special_tokens=True)
-    return output_str
+    return tokenizer.decode(token, skip_special_tokens=True)
 
-@app.route('/chat', methods=['POST'])
+@app.route("/chat", methods=["POST"])
 def chat():
-    logging.debug("Received a POST request")
     data = request.json
-    logging.debug(f"Request data: {data}")
     user_input = data.get("message", "")
     prompt = f"<human>: {user_input}\n<bot>:"
     response = generate_response(prompt)
-    logging.debug(f"Generated response: {response}")
     return jsonify({"response": response})
 
 if __name__ == "__main__":
-    # Get the port from environment variable or default to 5000
-    port = int(os.getenv("PORT", 5000))
+    port = int(os.getenv("PORT", 7860))  # Default to 7860
     logging.info(f"Starting Flask app on port {port}")
-    app.run(debug=True, host="0.0.0.0", port=port)
+    app.run(debug=False, host="0.0.0.0", port=port)