Initial commit: upload all files in current directory

upload.ipynb

@@ -44,9 +44,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "CommitInfo(commit_url='https://huggingface.co/eunJ/codebert_vulnerability_detector_multi/commit/1ddd624297235c3b2206b93a05789ba1f1cb4788', commit_message='Initial commit: upload all files in current directory', commit_description='', oid='1ddd624297235c3b2206b93a05789ba1f1cb4788', pr_url=None, repo_url=RepoUrl('https://huggingface.co/eunJ/codebert_vulnerability_detector_multi', endpoint='https://huggingface.co', repo_type='model', repo_id='eunJ/codebert_vulnerability_detector_multi'), pr_revision=None, pr_num=None)"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "local_dir = \".\"  # 현재 디렉토리 전체\n",
     "\n",
@@ -61,9 +72,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Some weights of the model checkpoint at eunJ/codebert_vulnerability_detector_multi were not used when initializing RobertaForSequenceClassification: ['classifier.bias', 'classifier.weight', 'encoder.classifier.dense.bias', 'encoder.classifier.dense.weight', 'encoder.classifier.out_proj.bias', 'encoder.classifier.out_proj.weight', 'encoder.roberta.embeddings.LayerNorm.bias', 'encoder.roberta.embeddings.LayerNorm.weight', 'encoder.roberta.embeddings.position_embeddings.weight', 'encoder.roberta.embeddings.token_type_embeddings.weight', 'encoder.roberta.embeddings.word_embeddings.weight', 'encoder.roberta.encoder.layer.0.attention.output.LayerNorm.bias', 'encoder.roberta.encoder.layer.0.attention.output.LayerNorm.weight', 'encoder.roberta.encoder.layer.0.attention.output.dense.bias', 'encoder.roberta.encoder.layer.0.attention.output.dense.weight', 'encoder.roberta.encoder.layer.0.attention.self.key.bias', 'encoder.roberta.encoder.layer.0.attention.self.key.weight', 'encoder.roberta.encoder.layer.0.attention.self.query.bias', 'encoder.roberta.encoder.layer.0.attention.self.query.weight', 'encoder.roberta.encoder.layer.0.attention.self.value.bias', 'encoder.roberta.encoder.layer.0.attention.self.value.weight', 'encoder.roberta.encoder.layer.0.intermediate.dense.bias', 'encoder.roberta.encoder.layer.0.intermediate.dense.weight', 'encoder.roberta.encoder.layer.0.output.LayerNorm.bias', 'encoder.roberta.encoder.layer.0.output.LayerNorm.weight', 'encoder.roberta.encoder.layer.0.output.dense.bias', 'encoder.roberta.encoder.layer.0.output.dense.weight', 'encoder.roberta.encoder.layer.1.attention.output.LayerNorm.bias', 'encoder.roberta.encoder.layer.1.attention.output.LayerNorm.weight', 'encoder.roberta.encoder.layer.1.attention.output.dense.bias', 'encoder.roberta.encoder.layer.1.attention.output.dense.weight', 'encoder.roberta.encoder.layer.1.attention.self.key.bias', 'encoder.roberta.encoder.layer.1.attention.self.key.weight', 'encoder.roberta.encoder.layer.1.attention.self.query.bias', 'encoder.roberta.encoder.layer.1.attention.self.query.weight', 'encoder.roberta.encoder.layer.1.attention.self.value.bias', 'encoder.roberta.encoder.layer.1.attention.self.value.weight', 'encoder.roberta.encoder.layer.1.intermediate.dense.bias', 'encoder.roberta.encoder.layer.1.intermediate.dense.weight', 'encoder.roberta.encoder.layer.1.output.LayerNorm.bias', 'encoder.roberta.encoder.layer.1.output.LayerNorm.weight', 