diff --git a/models/phishing-models/phishing-bert-20221115.onnx b/models/phishing-models/phishing-bert-20221115.onnx
deleted file mode 100644
index 7c1e0ec716..0000000000
--- a/models/phishing-models/phishing-bert-20221115.onnx
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:80cc263dd7f9087dd19decfa687614635381540b29ba5aabc4ae1ffa7009e757
-size 438007870
diff --git a/models/phishing-models/phishing-bert-20221115.pt b/models/phishing-models/phishing-bert-20221115.pt
deleted file mode 100644
index b28ef683ba..0000000000
--- a/models/phishing-models/phishing-bert-20221115.pt
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0bca567a4bd840fb4b20b6b4a1fb98d9a5a79b2b2dc959b7b539ee35e10357b6
-size 438040521
diff --git a/models/phishing-models/phishing-bert-20230421.onnx b/models/phishing-models/phishing-bert-20230421.onnx
new file mode 100644
index 0000000000..6365d2bc31
--- /dev/null
+++ b/models/phishing-models/phishing-bert-20230421.onnx
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d6e89b2890ed8f7d89577f3b204a117f115c90116025280a5b164c55400e8d4
+size 438207850
diff --git a/models/phishing-models/phishing-bert-20230421.pt b/models/phishing-models/phishing-bert-20230421.pt
new file mode 100644
index 0000000000..b27de845fb
--- /dev/null
+++ b/models/phishing-models/phishing-bert-20230421.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e0a4b6454dbf20625161e36337bf75e1175cc7fb9a70af22671379489818482
+size 438049721
diff --git a/models/sid-models/sid-minibert-20211021.onnx b/models/sid-models/sid-minibert-20211021.onnx
deleted file mode 100644
index 0140aa2fa4..0000000000
--- a/models/sid-models/sid-minibert-20211021.onnx
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9a8729582a6784121e78ba4305513c3099314a75ecf51501470d1244555588cc
-size 44720790
diff --git a/models/sid-models/sid-minibert-20211021.pth b/models/sid-models/sid-minibert-20211021.pth
deleted file mode 100644
index 3ce5fdd30a..0000000000
--- a/models/sid-models/sid-minibert-20211021.pth
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d552a23031146cc76952989f0299b6b79090bf0e8998c0c40bb635966b5801e7
-size 44737609
diff --git a/models/sid-models/sid-minibert-20230424.onnx b/models/sid-models/sid-minibert-20230424.onnx
new file mode 100644
index 0000000000..6e28a69796
--- /dev/null
+++ b/models/sid-models/sid-minibert-20230424.onnx
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d12f31d6dcebd03dab1824c850ebe928b5f5b76d3e9029e9b160f593c12bea9e
+size 44793456
diff --git a/models/sid-models/sid-minibert-20230424.pt b/models/sid-models/sid-minibert-20230424.pt
new file mode 100644
index 0000000000..c63fdc8124
--- /dev/null
+++ b/models/sid-models/sid-minibert-20230424.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4216cca489d02cfdf7d03f2c8c5f19e52d94de8661957f9449ba289329b6cb0
+size 44743365
diff --git a/models/training-tuning-scripts/log-parsing-models/log-parsing-training.ipynb b/models/training-tuning-scripts/log-parsing-models/log-parsing-training.ipynb
index 74b5f16d2a..6185f737ff 100644
--- a/models/training-tuning-scripts/log-parsing-models/log-parsing-training.ipynb
+++ b/models/training-tuning-scripts/log-parsing-models/log-parsing-training.ipynb
@@ -24,7 +24,9 @@
   {
    "cell_type": "code",
    "execution_count": 1,
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "from seqeval.metrics import classification_report,accuracy_score,f1_score\n",
@@ -66,7 +68,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
@@ -111,56 +113,59 @@
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th>257</th>\n",
+       "      <th>4655</th>\n",
        "      <td>&lt;NA&gt;</td>\n",
        "      <td>&lt;NA&gt;</td>\n",
-       "      <td>158.69.5.181 - - [04/Apr/2018:23:06:49 +0200] ...</td>\n",
-       "      <td>158.69.5.181</td>\n",
-       "      <td>-</td>\n",
+       "      <td>193.106.31.130 - - [11/Aug/2019:19:54:28 +0200...</td>\n",
+       "      <td>193.106.31.130</td>\n",
        "      <td>-</td>\n",
        "      <td>-</td>\n",
        "      <td>-</td>\n",
-       "      <td>Other</td>\n",
-       "      <td>Other</td>\n",
-       "      <td>&lt;NA&gt;</td>\n",
-       "      <td>1.1</td>\n",
+       "      <td>Mozilla/4.0 (compatible; MSIE 7.0; Windows NT ...</td>\n",
+       "      <td>IE</td>\n",
+       "      <td>Windows</td>\n",
+       "      <td>Vista</td>\n",
+       "      <td>1.0</td>\n",
        "      <td>POST</td>\n",
        "      <td>/administrator/index.php</td>\n",
-       "      <td>4498</td>\n",
+       "      <td>4481</td>\n",
        "      <td>200</td>\n",
-       "      <td>[04/Apr/2018:23:06:49 +0200]</td>\n",
+       "      <td>[11/Aug/2019:19:54:28 +0200]</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "text/plain": [
-       "    error_level error_message  \\\n",
-       "257        <NA>          <NA>   \n",
+       "     error_level error_message  \\\n",
+       "4655        <NA>          <NA>   \n",
+       "\n",
+       "                                                    raw     remote_host  \\\n",
+       "4655  193.106.31.130 - - [11/Aug/2019:19:54:28 +0200...  193.106.31.130   \n",
        "\n",
-       "                                                   raw   remote_host  \\\n",
-       "257  158.69.5.181 - - [04/Apr/2018:23:06:49 +0200] ...  158.69.5.181   \n",
+       "     remote_logname remote_user request_header_referer  \\\n",
+       "4655              -           -                      -   \n",
