# unbiased-toxic-roberta by Unitary: Open-Weight Model Source: https://savrn.com/models/unbiased-toxic-roberta Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Model Card By Unitary, published under apache-2.0, revision 36295dd80b42. ** Disclaimer:** The huggingface models currently give different results to the detoxify library (see issue [here](https://github.com/unitaryai/detoxify/issues/15)). For the most up to date models we recommend using the models from https://github.com/unitaryai/detoxify # Detoxify ## Toxic Comment Classification with Pytorch Lightning and Transformers ![CI testing](https://github.com/unitaryai/detoxify/workflows/CI%20testing/badge.svg) ![Lint](https://github.com/unitaryai/detoxify/workflows/Lint/badge.svg) ### Description Trained models & code to predict toxic comments on 3 Jigsaw challenges: Toxic comment classification, Unintended Bias in Toxic comments, Multilingual toxic comment classification. Built by [Laura Hanu](https://laurahanu.github.io/) at [Unitary](https://www.unitary.ai/), where we are working to stop harmful content online by interpreting visual content in context. Dependencies: - For inference: - Transformers - Pytorch lightning - For training will also need: - Kaggle API (to download data) [Read the full model card (1,244 words)](https://savrn.com/models/unbiased-toxic-roberta/card) ## Configuration Architecture RobertaForSequenceClassification Context length (tokens) 514 Layers 12 Hidden size 768 Feed-forward size 3,072 Attention heads 12 Vocabulary size 50,265 Model type roberta ## Identity and Version Repository unitary/unbiased-toxic-roberta Publisher Unitary Task Text classification Modality Text Library transformers Parameters Not stated by the source Languages jax Revision 36295dd80b422dc49f40052021430dae76241adc First published 2022-03-02 Last updated 2023-08-18 ## Files and Weights 9 files, 998.7 MB in total. The weights are 2 files totalling 997.4 MB in bin, msgpack. Weights2 files · 997.4 MB Configuration2 files · 2.2 KB Tokenizer3 files · 1.4 MB Documentation1 file · 11.1 KB Repository1 file · 391 B Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | flax_model.msgpack | Weights | 498.6 MB | 312c6b3df672 | | pytorch_model.bin | Weights | 498.7 MB | f1cfe8f98a22 | | config.json | Configuration | 1.4 KB | — | | special_tokens_map.json | Configuration | 772 B | — | | README.md | Documentation | 11.1 KB | — | | .gitattributes | Repository | 391 B | — | | merges.txt | Tokenizer | 456.3 KB | — | | tokenizer_config.json | Tokenizer | 997 B | — | | vocab.json | Tokenizer | 898.8 KB | — | ## License and Download License apache-2.0 Access Open weights, no gate Download size 997.4 MB [Download from Unitary](https://huggingface.co/unitary/unbiased-toxic-roberta) Released by Unitary through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Built From - Described by arXiv:1703.04009 - Described by arXiv:1905.12516 ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 997.4 MB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Built on This Model - Quantized from[unbiased-toxic-roberta-onnx](https://savrn.com/models/unbiased-toxic-roberta-onnx) - Derived from[unbiased-toxic-roberta-onnx](https://savrn.com/models/unbiased-toxic-roberta-onnx) ## Questions About unbiased-toxic-roberta ### Can I use unbiased-toxic-roberta commercially? Yes. unbiased-toxic-roberta is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors. ### What is unbiased-toxic-roberta's context length? 514 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Text classification ### [finbert](https://savrn.com/models/finbert) [Prosus AI](https://savrn.com/model-publishers/prosusai) FinBERT is a pre-trained NLP model to analyze sentiment of financial text. It is built by further training the BERT language model in the finance domain, using a large financial corpus and thereby fine-tuning it for financial sentiment classification. Financial PhraseBank by Malo et al. (2014) is used for fine-tuning. For more details, please see the paper FinBERT: Financial Sentiment Analysis with Pre-trained Language Models and our related blog post on Medium. The model will give softmax outputs for three labels: positive, negative or neutral. About Prosus Prosus is a global consumer internet group and one of the largest technology investors in the world. Operating and investing globally… Open weights 512 tokens transformers [View model](https://savrn.com/models/finbert) Model · Text classification ### [twitter-roberta-base-sentiment-latest](https://savrn.com/models/twitter-roberta-base-sentiment-latest) [Cardiff NLP](https://savrn.com/model-publishers/cardiffnlp) This is a RoBERTa-base model trained on ~124M tweets from January 2018 to December 2021, and finetuned for sentiment analysis with the TweetEval benchmark. The original Twitter-based RoBERTa model can be found here and the original reference paper is TweetEval. This model is suitable for English. 