Files
gpt2-117m-bahasa-cased-v2/tokenizer_config.json
ModelHub XC 5b97ad7109 初始化项目,由ModelHub XC社区提供模型
Model: mesolitica/gpt2-117m-bahasa-cased-v2
Source: Original Platform
2026-08-13 12:27:13 +08:00

35 lines
760 B
JSON

{
"add_bos_token": false,
"add_prefix_space": false,
"bos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"do_lower_case": false,
"eos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"errors": "replace",
"name_or_path": "./malay-cased-gpt2",
"pad_token": null,
"special_tokens_map_file": null,
"tokenizer_class": "GPT2Tokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}