        "\n",
-       "    remote_logname remote_user request_header_referer  \\\n",
-       "257              -           -                      -   \n",
+       "                              request_header_user_agent  \\\n",
+       "4655  Mozilla/4.0 (compatible; MSIE 7.0; Windows NT ...   \n",
        "\n",
-       "    request_header_user_agent request_header_user_agent__browser__family  \\\n",
-       "257                         -                                      Other   \n",
+       "     request_header_user_agent__browser__family  \\\n",
+       "4655                                         IE   \n",
        "\n",
-       "    request_header_user_agent__os__family  \\\n",
-       "257                                 Other   \n",
+       "     request_header_user_agent__os__family  \\\n",
+       "4655                               Windows   \n",
        "\n",
-       "    request_header_user_agent__os__version_string  request_http_ver  \\\n",
-       "257                                          <NA>               1.1   \n",
+       "     request_header_user_agent__os__version_string  request_http_ver  \\\n",
+       "4655                                         Vista               1.0   \n",
        "\n",
-       "    request_method               request_url response_bytes_clf status  \\\n",
-       "257           POST  /administrator/index.php               4498    200   \n",
+       "     request_method               request_url response_bytes_clf status  \\\n",
+       "4655           POST  /administrator/index.php               4481    200   \n",
        "\n",
-       "                    time_received  \n",
-       "257  [04/Apr/2018:23:06:49 +0200]  "
+       "                     time_received  \n",
+       "4655  [11/Aug/2019:19:54:28 +0200]  "
       ]
      },
-     "execution_count": 4,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -172,7 +177,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
@@ -191,7 +196,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -203,7 +208,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -215,7 +220,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -247,7 +252,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -274,7 +279,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -292,7 +297,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -323,15 +328,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/opt/conda/envs/rapids/lib/python3.8/site-packages/cudf/core/subword_tokenizer.py:187: UserWarning: When truncation is not True, the behaviour currently differs from HuggingFace as cudf always returns overflowing tokens\n",
-      "  warn(warning_msg)\n"
+      "/opt/conda/envs/morpheus/lib/python3.8/site-packages/cudf/core/subword_tokenizer.py:189: UserWarning: When truncation is not True, the behavior currently differs from HuggingFace as cudf always returns overflowing tokens\n",
+      "  warnings.warn(warning_msg)\n"
      ]
     }
    ],
@@ -349,7 +354,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -365,7 +370,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -376,7 +381,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -395,7 +400,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -414,7 +419,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -424,7 +429,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -437,7 +442,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 18,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -456,17 +461,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 19,
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Some weights of the model checkpoint at bert-base-cased were not used when initializing BertForTokenClassification: ['cls.seq_relationship.bias', 'cls.predictions.decoder.weight', 'cls.predictions.transform.dense.bias', 'cls.seq_relationship.weight', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.bias', 'cls.predictions.transform.dense.weight', 'cls.predictions.transform.LayerNorm.bias']\n",
+      "Some weights of the model checkpoint at bert-base-cased were not used when initializing BertForTokenClassification: ['cls.predictions.transform.dense.bias', 'cls.seq_relationship.weight', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.decoder.weight', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.bias', 'cls.seq_relationship.bias', 'cls.predictions.transform.dense.weight']\n",
       "- This IS expected if you are initializing BertForTokenClassification 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 BertForTokenClassification 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 BertForTokenClassification were not initialized from the model checkpoint at bert-base-cased and are newly initialized: ['classifier.bias', 'classifier.weight']\n",
+      "Some weights of BertForTokenClassification were not initialized from the model checkpoint at bert-base-cased and are newly initialized: ['classifier.weight', 'classifier.bias']\n",
       "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
      ]
     }
@@ -491,7 +496,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 20,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -515,37 +520,37 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Epoch:  50%|█████     | 1/2 [00:35<00:35, 35.41s/it]"
+      "Epoch:  50%|█████     | 1/2 [00:38<00:38, 38.73s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Train loss: 0.18636336472931586\n"