'encoder.roberta.encoder.layer.1.output.dense.bias', 'encoder.roberta.encoder.layer.1.output.dense.weight', 'encoder.roberta.encoder.layer.10.attention.output.LayerNorm.bias', 'encoder.roberta.encoder.layer.10.attention.output.LayerNorm.weight', 'encoder.roberta.encoder.layer.10.attention.output.dense.bias', 'encoder.roberta.encoder.layer.10.attention.output.dense.weight', 'encoder.roberta.encoder.layer.10.attention.self.key.bias', 'encoder.roberta.encoder.layer.10.attention.self.key.weight', 'encoder.roberta.encoder.layer.10.attention.self.query.bias', 'encoder.roberta.encoder.layer.10.attention.self.query.weight', 'encoder.roberta.encoder.layer.10.attention.self.value.bias', 'encoder.roberta.encoder.layer.10.attention.self.value.weight', 'encoder.roberta.encoder.layer.10.intermediate.dense.bias', 'encoder.roberta.encoder.layer.10.intermediate.dense.weight', 'encoder.roberta.encoder.layer.10.output.LayerNorm.bias', 'encoder.roberta.encoder.layer.10.output.LayerNorm.weight', 'encoder.roberta.encoder.layer.10.output.dense.bias', 'encoder.roberta.encoder.layer.10.output.dense.weight', 'encoder.roberta.encoder.layer.11.attention.output.LayerNorm.bias', 'encoder.roberta.encoder.layer.11.attention.output.LayerNorm.weight', 'encoder.roberta.encoder.layer.11.attention.output.dense.bias', 'encoder.roberta.encoder.layer.11.attention.output.dense.weight', 'encoder.roberta.encoder.layer.11.attention.self.key.bias', 'encoder.roberta.encoder.layer.11.attention.self.key.weight', 'encoder.roberta.encoder.layer.11.attention.self.query.bias', 'encoder.roberta.encoder.layer.11.attention.self.query.weight', 'encoder.roberta.encoder.layer.11.attention.self.value.bias', 'encoder.roberta.encoder.layer.11.attention.self.value.weight', 'encoder.roberta.encoder.layer.11.intermediate.dense.bias', 'encoder.roberta.encoder.layer.11.intermediate.dense.weight', 'encoder.roberta.encoder.layer.11.output.LayerNorm.bias', 'encoder.roberta.encoder.layer.11.output.LayerNorm.weight', 'encoder.roberta.encoder.layer.11.output.dense.bias', 'encoder.roberta.encoder.layer.11.output.dense.weight', 'encoder.roberta.encoder.layer.2.attention.output.LayerNorm.bias', 'encoder.roberta.encoder.layer.2.attention.output.LayerNorm.weight', 'encoder.roberta.encoder.layer.2.attention.output.dense.bias', 'encoder.roberta.encoder.layer.2.attention.output.dense.weight', 'encoder.roberta.encoder.layer.2.attention.self.key.bias', 'encoder.roberta.encoder.layer.2.attention.self.key.weight', 'encoder.roberta.encoder.layer.2.attention.self.query.bias', 'encoder.roberta.encoder.layer.2.attention.self.query.weight', 'encoder.roberta.encoder.layer.2.attention.self.value.bias', 'encoder.roberta.encoder.layer.2.attention.self.value.weight', 'encoder.roberta.encoder.layer.2.intermediate.dense.bias', 'encoder.roberta.encoder.layer.2.intermediate.dense.weight', 'encoder.roberta.encoder.layer.2.output.LayerNorm.bias', 'encoder.roberta.encoder.layer.2.output.LayerNorm.weight', 'encoder.roberta.encoder.layer.2.output.dense.bias', 'encoder.roberta.encoder.layer.2.output.dense.weight', 'encoder.roberta.encoder.layer.3.attention.output.LayerNorm.bias', 'encoder.roberta.encoder.layer.3.attention.output.LayerNorm.weight', 'encoder.roberta.encoder.layer.3.attention.output.dense.bias', 