diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..b267a7e --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1 @@ +{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "additional_special_tokens": ["<s>NOTUSED", "</s>NOTUSED"], "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "camembert-base"} \ No newline at end of file