+      "Train loss: 0.2076284834630277\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Epoch: 100%|██████████| 2/2 [01:10<00:00, 35.27s/it]"
+      "Epoch: 100%|██████████| 2/2 [01:17<00:00, 38.85s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Train loss: 0.0059268270875965185\n",
-      "CPU times: user 44.8 s, sys: 25.7 s, total: 1min 10s\n",
-      "Wall time: 1min 10s\n"
+      "Train loss: 0.008250679652531925\n",
+      "CPU times: user 1min 16s, sys: 896 ms, total: 1min 17s\n",
+      "Wall time: 1min 17s\n"
      ]
     },
     {
@@ -596,7 +601,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 22,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -606,33 +611,58 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 23,
    "metadata": {},
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/opt/conda/envs/morpheus/lib/python3.8/site-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: [PAD] seems not to be NE tag.\n",
+      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "f1 score: 0.997863\n",
+      "Accuracy score: 0.999263\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/opt/conda/envs/morpheus/lib/python3.8/site-packages/seqeval/metrics/v1.py:57: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
+      "  _warn_prf(average, modifier, msg_start, len(result))\n",
+      "/opt/conda/envs/morpheus/lib/python3.8/site-packages/seqeval/metrics/v1.py:57: UndefinedMetricWarning: Recall and F-score are ill-defined and being set to 0.0 in labels with no true samples. Use `zero_division` parameter to control this behavior.\n",
+      "  _warn_prf(average, modifier, msg_start, len(result))\n"
+     ]
+    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "f1 score: 0.998655\n",
-      "Accuracy score: 0.999771\n",
       "                                               precision    recall  f1-score   support\n",
       "\n",
-      "                                  error_level      1.000     1.000     1.000       100\n",
-      "                                error_message      1.000     1.000     1.000       100\n",
-      "                                  remote_host      1.000     1.000     1.000       913\n",
-      "                       request_header_referer      1.000     1.000     1.000       508\n",
-      "                    request_header_user_agent      1.000     1.000     1.000      1002\n",
-      "request_header_user_agent__os__version_string      0.875     1.000     0.933        14\n",
-      "                             request_http_ver      1.000     1.000     1.000       913\n",
-      "                               request_method      1.000     1.000     1.000       913\n",
-      "                                  request_url      0.997     0.981     0.989       913\n",
-      "                           response_bytes_clf      1.000     1.000     1.000       911\n",
-      "                                       status      1.000     1.000     1.000       912\n",
-      "                                time_received      1.000     1.000     1.000       985\n",
+      "                                         PAD]      0.000     0.000     0.000         0\n",
+      "                                  error_level      1.000     1.000     1.000        90\n",
+      "                                error_message      1.000     1.000     1.000        90\n",
+      "                                  remote_host      1.000     1.000     1.000       890\n",
+      "                       request_header_referer      1.000     0.996     0.998       476\n",
+      "                    request_header_user_agent      1.000     1.000     1.000      1005\n",
+      "request_header_user_agent__os__version_string      0.000     0.000     0.000        19\n",
+      "                             request_http_ver      1.000     1.000     1.000       890\n",
+      "                               request_method      1.000     1.000     1.000       890\n",
+      "                                  request_url      1.000     0.990     0.995       890\n",
+      "                           response_bytes_clf      1.000     1.000     1.000       888\n",
+      "                                       status      1.000     1.000     1.000       888\n",
+      "                                time_received      0.998     1.000     0.999       952\n",
       "\n",
-      "                                    micro avg      0.999     0.998     0.999      8184\n",
-      "                                    macro avg      0.989     0.998     0.994      8184\n",
-      "                                 weighted avg      0.999     0.998     0.999      8184\n",
+      "                                    micro avg      0.999     0.996     0.998      7968\n",
+      "                                    macro avg      0.846     0.845     0.846      7968\n",
+      "                                 weighted avg      0.997     0.996     0.997      7968\n",
       "\n"
      ]
     }
@@ -700,7 +730,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 24,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -714,6 +744,65 @@
     "    model.save_pretrained('log_parsing_apache_morpheus')"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Export model to ONNX"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "tokenizer_output = tokenizer(logs_df[\"raw_preprocess\"][0:3],\n",