'encoder.roberta.encoder.layer.3.attention.output.dense.weight', 'encoder.roberta.encoder.layer.3.attention.self.key.bias', 'encoder.roberta.encoder.layer.3.attention.self.key.weight', 'encoder.roberta.encoder.layer.3.attention.self.query.bias', 'encoder.roberta.encoder.layer.3.attention.self.query.weight', 'encoder.roberta.encoder.layer.3.attention.self.value.bias', 'encoder.roberta.encoder.layer.3.attention.self.value.weight', 'encoder.roberta.encoder.layer.3.intermediate.dense.bias', 'encoder.roberta.encoder.layer.3.intermediate.dense.weight', 'encoder.roberta.encoder.layer.3.output.LayerNorm.bias', 'encoder.roberta.encoder.layer.3.output.LayerNorm.weight', 'encoder.roberta.encoder.layer.3.output.dense.bias', 'encoder.roberta.encoder.layer.3.output.dense.weight', 'encoder.roberta.encoder.layer.4.attention.output.LayerNorm.bias', 'encoder.roberta.encoder.layer.4.attention.output.LayerNorm.weight', 'encoder.roberta.encoder.layer.4.attention.output.dense.bias', 'encoder.roberta.encoder.layer.4.attention.output.dense.weight', 'encoder.roberta.encoder.layer.4.attention.self.key.bias', 'encoder.roberta.encoder.layer.4.attention.self.key.weight', 'encoder.roberta.encoder.layer.4.attention.self.query.bias', 'encoder.roberta.encoder.layer.4.attention.self.query.weight', 'encoder.roberta.encoder.layer.4.attention.self.value.bias', 'encoder.roberta.encoder.layer.4.attention.self.value.weight', 'encoder.roberta.encoder.layer.4.intermediate.dense.bias', 'encoder.roberta.encoder.layer.4.intermediate.dense.weight', 'encoder.roberta.encoder.layer.4.output.LayerNorm.bias', 'encoder.roberta.encoder.layer.4.output.LayerNorm.weight', 'encoder.roberta.encoder.layer.4.output.dense.bias', 'encoder.roberta.encoder.layer.4.output.dense.weight', 'encoder.roberta.encoder.layer.5.attention.output.LayerNorm.bias', 'encoder.roberta.encoder.layer.5.attention.output.LayerNorm.weight', 'encoder.roberta.encoder.layer.5.attention.output.dense.bias', 'encoder.roberta.encoder.layer.5.attention.output.dense.weight', 'encoder.roberta.encoder.layer.5.attention.self.key.bias', 'encoder.roberta.encoder.layer.5.attention.self.key.weight', 'encoder.roberta.encoder.layer.5.attention.self.query.bias', 'encoder.roberta.encoder.layer.5.attention.self.query.weight', 'encoder.roberta.encoder.layer.5.attention.self.value.bias', 'encoder.roberta.encoder.layer.5.attention.self.value.weight', 'encoder.roberta.encoder.layer.5.intermediate.dense.bias', 'encoder.roberta.encoder.layer.5.intermediate.dense.weight', 'encoder.roberta.encoder.layer.5.output.LayerNorm.bias', 'encoder.roberta.encoder.layer.5.output.LayerNorm.weight', 'encoder.roberta.encoder.layer.5.output.dense.bias', 'encoder.roberta.encoder.layer.5.output.dense.weight', 'encoder.roberta.encoder.layer.6.attention.output.LayerNorm.bias', 'encoder.roberta.encoder.layer.6.attention.output.LayerNorm.weight', 'encoder.roberta.encoder.layer.6.attention.output.dense.bias', 'encoder.roberta.encoder.layer.6.attention.output.dense.weight', 'encoder.roberta.encoder.layer.6.attention.self.key.bias', 'encoder.roberta.encoder.layer.6.attention.self.key.weight', 'encoder.roberta.encoder.layer.6.attention.self.query.bias', 'encoder.roberta.encoder.layer.6.attention.self.query.weight', 