初始化项目,由ModelHub XC社区提供模型

Model: kornwtp/ConGen-simcse-model-roberta-base-thai
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-10-01 19:51:55 +08:00
commit 2bb93a5df4
9 changed files with 135 additions and 0 deletions

1
tokenizer_config.json Normal file
View File

@@ -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", "<_>"], "special_tokens_map_file": null, "name_or_path": "../../seeder-sbert/pretrain-models/wangchanberta-base-att-spm-uncased", "sp_model_kwargs": {}, "tokenizer_class": "CamembertTokenizer"}