+    "          max_length=MAX_SEQ_LEN,\n",
+    "          stride = STRIDE,\n",
+    "          truncation=False,\n",
+    "          max_num_rows = 3,\n",
+    "          add_special_tokens=False,\n",
+    "          return_tensors='pt'\n",
+    "     )\n",
+    "sample_input_ids = tokenizer_output['input_ids'].type(torch.long)\n",
+    "sample_attention_masks = tokenizer_output['attention_mask'].type(torch.long)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "sample_model_input = (sample_input_ids, sample_attention_masks)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "torch.onnx.export(model,              \n",
+    "                  sample_model_input,               \n",
+    "                  \"model.onnx\",                                      # where to save the model\n",
+    "                  export_params=True,                                # store the trained parameter weights inside the model file\n",
+    "                  opset_version=10,                                  # the ONNX version to export the model to\n",
+    "                  do_constant_folding=True,                          # whether to execute constant folding for optimization\n",
+    "                  input_names = ['input_ids','attention_mask'],      # the model's input names\n",
+    "                  output_names = ['output'],                         # the model's output names\n",
+    "                  dynamic_axes={'input_ids' : {0 : 'batch_size'},    # variable length axes\n",
+    "                                'attention_mask': {0: 'batch_size'}, \n",
+    "                                'output' : {0 : 'batch_size'}})"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -733,18 +822,11 @@
     "\n",
     "https://medium.com/rapids-ai/cybert-28b35a4c81c4"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -758,7 +840,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.10"
+   "version": "3.8.15"
   }
  },
  "nbformat": 4,
diff --git a/models/training-tuning-scripts/phishing-models/phish-bert-training.ipynb b/models/training-tuning-scripts/phishing-models/phish-bert-training.ipynb
index 743ad313fc..3cd8eed7d7 100644
--- a/models/training-tuning-scripts/phishing-models/phish-bert-training.ipynb
+++ b/models/training-tuning-scripts/phishing-models/phish-bert-training.ipynb
@@ -43,19 +43,13 @@
   {
    "cell_type": "code",
    "execution_count": 1,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/opt/conda/envs/morpheus/lib/python3.8/site-packages/tqdm/auto.py:22: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
-      "  from .autonotebook import tqdm as notebook_tqdm\n"
-     ]
-    }
-   ],
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
    "source": [
     "import cudf\n",
+    "from cudf.core.subword_tokenizer import SubwordTokenizer\n",
     "from sklearn.model_selection import train_test_split\n",
     "from sklearn.metrics import f1_score\n",
     "import binary_sequence_classifier\n",
@@ -91,7 +85,9 @@
   {
    "cell_type": "code",
    "execution_count": 2,
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "if not os.path.isfile(\"smsspamcollection.zip\"):    \n",
@@ -103,7 +99,9 @@
   {
    "cell_type": "code",
    "execution_count": 3,
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [
     {
      "name": "stdout",
@@ -127,7 +125,9 @@
   {
    "cell_type": "code",
    "execution_count": 4,
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "if not os.path.isfile(\"SMSSpamCollection\"):\n",
@@ -202,10 +202,10 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertForSequenceClassification: ['cls.predictions.transform.dense.bias', 'cls.seq_relationship.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.transform.dense.weight', 'cls.predictions.decoder.weight', 'cls.seq_relationship.weight', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.bias']\n",
+      "Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertForSequenceClassification: ['cls.predictions.transform.dense.weight', 'cls.predictions.transform.dense.bias', 'cls.seq_relationship.bias', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.decoder.weight', 'cls.predictions.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.seq_relationship.weight']\n",
       "- This IS expected if you are initializing BertForSequenceClassification 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 BertForSequenceClassification 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 BertForSequenceClassification were not initialized from the model checkpoint at bert-base-uncased and are newly initialized: ['classifier.bias', 'classifier.weight']\n",
+      "Some weights of BertForSequenceClassification were not initialized from the model checkpoint at bert-base-uncased and are newly initialized: ['classifier.weight', 'classifier.bias']\n",
       "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
      ]
     }
@@ -241,28 +241,28 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Epoch:  50%|█████     | 1/2 [00:35<00:35, 35.78s/it]"
+      "Epoch:  50%|█████     | 1/2 [00:34<00:34, 34.08s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Train loss: 0.09204745624946165\n"
+      "Train loss: 0.07317519100782062\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Epoch: 100%|██████████| 2/2 [01:11<00:00, 35.92s/it]"
+      "Epoch: 100%|██████████| 2/2 [01:09<00:00, 34.79s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Train loss: 0.01900260798949083\n"
