Upload tokenizer

This commit is contained in:
Jasper Kyle Catapang
2023-05-26 17:17:39 +00:00
committed by huggingface-web
parent fdd4c93ec6
commit 5022707b8f
5 changed files with 150436 additions and 0 deletions

50001
merges.txt Normal file

File diff suppressed because it is too large Load Diff

30
special_tokens_map.json Normal file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

100364
tokenizer.json Normal file

File diff suppressed because it is too large Load Diff

40
tokenizer_config.json Normal file
View File

@@ -0,0 +1,40 @@
{
"add_bos_token": true,
"add_prefix_space": false,
"bos_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": true,
"eos_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"errors": "replace",
"model_max_length": 1000000000000000019884624838656,
"pad_token": {
"__type": "AddedToken",
"content": "<pad>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"tokenizer_class": "GPT2Tokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

1
vocab.json Normal file

File diff suppressed because one or more lines are too long