| license: cc-by-nc-3.0 | |
| datasets: | |
| - FredZhang7/toxi-text-3M | |
| pipeline_tag: text-classification | |
| **I have decided to release the auto-moderation models all at once sometime in July. The curated datasets for training these models will be avaliable first.** | |
| <br> | |
| Finished training: 6/30/2023 | |
| Final Train & Validation Accuracy: 95-98% | |
| Large model (v2) will be avaliable for PyTorch | |
| Lightweight model and tokenizer (v1) will be avaliable for transformers.js | |
| <br> | |
| <br> | |
| Models tested: roberta, xlm-roberta, bert-tiny, bert-base-cased/uncased, bert-multilingual-cased/uncased, alberta-large-v2 | |
| Model chosen based on cost-efficiency and performance: bert-multilingual-cased |