+      "Train loss: 0.015208904994817982\n"
      ]
     },
     {
@@ -283,8 +283,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# save model file and configuration file in a directory\n",
-    "seq_classifier.save_model(\"./phish-bert-model\")"
+    "# save as pytorch model\n",
+    "torch.save(seq_classifier._model.module, \"phishing-bert.pt\")"
    ]
   },
   {
@@ -345,7 +345,7 @@
     {
      "data": {
       "text/plain": [
-       "0.9729729729729729"
+       "0.9731543624161074"
       ]
      },
      "execution_count": 15,
@@ -359,6 +359,59 @@
     "f1_score(true_labels, tests)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "## Export Model to ONNX"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tokenizer = SubwordTokenizer(\"./resources/bert-base-uncased-hash.txt\", do_lower_case=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tokenizer_output = tokenizer(df[\"message\"][0:3],\n",
+    "                                max_length=128,\n",
+    "                                max_num_rows=3,\n",
+    "                                truncation=True,\n",
+    "                                add_special_tokens=True,\n",
+    "                                return_tensors=\"pt\")\n",
+    "\n",
+    "sample_model_input = (tokenizer_output[\"input_ids\"].type(torch.long), tokenizer_output[\"attention_mask\"].type(torch.long))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "torch.onnx.export(seq_classifier._model.module,              \n",
+    "                  sample_model_input,               \n",
+    "                  \"model.onnx\",                                      # where to save the model\n",
+    "                  export_params=True,                                # store the trained parameter weights inside the model file\n",
+    "                  opset_version=10,                                  # the ONNX version to export the model to\n",
+    "                  do_constant_folding=True,                          # whether to execute constant folding for optimization\n",
+    "                  input_names = ['input_ids','attention_mask'],      # the model's input names\n",
+    "                  output_names = ['output'],                         # the model's output names\n",
+    "                  dynamic_axes={'input_ids' : {0 : 'batch_size'},    # variable length axes\n",
+    "                                'attention_mask': {0: 'batch_size'}, \n",
+    "                                'output' : {0 : 'batch_size'}})"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -418,7 +471,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.9 (default, Jan 26 2021, 15:33:00) \n[GCC 8.4.0]"
+   "version": "3.8.15"
   },
   "vscode": {
    "interpreter": {
diff --git a/models/training-tuning-scripts/root-cause-models/root-cause-bert.ipynb b/models/training-tuning-scripts/root-cause-models/root-cause-bert.ipynb
index 9d729610ac..37f09e6754 100644
--- a/models/training-tuning-scripts/root-cause-models/root-cause-bert.ipynb
+++ b/models/training-tuning-scripts/root-cause-models/root-cause-bert.ipynb
@@ -64,8 +64,9 @@
    },
    "outputs": [],
    "source": [
-    "import cudf;\n",
-    "from binary_sequence_classifier import BinarySequenceClassifier;\n",
+    "import cudf\n",
+    "from cudf.core.subword_tokenizer import SubwordTokenizer\n",
+    "from binary_sequence_classifier import BinarySequenceClassifier\n",
     "from os import path;\n",
     "from sklearn.metrics import confusion_matrix\n",
     "from sklearn.metrics import f1_score\n",
@@ -88,7 +89,9 @@
   {
    "cell_type": "code",
    "execution_count": 2,
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "random_seed=42"
@@ -100,7 +103,8 @@
    "metadata": {
     "colab": {},
     "colab_type": "code",
-    "id": "_UkeC7SG2krJ"
+    "id": "_UkeC7SG2krJ",
+    "tags": []
    },
    "outputs": [],
    "source": [
@@ -187,7 +191,9 @@
   {
    "cell_type": "code",
    "execution_count": 11,
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "#X_train.to_csv(\"Rootcause-training-data.csv\",index=False)"
@@ -217,7 +223,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "X_test.to_json(\"Rootcause-validation-data.jsonlines\",orient='records',lines=True)"
+    "X_test.to_json(\"Rootcause-validation-data.jsonlines\", orient='records',lines=True)"
    ]
   },
   {
@@ -264,10 +270,10 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertForSequenceClassification: ['cls.predictions.transform.dense.weight', 'cls.predictions.transform.dense.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.seq_relationship.weight', 'cls.predictions.transform.LayerNorm.bias', 'cls.seq_relationship.bias', 'cls.predictions.bias', 'cls.predictions.decoder.weight']\n",
+      "Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertForSequenceClassification: ['cls.predictions.decoder.weight', 'cls.predictions.transform.dense.weight', 'cls.seq_relationship.weight', 'cls.predictions.transform.LayerNorm.weight', 'cls.seq_relationship.bias', 'cls.predictions.transform.dense.bias', 'cls.predictions.bias', 'cls.predictions.transform.LayerNorm.bias']\n",
       "- This IS expected if you are initializing BertForSequenceClassification 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 BertForSequenceClassification 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 BertForSequenceClassification were not initialized from the model checkpoint at bert-base-uncased and are newly initialized: ['classifier.weight', 'classifier.bias']\n",