'encoder.roberta.encoder.layer.6.attention.self.value.bias', 'encoder.roberta.encoder.layer.6.attention.self.value.weight', 'encoder.roberta.encoder.layer.6.intermediate.dense.bias', 'encoder.roberta.encoder.layer.6.intermediate.dense.weight', 'encoder.roberta.encoder.layer.6.output.LayerNorm.bias', 'encoder.roberta.encoder.layer.6.output.LayerNorm.weight', 'encoder.roberta.encoder.layer.6.output.dense.bias', 'encoder.roberta.encoder.layer.6.output.dense.weight', 'encoder.roberta.encoder.layer.7.attention.output.LayerNorm.bias', 'encoder.roberta.encoder.layer.7.attention.output.LayerNorm.weight', 'encoder.roberta.encoder.layer.7.attention.output.dense.bias', 'encoder.roberta.encoder.layer.7.attention.output.dense.weight', 'encoder.roberta.encoder.layer.7.attention.self.key.bias', 'encoder.roberta.encoder.layer.7.attention.self.key.weight', 'encoder.roberta.encoder.layer.7.attention.self.query.bias', 'encoder.roberta.encoder.layer.7.attention.self.query.weight', 'encoder.roberta.encoder.layer.7.attention.self.value.bias', 'encoder.roberta.encoder.layer.7.attention.self.value.weight', 'encoder.roberta.encoder.layer.7.intermediate.dense.bias', 'encoder.roberta.encoder.layer.7.intermediate.dense.weight', 'encoder.roberta.encoder.layer.7.output.LayerNorm.bias', 'encoder.roberta.encoder.layer.7.output.LayerNorm.weight', 'encoder.roberta.encoder.layer.7.output.dense.bias', 'encoder.roberta.encoder.layer.7.output.dense.weight', 'encoder.roberta.encoder.layer.8.attention.output.LayerNorm.bias', 'encoder.roberta.encoder.layer.8.attention.output.LayerNorm.weight', 'encoder.roberta.encoder.layer.8.attention.output.dense.bias', 'encoder.roberta.encoder.layer.8.attention.output.dense.weight', 'encoder.roberta.encoder.layer.8.attention.self.key.bias', 'encoder.roberta.encoder.layer.8.attention.self.key.weight', 'encoder.roberta.encoder.layer.8.attention.self.query.bias', 'encoder.roberta.encoder.layer.8.attention.self.query.weight', 'encoder.roberta.encoder.layer.8.attention.self.value.bias', 'encoder.roberta.encoder.layer.8.attention.self.value.weight', 'encoder.roberta.encoder.layer.8.intermediate.dense.bias', 'encoder.roberta.encoder.layer.8.intermediate.dense.weight', 'encoder.roberta.encoder.layer.8.output.LayerNorm.bias', 'encoder.roberta.encoder.layer.8.output.LayerNorm.weight', 'encoder.roberta.encoder.layer.8.output.dense.bias', 'encoder.roberta.encoder.layer.8.output.dense.weight', 'encoder.roberta.encoder.layer.9.attention.output.LayerNorm.bias', 'encoder.roberta.encoder.layer.9.attention.output.LayerNorm.weight', 'encoder.roberta.encoder.layer.9.attention.output.dense.bias', 'encoder.roberta.encoder.layer.9.attention.output.dense.weight', 'encoder.roberta.encoder.layer.9.attention.self.key.bias', 'encoder.roberta.encoder.layer.9.attention.self.key.weight', 'encoder.roberta.encoder.layer.9.attention.self.query.bias', 'encoder.roberta.encoder.layer.9.attention.self.query.weight', 'encoder.roberta.encoder.layer.9.attention.self.value.bias', 'encoder.roberta.encoder.layer.9.attention.self.value.weight', 'encoder.roberta.encoder.layer.9.intermediate.dense.bias', 'encoder.roberta.encoder.layer.9.intermediate.dense.weight', 'encoder.roberta.encoder.layer.9.output.LayerNorm.bias', 'encoder.roberta.encoder.layer.9.output.LayerNorm.weight', 'encoder.roberta.encoder.layer.9.output.dense.bias', 'encoder.roberta.encoder.layer.9.output.dense.weight']\n",
