Publish seven-label toxicity classifier

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,197 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or Object
+      form, made available under the License, as indicated by a copyright
+      notice that is included in or attached to the work (an example is
+      provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the Work
+      or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You meet
+      the following conditions:
+
+      (a) You must give any other recipients of the Work or Derivative Works
+          a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works that
+          You distribute, all copyright, patent, trademark, and attribution
+          notices from the Source form of the Work, excluding those notices
+          that do not pertain to any part of the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -0,0 +1,135 @@
+---
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-classification
+language:
+- en
+base_model: datalama/mmBERT-small
+datasets:
+- google/civil_comments
+- Heliosoph/Jigsaw-Toxic-Comments
+tags:
+- toxicity
+- content-moderation
+- multi-label-classification
+- modernbert
+- multilingual
+metrics:
+- roc_auc
+- f1
+---
+
+# Multilabel Toxic Comment Classifier
+
+This model produces seven independent moderation scores for English comments:
+`toxicity`, `severe_toxicity`, `obscene`, `threat`, `insult`,
+`identity_attack`, and `sexual_explicit`. It is a fine-tune of
+[`datalama/mmBERT-small`](https://huggingface.co/datalama/mmBERT-small), a
+multilingual ModernBERT/mmBERT base model.
+
+This is a multi-label classifier, not a mutually exclusive class classifier.
+Every output is a sigmoid score and a comment can score highly on multiple
+dimensions. `toxicity` is trained as its own target; it is not computed as an
+OR of the other labels.
+
+## Intended use
+
+Use the scores as one input to a broader content-moderation workflow. Choose
+and validate a separate decision threshold for every label and review decisions
+in context. Do not use this model as the sole basis for high-impact decisions
+about people.
+
+## Usage
+
+```python
+import torch
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+
+model_id = "wagesj45/multilabel-toxic-comment-classifier"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForSequenceClassification.from_pretrained(model_id).eval()
+
+inputs = tokenizer(
+    "Your text to score goes here.",
+    return_tensors="pt",
+    truncation=True,
+    max_length=256,
+)
+with torch.no_grad():
+    scores = torch.sigmoid(model(**inputs).logits[0]).tolist()
+
+result = {
+    model.config.id2label.get(index, model.config.id2label.get(str(index))): score
+    for index, score in enumerate(scores)
+}
+print(result)
+```
+
+The model's saved label order is:
+
+1. `toxicity`
+2. `severe_toxicity`
+3. `obscene`
+4. `threat`
+5. `insult`
+6. `identity_attack`
+7. `sexual_explicit`
+
+Scores are model outputs, not calibrated probabilities. Thresholds should be
+chosen for the target application and monitored after deployment.
+
+## Training
+
+The model was fine-tuned with `transformers` on
+[`google/civil_comments`](https://huggingface.co/datasets/google/civil_comments)
+and
+[`Heliosoph/Jigsaw-Toxic-Comments`](https://huggingface.co/datasets/Heliosoph/Jigsaw-Toxic-Comments).
+Civil Comments supplies all seven continuous annotation-fraction targets.
+Jigsaw supplies binary targets for the first six dimensions; its unavailable
+`sexual_explicit` label is masked from loss rather than treated as negative.
+
+The combined corpus was shuffled and split deterministically 90/10 with seed
+42. Training used three epochs, a learning rate of `2e-5`, batch sizes 16/32,
+weight decay `0.01`, and a 256-token input limit. The exported weights are the
+best checkpoint, selected by validation macro ROC-AUC at epoch 2.
+
+## Evaluation
+
+Evaluation used the held-out split described above. Metrics threshold soft
+annotation targets at 0.5 for F1; ROC-AUC uses the continuous model scores.
+
+| Label | ROC-AUC | F1 at 0.5 |
+| --- | ---: | ---: |
+| toxicity | 0.9744 | 0.6992 |
+| severe_toxicity | 0.9991 | 0.4085 |
+| obscene | 0.9936 | 0.7141 |
+| threat | 0.9894 | 0.4847 |
+| insult | 0.9802 | 0.6959 |
+| identity_attack | 0.9873 | 0.3902 |
+| sexual_explicit | 0.9967 | 0.5075 |
+| **Macro average** | **0.9887** | **0.5571** |
+
+These results are not a measure of performance on arbitrary production
+comments or languages outside the evaluation data.
+
+## Limitations and risks
+
+- The training and evaluation comments are English. The multilingual base model
+  does not establish validated performance for non-English text.
+- Toxicity labels are subjective and noisy, and data may carry historical or
+  cultural biases.
+- Profanity, reclaimed language, identity terms, quotations, discussions of
+  abuse, and strongly worded criticism can cause false positives.
+- The model can miss implicit, coded, contextual, or adversarially written
+  abuse.
+- Use application-specific thresholds, appeals, human review, and monitoring
+  for real moderation systems.
+
+## Licensing and provenance
+
+The fine-tuned model artifacts in this repository are released under the
+[Apache License 2.0](LICENSE). The listed base model and both listed Hugging
+Face training datasets use Apache-2.0 and CC0-1.0 licensing, respectively;
+refer to their dataset cards for source attribution and terms. This repository
+does not redistribute training rows. Any future hard-negative data must be
+documented with its source and license before use in a released model.

config.json

@@ -0,0 +1,98 @@
+{
+  "architectures": [
+    "ModernBertForSequenceClassification"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "mean",
+  "cls_token_id": 1,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "dtype": "float32",
+  "embedding_dropout": 0.0,
+  "eos_token_id": 1,
+  "global_attn_every_n_layers": 3,
+  "gradient_checkpointing": false,
+  "hidden_activation": "gelu",
+  "hidden_size": 384,
+  "id2label": {
+    "0": "toxicity",
+    "1": "severe_toxicity",
+    "2": "obscene",
+    "3": "threat",
+    "4": "insult",
+    "5": "identity_attack",
+    "6": "sexual_explicit"
+  },
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "label2id": {
+    "identity_attack": 5,
+    "insult": 4,
+    "obscene": 2,
+    "severe_toxicity": 1,
+    "sexual_explicit": 6,
+    "threat": 3,
+    "toxicity": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "layer_types": [
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "local_attention": 128,
+  "mask_token_id": 4,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 6,
+  "num_hidden_layers": 22,
+  "pad_token_id": 0,
+  "position_embedding_type": "sans_pos",
+  "problem_type": "multi_label_classification",
+  "rope_parameters": {
+    "full_attention": {
+      "rope_theta": 160000.0,
+      "rope_type": "default"
+    },
+    "sliding_attention": {
+      "rope_theta": 160000.0,
+      "rope_type": "default"
+    }
+  },
+  "sep_token_id": 1,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.15.1",
+  "use_cache": false,
+  "vocab_size": 256000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb551fc0e8a58721d456fc3b2c2d57e33c2666f66e2b90806dbc153248bef51c
+size 562591100

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4379fe7f4a7af10b1ac15ffc8ae90f446f92082393699e9dd54b8c3b5ec0abad
+size 34363286

tokenizer_config.json

@@ -0,0 +1,25 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<bos>",
+  "eos_token": "<eos>",
+  "extra_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sep_token": "<eos>",
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>"
+}