+      "Some weights of BertForSequenceClassification were not initialized from the model checkpoint at bert-base-uncased and are newly initialized: ['classifier.bias', 'classifier.weight']\n",
       "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
      ]
     }
@@ -307,14 +313,14 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Epoch: 100%|██████████| 1/1 [00:08<00:00,  8.64s/it]"
+      "Epoch: 100%|██████████| 1/1 [00:09<00:00,  9.12s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Train loss: 0.6523606370795857\n"
+      "Train loss: 0.5870807089588859\n"
      ]
     },
     {
@@ -370,7 +376,7 @@
     {
      "data": {
       "text/plain": [
-       "0.9601666666666666"
+       "0.95"
       ]
      },
      "execution_count": 21,
@@ -423,7 +429,7 @@
     {
      "data": {
       "text/plain": [
-       "0.9765765765765766"
+       "0.9591474245115452"
       ]
      },
      "execution_count": 24,
@@ -457,8 +463,8 @@
     {
      "data": {
       "text/plain": [
-       "array([[189,  13],\n",
-       "       [  0, 271]])"
+       "array([[180,  22],\n",
+       "       [  1, 270]])"
       ]
      },
      "execution_count": 25,
@@ -487,28 +493,29 @@
     {
      "data": {
       "text/plain": [
-       "(array([  0,   1,   7,   9,  11,  12,  13,  14,  16,  18,  19,  20,  22,\n",
-       "         23,  24,  25,  29,  31,  34,  42,  44,  45,  46,  47,  49,  50,\n",
-       "         51,  52,  53,  55,  56,  57,  58,  59,  61,  62,  63,  64,  65,\n",
-       "         66,  67,  68,  69,  70,  71,  73,  74,  75,  80,  81,  82,  85,\n",
-       "         86,  88,  89,  90,  92,  93,  94,  95,  97,  98,  99, 101, 103,\n",
-       "        104, 105, 106, 107, 109, 110, 112, 113, 114, 115, 117, 119, 120,\n",
-       "        123, 124, 125, 126, 128, 129, 130, 131, 134, 136, 137, 138, 139,\n",
-       "        140, 141, 142, 143, 144, 145, 146, 148, 149, 150, 153, 154, 156,\n",
-       "        159, 160, 161, 162, 163, 164, 165, 166, 170, 172, 173, 174, 175,\n",
-       "        176, 178, 181, 182, 183, 187, 188, 191, 194, 196, 200, 201, 202,\n",
-       "        205, 206, 207, 209, 210, 214, 215, 216, 217, 218, 221, 222, 223,\n",
-       "        224, 226, 227, 228, 229, 231, 234, 235, 236, 237, 240, 244, 245,\n",
-       "        246, 250, 251, 254, 255, 256, 257, 262, 265, 266, 267, 268, 269,\n",
-       "        271, 274, 275, 276, 278, 284, 285, 287, 289, 290, 291, 292, 293,\n",
-       "        294, 295, 296, 299, 300, 301, 302, 303, 304, 309, 311, 312, 315,\n",
-       "        316, 317, 318, 319, 321, 322, 323, 328, 329, 330, 331, 332, 334,\n",
-       "        335, 340, 343, 347, 349, 350, 351, 352, 353, 354, 355, 356, 357,\n",
-       "        358, 361, 363, 365, 367, 369, 373, 374, 375, 378, 379, 380, 381,\n",
-       "        382, 383, 384, 385, 386, 388, 389, 390, 392, 394, 395, 396, 397,\n",
-       "        398, 399, 400, 401, 402, 404, 406, 407, 408, 409, 410, 411, 412,\n",
-       "        414, 415, 416, 418, 419, 420, 421, 425, 426, 429, 432, 434, 435,\n",
-       "        436, 437, 438, 441, 442, 443, 444, 450, 453, 460, 471]),)"
+       "(array([  0,   1,   2,   7,   9,  11,  12,  13,  14,  16,  18,  19,  20,\n",
+       "         22,  23,  24,  25,  29,  31,  34,  42,  43,  44,  45,  46,  47,\n",
+       "         49,  50,  51,  52,  53,  55,  56,  57,  58,  59,  61,  62,  63,\n",
+       "         64,  65,  66,  67,  68,  69,  70,  71,  73,  74,  80,  81,  82,\n",
+       "         85,  86,  88,  89,  90,  92,  93,  94,  95,  97,  98,  99, 101,\n",
+       "        103, 104, 105, 106, 107, 109, 110, 112, 113, 114, 115, 117, 119,\n",
+       "        120, 123, 124, 125, 126, 127, 128, 129, 130, 131, 134, 136, 137,\n",
+       "        138, 139, 140, 141, 142, 143, 144, 145, 146, 148, 149, 150, 153,\n",
+       "        154, 155, 156, 159, 160, 161, 162, 163, 164, 165, 166, 170, 171,\n",
+       "        172, 173, 174, 175, 176, 178, 181, 182, 183, 187, 188, 191, 194,\n",
+       "        196, 200, 201, 202, 205, 206, 207, 209, 210, 214, 215, 216, 217,\n",
+       "        218, 221, 222, 223, 224, 226, 227, 228, 229, 231, 234, 235, 236,\n",
+       "        237, 238, 240, 244, 245, 246, 250, 251, 254, 255, 256, 257, 262,\n",
+       "        263, 265, 266, 267, 268, 269, 271, 274, 275, 276, 278, 279, 284,\n",
+       "        285, 287, 289, 290, 291, 292, 293, 294, 295, 296, 297, 299, 300,\n",
+       "        301, 302, 303, 304, 309, 311, 312, 315, 316, 317, 318, 319, 321,\n",
+       "        322, 323, 328, 329, 330, 331, 332, 334, 340, 343, 344, 347, 349,\n",
+       "        350, 351, 352, 353, 354, 355, 356, 357, 358, 361, 363, 365, 367,\n",
+       "        369, 372, 373, 374, 375, 378, 379, 380, 381, 382, 383, 384, 385,\n",
+       "        386, 388, 389, 390, 392, 394, 395, 396, 397, 398, 399, 400, 401,\n",
+       "        402, 404, 406, 407, 408, 409, 410, 411, 412, 414, 415, 416, 418,\n",
+       "        419, 420, 421, 425, 426, 429, 432, 434, 435, 436, 437, 438, 441,\n",
+       "        442, 443, 444, 450, 452, 453]),)"
       ]
      },
      "execution_count": 27,
@@ -520,6 +527,57 @@
     "(np.where(testpredseries == 1))"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Export model to ONNX"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tokenizer = SubwordTokenizer(\"./resources/bert-base-uncased-hash.txt\", do_lower_case=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tokenizer_output = tokenizer(dflogs[\"log\"][0:3],\n",