+      "- This IS expected if you are initializing RobertaForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
+      "- This IS NOT expected if you are initializing RobertaForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n",
+      "Some weights of RobertaForSequenceClassification were not initialized from the model checkpoint at eunJ/codebert_vulnerability_detector_multi and are newly initialized: ['classifier.dense.bias', 'classifier.dense.weight', 'classifier.out_proj.bias', 'classifier.out_proj.weight', 'embeddings.LayerNorm.bias', 'embeddings.LayerNorm.weight', 'embeddings.position_embeddings.weight', 'embeddings.token_type_embeddings.weight', 'embeddings.word_embeddings.weight', 'encoder.layer.0.attention.output.LayerNorm.bias', 'encoder.layer.0.attention.output.LayerNorm.weight', 'encoder.layer.0.attention.output.dense.bias', 'encoder.layer.0.attention.output.dense.weight', 'encoder.layer.0.attention.self.key.bias', 'encoder.layer.0.attention.self.key.weight', 'encoder.layer.0.attention.self.query.bias', 'encoder.layer.0.attention.self.query.weight', 'encoder.layer.0.attention.self.value.bias', 'encoder.layer.0.attention.self.value.weight', 'encoder.layer.0.intermediate.dense.bias', 'encoder.layer.0.intermediate.dense.weight', 'encoder.layer.0.output.LayerNorm.bias', 'encoder.layer.0.output.LayerNorm.weight', 'encoder.layer.0.output.dense.bias', 'encoder.layer.0.output.dense.weight', 'encoder.layer.1.attention.output.LayerNorm.bias', 'encoder.layer.1.attention.output.LayerNorm.weight', 'encoder.layer.1.attention.output.dense.bias', 'encoder.layer.1.attention.output.dense.weight', 'encoder.layer.1.attention.self.key.bias', 'encoder.layer.1.attention.self.key.weight', 'encoder.layer.1.attention.self.query.bias', 'encoder.layer.1.attention.self.query.weight', 'encoder.layer.1.attention.self.value.bias', 'encoder.layer.1.attention.self.value.weight', 'encoder.layer.1.intermediate.dense.bias', 'encoder.layer.1.intermediate.dense.weight', 'encoder.layer.1.output.LayerNorm.bias', 'encoder.layer.1.output.LayerNorm.weight', 'encoder.layer.1.output.dense.bias', 'encoder.layer.1.output.dense.weight', 'encoder.layer.10.attention.output.LayerNorm.bias', 'encoder.layer.10.attention.output.LayerNorm.weight', 'encoder.layer.10.attention.output.dense.bias', 'encoder.layer.10.attention.output.dense.weight', 'encoder.layer.10.attention.self.key.bias', 'encoder.layer.10.attention.self.key.weight', 'encoder.layer.10.attention.self.query.bias', 'encoder.layer.10.attention.self.query.weight', 'encoder.layer.10.attention.self.value.bias', 'encoder.layer.10.attention.self.value.weight', 'encoder.layer.10.intermediate.dense.bias', 'encoder.layer.10.intermediate.dense.weight', 'encoder.layer.10.output.LayerNorm.bias', 'encoder.layer.10.output.LayerNorm.weight', 'encoder.layer.10.output.dense.bias', 'encoder.layer.10.output.dense.weight', 'encoder.layer.11.attention.output.LayerNorm.bias', 'encoder.layer.11.attention.output.LayerNorm.weight', 'encoder.layer.11.attention.output.dense.bias', 'encoder.layer.11.attention.output.dense.weight', 