finalized

app.py

@@ -5,64 +5,42 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
 import logging
 import os
 
-# Logging setup
-logging.basicConfig(level=logging.DEBUG, format='%(asctime)s - %(levelname)s - %(message)s')
+MIN_TRANSFORMERS_VERSION = '4.25.1'
 
-# Hugging Face Model Hub Repository
-MODEL_REPO = "./"  # Replace with your Hugging Face model repo name
+# Check transformers version
+import transformers
+assert transformers.__version__ >= MIN_TRANSFORMERS_VERSION, f'Please upgrade transformers to version {MIN_TRANSFORMERS_VERSION} or higher.'
 
-# Load tokenizer and model from Hugging Face Model Hub
-try:
-    logging.info("Loading model and tokenizer from Hugging Face Model Hub...")
-    tokenizer = AutoTokenizer.from_pretrained(MODEL_REPO)
-    dtype = torch.bfloat16 if torch.cuda.is_available() else torch.float32
-    model = AutoModelForCausalLM.from_pretrained(MODEL_REPO, torch_dtype=dtype).to(
-        "cuda" if torch.cuda.is_available() else "cpu"
-    )
-    logging.info("Model loaded successfully.")
-except Exception as e:
-    logging.error("Failed to load the model or tokenizer.", exc_info=True)
-    raise e
+# Initialize tokenizer and model from local directory
+model_dir = "./"
+tokenizer = AutoTokenizer.from_pretrained(model_dir)
+model = AutoModelForCausalLM.from_pretrained(model_dir, torch_dtype=torch.bfloat16)
 
-# Flask app initialization
 app = Flask(__name__)
 CORS(app)  # Enable CORS
 
+logging.basicConfig(level=logging.DEBUG)
+
 def generate_response(prompt):
-    """Generate a response from the model given a prompt."""
-    try:
-        logging.debug(f"Generating response for prompt: {prompt}")
-        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
-        )
-        token = outputs.sequences[0, input_length:]
-        output_str = tokenizer.decode(token, skip_special_tokens=True)
-        logging.debug(f"Generated response: {output_str}")
-        return output_str
-    except Exception as e:
-        logging.error("Error during response generation", exc_info=True)
-        return "Sorry, I encountered an error while generating the response."
+    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
+    )
+    token = outputs.sequences[0, input_length:]
+    output_str = tokenizer.decode(token, skip_special_tokens=True)
+    return output_str
 
 @app.route('/chat', methods=['POST'])
 def chat():
-    """Endpoint to handle chat requests."""
-    try:
-        logging.debug("Received a POST request to /chat")
-        data = request.json
-        logging.debug(f"Request data: {data}")
-
-        if not data or "message" not in data:
-            return jsonify({"error": "Invalid request. 'message' field is required."}), 400
-
-        user_input = data.get("message", "")
-        prompt = f"<human>: {user_input}\n<bot>:"
-        response = generate_response(prompt)
-        return jsonify({"response": response}), 200
-    except Exception as e:
-        logging.error("Error in /chat endpoint", exc_info=True)
-        return jsonify({"error": "Internal server error", "message": str(e)}), 500
+    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

config.json

@@ -22,4 +22,4 @@
   "use_cache": true,
   "use_parallel_residual": false,
   "vocab_size": 50432
-}
+}

generation_config.json

@@ -3,4 +3,4 @@
   "bos_token_id": 0,
   "eos_token_id": 0,
   "transformers_version": "4.28.1"
-}
+}

special_tokens_map.json

@@ -2,4 +2,4 @@
   "bos_token": "<|endoftext|>",
   "eos_token": "<|endoftext|>",
   "unk_token": "<|endoftext|>"
-}
+}

tokenizer_config.json

@@ -1,4 +1,3 @@
-<<<<<<< HEAD
 {
   "add_prefix_space": false,
   "bos_token": "<|endoftext|>",
@@ -8,14 +7,3 @@
   "tokenizer_class": "GPTNeoXTokenizer",
   "unk_token": "<|endoftext|>"
 }
-=======
-{
-  "add_prefix_space": false,
-  "bos_token": "<|endoftext|>",
-  "clean_up_tokenization_spaces": true,
-  "eos_token": "<|endoftext|>",
-  "model_max_length": 2048,
-  "tokenizer_class": "GPTNeoXTokenizer",
-  "unk_token": "<|endoftext|>"
-}
->>>>>>> 6ff0da104f5a2eb5ee298dc0164db0c0b16215e2