0 -> Negative; 1 -> Neutral; 2 -> Positive This sentiment analysis model has been integrated into TweetNLP. You can access the demo here. Open weights cc-by-4.0 514 tokens transformers [View model](https://savrn.com/models/twitter-roberta-base-sentiment-latest) Model · Text classification ### [finbert-tone](https://savrn.com/models/finbert-tone) [Yi](https://savrn.com/model-publishers/yiyanghkust) FinBERT is a BERT model pre-trained on financial communication text. The purpose is to enhance financial NLP research and practice. It is trained on the following three financial communication corpus. The total corpora size is 4.9B tokens. More technical details on FinBERT: Click Link This released finbert-tone model is the FinBERT model fine-tuned on 10,000 manually annotated (positive, negative, neutral) sentences from analyst reports. This model achieves superior performance on financial tone analysis task. If you are simply interested in using FinBERT for financial tone analysis, give it a try. If you use the model in your academic work, please cite the following paper: Huang, Allen H.… Open weights 512 tokens transformers [View model](https://savrn.com/models/finbert-tone) Model · Text classification ### [ms-marco-MiniLM-L-6-v2](https://savrn.com/models/ms-marco-minilm-l-6-v2) [Joshua](https://savrn.com/model-publishers/xenova) https://huggingface.co/cross-encoder/ms-marco-MiniLM-L-6-v2 with ONNX weights to be compatible with Transformers.js. If you haven't already, you can install the Transformers.js JavaScript library from NPM using: Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx). Open weights 512 tokens transformers.js [View model](https://savrn.com/models/ms-marco-minilm-l-6-v2) Model · Text classification ### [twitter-xlm-roberta-base-sentiment](https://savrn.com/models/twitter-xlm-roberta-base-sentiment) [Cardiff NLP](https://savrn.com/model-publishers/cardiffnlp) This is a multilingual XLM-roBERTa-base model trained on ~198M tweets and finetuned for sentiment analysis. The sentiment fine-tuning was done on 8 languages (Ar, En, Fr, De, Hi, It, Sp, Pt) but it can be used for more languages (see paper for details). This model has been integrated into the TweetNLP library. Open weights 514 tokens transformers [View model](https://savrn.com/models/twitter-xlm-roberta-base-sentiment) Model · Text classification ### [emotion-english-distilroberta-base](https://savrn.com/models/emotion-english-distilroberta-base) [Hartmann](https://savrn.com/model-publishers/j-hartmann) With this model, you can classify emotions in English text data. The model was trained on 6 diverse datasets (see Appendix below) and predicts Ekman's 6 basic emotions, plus a neutral class: 1) anger 2) disgust 3) fear 4) joy 5) neutral 6) sadness 7) surprise The model is a fine-tuned checkpoint of DistilRoBERTa-base. For a 'non-distilled' emotion model, please refer to the model card of the RoBERTa-large version. a) Run emotion model with 3 lines of code on single text example using Hugging Face's pipeline command on Google Colab: b) Run emotion model on multiple examples and full datasets (e.g.,.csv files) on Google Colab: Please reach out to jochen.hartmann@tum.de if you have any… Open weights 514 tokens transformers [View model](https://savrn.com/models/emotion-english-distilroberta-base) ## Unitary [All models and datasets](https://savrn.com/model-publishers/unitary) ## Versions - [36295dd80b42](https://savrn.com/models/unbiased-toxic-roberta/versions/36295dd80b42) · current 2026-10-09 ## Explore More - [All text classification models](https://savrn.com/models/tasks/text-classification) - [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-09. - [Hugging Face record](https://huggingface.co/unitary/unbiased-toxic-roberta) - [How the hub is built](https://savrn.com/model-hub/methodology)