'encoder.layer.11.attention.self.key.bias', 'encoder.layer.11.attention.self.key.weight', 'encoder.layer.11.attention.self.query.bias', 'encoder.layer.11.attention.self.query.weight', 'encoder.layer.11.attention.self.value.bias', 'encoder.layer.11.attention.self.value.weight', 'encoder.layer.11.intermediate.dense.bias', 'encoder.layer.11.intermediate.dense.weight', 'encoder.layer.11.output.LayerNorm.bias', 'encoder.layer.11.output.LayerNorm.weight', 'encoder.layer.11.output.dense.bias', 'encoder.layer.11.output.dense.weight', 'encoder.layer.2.attention.output.LayerNorm.bias', 'encoder.layer.2.attention.output.LayerNorm.weight', 'encoder.layer.2.attention.output.dense.bias', 'encoder.layer.2.attention.output.dense.weight', 'encoder.layer.2.attention.self.key.bias', 'encoder.layer.2.attention.self.key.weight', 'encoder.layer.2.attention.self.query.bias', 'encoder.layer.2.attention.self.query.weight', 'encoder.layer.2.attention.self.value.bias', 'encoder.layer.2.attention.self.value.weight', 'encoder.layer.2.intermediate.dense.bias', 'encoder.layer.2.intermediate.dense.weight', 'encoder.layer.2.output.LayerNorm.bias', 'encoder.layer.2.output.LayerNorm.weight', 'encoder.layer.2.output.dense.bias', 'encoder.layer.2.output.dense.weight', 'encoder.layer.3.attention.output.LayerNorm.bias', 'encoder.layer.3.attention.output.LayerNorm.weight', 'encoder.layer.3.attention.output.dense.bias', 'encoder.layer.3.attention.output.dense.weight', 'encoder.layer.3.attention.self.key.bias', 'encoder.layer.3.attention.self.key.weight', 'encoder.layer.3.attention.self.query.bias', 'encoder.layer.3.attention.self.query.weight', 'encoder.layer.3.attention.self.value.bias', 'encoder.layer.3.attention.self.value.weight', 'encoder.layer.3.intermediate.dense.bias', 'encoder.layer.3.intermediate.dense.weight', 'encoder.layer.3.output.LayerNorm.bias', 'encoder.layer.3.output.LayerNorm.weight', 'encoder.layer.3.output.dense.bias', 'encoder.layer.3.output.dense.weight', 'encoder.layer.4.attention.output.LayerNorm.bias', 'encoder.layer.4.attention.output.LayerNorm.weight', 'encoder.layer.4.attention.output.dense.bias', 'encoder.layer.4.attention.output.dense.weight', 'encoder.layer.4.attention.self.key.bias', 'encoder.layer.4.attention.self.key.weight', 'encoder.layer.4.attention.self.query.bias', 'encoder.layer.4.attention.self.query.weight', 'encoder.layer.4.attention.self.value.bias', 'encoder.layer.4.attention.self.value.weight', 'encoder.layer.4.intermediate.dense.bias', 'encoder.layer.4.intermediate.dense.weight', 'encoder.layer.4.output.LayerNorm.bias', 'encoder.layer.4.output.LayerNorm.weight', 'encoder.layer.4.output.dense.bias', 'encoder.layer.4.output.dense.weight', 'encoder.layer.5.attention.output.LayerNorm.bias', 'encoder.layer.5.attention.output.LayerNorm.weight', 'encoder.layer.5.attention.output.dense.bias', 'encoder.layer.5.attention.output.dense.weight', 'encoder.layer.5.attention.self.key.bias', 'encoder.layer.5.attention.self.key.weight', 'encoder.layer.5.attention.self.query.bias', 'encoder.layer.5.attention.self.query.weight', 'encoder.layer.5.attention.self.value.bias', 'encoder.layer.5.attention.self.value.weight', 'encoder.layer.5.intermediate.dense.bias', 'encoder.layer.5.intermediate.dense.weight', 