+    "                                max_length=128,\n",
+    "                                max_num_rows=3,\n",
+    "                                truncation=True,\n",
+    "                                add_special_tokens=True,\n",
+    "                                return_tensors=\"pt\")\n",
+    "\n",
+    "sample_model_input = (tokenizer_output[\"input_ids\"], tokenizer_output[\"attention_mask\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "torch.onnx.export(seq_classifier._model.module,              \n",
+    "                  sample_model_input,               \n",
+    "                  \"model.onnx\",                                      # where to save the model\n",
+    "                  export_params=True,                                # store the trained parameter weights inside the model file\n",
+    "                  opset_version=10,                                  # the ONNX version to export the model to\n",
+    "                  do_constant_folding=True,                          # whether to execute constant folding for optimization\n",
+    "                  input_names = ['input_ids','attention_mask'],      # the model's input names\n",
+    "                  output_names = ['output'],                         # the model's output names\n",
+    "                  dynamic_axes={'input_ids' : {0 : 'batch_size'},    # variable length axes\n",
+    "                                'attention_mask': {0: 'batch_size'}, \n",
+    "                                'output' : {0 : 'batch_size'}})"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -567,7 +625,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.13"
+   "version": "3.8.15"
   }
  },
  "nbformat": 4,
diff --git a/models/training-tuning-scripts/sid-models/sid-minibert-20211021-script.py b/models/training-tuning-scripts/sid-models/sid-minibert-20230424-script.py
similarity index 96%
rename from models/training-tuning-scripts/sid-models/sid-minibert-20211021-script.py
rename to models/training-tuning-scripts/sid-models/sid-minibert-20230424-script.py
index 7ebf5a9c93..e283bd40f0 100644
--- a/models/training-tuning-scripts/sid-models/sid-minibert-20211021-script.py
+++ b/models/training-tuning-scripts/sid-models/sid-minibert-20230424-script.py
@@ -13,19 +13,19 @@
 # limitations under the License.
 """
 Example Usage:
-python sid-minibert-20210614-script.py \
-       --training-data /datasets/training-data/sid-sample-training-data.csv \
+python sid-minibert-20230424-script.py \
+       --training-data ../../datasets/training-data/sid-sample-training-data.csv \
        --model-dir google/bert_uncased_L-4_H-256_A-4 \
-       --tokenizer-hash-filepath /resources/bert-base-uncased-hash.txt
-       --output-file /trained_models/model.pth
+       --tokenizer-hash-filepath /resources/bert-base-uncased-hash.txt \
+       --output-file sid-minibert-model.pt
 """
 
 import argparse
-
-import torch
 from sklearn.metrics import accuracy_score
 from sklearn.metrics import f1_score
 from sklearn.metrics import multilabel_confusion_matrix
+
+import torch
 from torch.nn import BCEWithLogitsLoss
 from torch.utils.data import DataLoader
 from torch.utils.data import TensorDataset
@@ -62,9 +62,9 @@ def data_preprocessing(training_data):
 
     cased_tokenizer = SubwordTokenizer("resources/bert-base-uncased-hash.txt", do_lower_case=True)
 
-    tokenizer_output = cased_tokenizer(df.text,
+    tokenizer_output = cased_tokenizer(df.data,
                                        max_length=256,
-                                       max_num_rows=len(df.text),
+                                       max_num_rows=len(df.data),
                                        padding='max_length',
                                        return_tensors='pt',
                                        truncation=True,
diff --git a/models/training-tuning-scripts/sid-models/sid-minibert-20211021.ipynb b/models/training-tuning-scripts/sid-models/sid-minibert-20230424.ipynb
similarity index 82%
rename from models/training-tuning-scripts/sid-models/sid-minibert-20211021.ipynb
rename to models/training-tuning-scripts/sid-models/sid-minibert-20230424.ipynb
index 5bf632bdf0..a5564de42b 100644
--- a/models/training-tuning-scripts/sid-models/sid-minibert-20211021.ipynb
+++ b/models/training-tuning-scripts/sid-models/sid-minibert-20230424.ipynb
@@ -63,7 +63,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "df = cudf.read_csv(\"../datasets/training-data/sid-sample-training-data.csv\")"
+    "df = cudf.read_csv(\"../../datasets/training-data/sid-sample-training-data.csv\")"
    ]
   },
   {
@@ -224,7 +224,7 @@
     "# load the following model for mini-bert from huggingface\n",
     "# model = AutoModelForSequenceClassification.from_pretrained(\"google/bert_uncased_L-4_H-256_A-4\", num_labels=num_labels)\n",
     "\n",
-    "model = torch.load('repo_model/sid-minibert-20211021.pth')"
+    "model = torch.load('../../sid-models/sid-minibert-20230424.pt')"
    ]
   },
   {
@@ -266,7 +266,16 @@
    "execution_count": 13,
    "id": "educational-channel",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/opt/conda/envs/morpheus/lib/python3.8/site-packages/transformers/optimization.py:391: FutureWarning: This implementation of AdamW is deprecated and will be removed in a future version. Use the PyTorch implementation torch.optim.AdamW instead, or set `no_deprecation_warning=True` to disable this warning\n",
