Replace toxicity model with multi-label classifier

This commit is contained in:
Jordan Wages 2026-08-26 17:00:49 -05:00
commit 1568c787f8
24 changed files with 2581129 additions and 119717 deletions

View file

@ -1,15 +1,25 @@
{
"backend": "tokenizers",
"cls_token": "[CLS]",
"do_lower_case": false,
"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_max_length": 512,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
"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>"
}