'encoder.layer.5.output.LayerNorm.bias', 'encoder.layer.5.output.LayerNorm.weight', 'encoder.layer.5.output.dense.bias', 'encoder.layer.5.output.dense.weight', 'encoder.layer.6.attention.output.LayerNorm.bias', 'encoder.layer.6.attention.output.LayerNorm.weight', 'encoder.layer.6.attention.output.dense.bias', 'encoder.layer.6.attention.output.dense.weight', 'encoder.layer.6.attention.self.key.bias', 'encoder.layer.6.attention.self.key.weight', 'encoder.layer.6.attention.self.query.bias', 'encoder.layer.6.attention.self.query.weight', 'encoder.layer.6.attention.self.value.bias', 'encoder.layer.6.attention.self.value.weight', 'encoder.layer.6.intermediate.dense.bias', 'encoder.layer.6.intermediate.dense.weight', 'encoder.layer.6.output.LayerNorm.bias', 'encoder.layer.6.output.LayerNorm.weight', 'encoder.layer.6.output.dense.bias', 'encoder.layer.6.output.dense.weight', 'encoder.layer.7.attention.output.LayerNorm.bias', 'encoder.layer.7.attention.output.LayerNorm.weight', 'encoder.layer.7.attention.output.dense.bias', 'encoder.layer.7.attention.output.dense.weight', 'encoder.layer.7.attention.self.key.bias', 'encoder.layer.7.attention.self.key.weight', 'encoder.layer.7.attention.self.query.bias', 'encoder.layer.7.attention.self.query.weight', 'encoder.layer.7.attention.self.value.bias', 'encoder.layer.7.attention.self.value.weight', 'encoder.layer.7.intermediate.dense.bias', 'encoder.layer.7.intermediate.dense.weight', 'encoder.layer.7.output.LayerNorm.bias', 'encoder.layer.7.output.LayerNorm.weight', 'encoder.layer.7.output.dense.bias', 'encoder.layer.7.output.dense.weight', 'encoder.layer.8.attention.output.LayerNorm.bias', 'encoder.layer.8.attention.output.LayerNorm.weight', 'encoder.layer.8.attention.output.dense.bias', 'encoder.layer.8.attention.output.dense.weight', 'encoder.layer.8.attention.self.key.bias', 'encoder.layer.8.attention.self.key.weight', 'encoder.layer.8.attention.self.query.bias', 'encoder.layer.8.attention.self.query.weight', 'encoder.layer.8.attention.self.value.bias', 'encoder.layer.8.attention.self.value.weight', 'encoder.layer.8.intermediate.dense.bias', 'encoder.layer.8.intermediate.dense.weight', 'encoder.layer.8.output.LayerNorm.bias', 'encoder.layer.8.output.LayerNorm.weight', 'encoder.layer.8.output.dense.bias', 'encoder.layer.8.output.dense.weight', 'encoder.layer.9.attention.output.LayerNorm.bias', 'encoder.layer.9.attention.output.LayerNorm.weight', 'encoder.layer.9.attention.output.dense.bias', 'encoder.layer.9.attention.output.dense.weight', 'encoder.layer.9.attention.self.key.bias', 'encoder.layer.9.attention.self.key.weight', 'encoder.layer.9.attention.self.query.bias', 'encoder.layer.9.attention.self.query.weight', 'encoder.layer.9.attention.self.value.bias', 'encoder.layer.9.attention.self.value.weight', 'encoder.layer.9.intermediate.dense.bias', 'encoder.layer.9.intermediate.dense.weight', 'encoder.layer.9.output.LayerNorm.bias', 'encoder.layer.9.output.LayerNorm.weight', 'encoder.layer.9.output.dense.bias', 'encoder.layer.9.output.dense.weight']\n",
+      "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
+     ]
+    }
+   ],
    "source": [
     "# Load model directly\n",
     "from transformers import AutoTokenizer, AutoModelForSequenceClassification\n",