initial commit

app.py

@@ -12,7 +12,7 @@ app = Flask(__name__)
 
 # Minimal setup: pick a detector (example: MarylandDetector)
 model_id = "meta-llama/Llama-3.2-1B-Instruct"
-tokenizer = AutoTokenizer.from_pretrained(model_id)
+tokenizer = AutoTokenizer.from_pretrained(model_id, cache_dir="static/hf_cache")
 detector = MarylandDetector(tokenizer=tokenizer)
 
 def tokenize_text(text):

sandbox.ipynb

@@ -9,14 +9,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
     "from transformers import AutoTokenizer, LlamaForCausalLM\n",
     "\n",
     "model_id = \"meta-llama/Llama-3.2-1B-Instruct\"\n",
-    "# cache should be in static/hf_cache\n",
     "tokenizer = AutoTokenizer.from_pretrained(model_id, cache_dir=\"static/hf_cache\")"
    ]
   },