+      "  warnings.warn(\n"
+     ]
+    }
+   ],
    "source": [
     "# using hyperparameters recommended in orginial BERT paper\n",
     "# the optimizer allows us to apply different hyperpameters for specific parameter groups\n",
@@ -293,14 +302,14 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Epoch: 100%|██████████| 1/1 [00:24<00:00, 24.37s/it]"
+      "Epoch: 100%|██████████| 1/1 [00:02<00:00,  2.61s/it]"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Train loss: 0.0006268636239110492\n"
+      "Train loss: 0.000367460027046036\n"
      ]
     },
     {
@@ -373,8 +382,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "F1 Macro Validation Accuracy:  99.87012987012986\n",
-      "Flat Validation Accuracy:  99.75\n"
+      "F1 Macro Validation Accuracy:  100.0\n",
+      "Flat Validation Accuracy:  100.0\n"
      ]
     }
    ],
@@ -427,32 +436,32 @@
       "[[370   0]\n",
       " [  0  30]]\n",
       "si_bank_acct\n",
-      "[[354   0]\n",
-      " [  0  46]]\n",
+      "[[358   0]\n",
+      " [  0  42]]\n",
       "si_credit_card\n",
-      "[[357   0]\n",
-      " [  0  43]]\n",
+      "[[363   0]\n",
+      " [  0  37]]\n",
       "si_email\n",
-      "[[362   0]\n",
-      " [  0  38]]\n",
+      "[[369   0]\n",
+      " [  0  31]]\n",
       "si_govt_id\n",
-      "[[361   0]\n",
-      " [  0  39]]\n",
-      "si_name\n",
-      "[[361   1]\n",
-      " [  0  38]]\n",
-      "si_password\n",
       "[[357   0]\n",
       " [  0  43]]\n",
+      "si_name\n",
+      "[[369   0]\n",
+      " [  0  31]]\n",
+      "si_password\n",
+      "[[358   0]\n",
+      " [  0  42]]\n",
       "si_phone_num\n",
-      "[[355   0]\n",
-      " [  0  45]]\n",
+      "[[368   0]\n",
+      " [  0  32]]\n",
       "si_secret_keys\n",
-      "[[365   0]\n",
-      " [  0  35]]\n",
+      "[[361   0]\n",
+      " [  0  39]]\n",
       "si_user\n",
-      "[[365   0]\n",
-      " [  0  35]]\n"
+      "[[361   0]\n",
+      " [  0  39]]\n"
      ]
     }
    ],
@@ -485,6 +494,55 @@
     "# torch.save(model, output_file)   "
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "96d4dc3b-54a4-4ca8-8a40-bb7dca765180",
+   "metadata": {},
+   "source": [
+    "## Export Model to ONNX"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "96f92112-cf40-4b1c-b796-b196ab9f3928",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "tokenizer_output = bert_uncased_tokenizer(df[\"data\"][0:3],\n",
+    "                                max_length=256,\n",
+    "                                max_num_rows=3,\n",
+    "                                truncation=True,\n",
+    "                                add_special_tokens=True,\n",
+    "                                return_tensors=\"pt\")\n",
+    "\n",
+    "sample_model_input = (tokenizer_output[\"input_ids\"], tokenizer_output[\"attention_mask\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "beef0eab-e852-4fb1-8020-7fc02d475c1e",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "torch.onnx.export(model,              \n",
+    "                  sample_model_input,               \n",
+    "                  \"model.onnx\",                                      # where to save the model\n",
+    "                  export_params=True,                                # store the trained parameter weights inside the model file\n",
+    "                  opset_version=10,                                  # the ONNX version to export the model to\n",
+    "                  do_constant_folding=True,                          # whether to execute constant folding for optimization\n",
+    "                  input_names = ['input_ids','attention_mask'],      # the model's input names\n",
+    "                  output_names = ['output'],                         # the model's output names\n",
+    "                  dynamic_axes={'input_ids' : {0 : 'batch_size'},    # variable length axes\n",
+    "                                'attention_mask': {0: 'batch_size'}, \n",
+    "                                'output' : {0 : 'batch_size'}})"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "ideal-community",
@@ -498,7 +556,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -512,7 +570,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.10"
+   "version": "3.8.15"
   }
  },
  "nbformat": 4,
diff --git a/models/triton-model-repo/phishing-bert-onnx/1/model.onnx b/models/triton-model-repo/phishing-bert-onnx/1/model.onnx
index a3aacf0265..164a725392 120000
--- a/models/triton-model-repo/phishing-bert-onnx/1/model.onnx
+++ b/models/triton-model-repo/phishing-bert-onnx/1/model.onnx
@@ -1 +1 @@
-../../../phishing-models/phishing-bert-20221115.onnx
\ No newline at end of file
+../../../phishing-models/phishing-bert-20230421.onnx
\ No newline at end of file
diff --git a/models/triton-model-repo/sid-minibert-onnx/1/model.onnx b/models/triton-model-repo/sid-minibert-onnx/1/model.onnx
index 7340667742..b46b5afbc1 120000
--- a/models/triton-model-repo/sid-minibert-onnx/1/model.onnx
+++ b/models/triton-model-repo/sid-minibert-onnx/1/model.onnx
@@ -1 +1 @@
-../../../sid-models/sid-minibert-20211021.onnx
\ No newline at end of file
+../../../sid-models/sid-minibert-20230424.onnx
\ No newline at end of file