microsoft/phi-2
microsoft/phi-2
1
0
Overview Code Discussions Pull Requests Wiki Activity

Upload tokenizer

Browse Source
This commit is contained in:
Gustavo de Rosa 2023-12-13 21:20:00 +00:00 committed by huggingface-web
parent fb2b71424e
commit 3fee3716b6
6 changed files with 151017 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

40
added_tokens.json Normal file
View File

@ -0,0 +1,40 @@
{
"\t\t": 50294,
"\t\t\t": 50293,
"\t\t\t\t": 50292,
"\t\t\t\t\t": 50291,
"\t\t\t\t\t\t": 50290,
"\t\t\t\t\t\t\t": 50289,
"\t\t\t\t\t\t\t\t": 50288,
"\t\t\t\t\t\t\t\t\t": 50287,
" ": 50286,
" ": 50285,
" ": 50284,
" ": 50283,
" ": 50282,
" ": 50281,
" ": 50280,
" ": 50279,
" ": 50278,
" ": 50277,
" ": 50276,
" ": 50275,
" ": 50274,
" ": 50273,
" ": 50272,
" ": 50271,
" ": 50270,
" ": 50269,
" ": 50268,
" ": 50267,
" ": 50266,
" ": 50265,
" ": 50264,
" ": 50263,
" ": 50262,
" ": 50261,
" ": 50260,
" ": 50259,
" ": 50258,
" ": 50257
}

50001
merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

5
special_tokens_map.json Normal file
View File

@ -0,0 +1,5 @@
{
"bos_token": "<|endoftext|>",
"eos_token": "<|endoftext|>",
"unk_token": "<|endoftext|>"
}

100647
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

323
tokenizer_config.json Normal file
View File

@ -0,0 +1,323 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"50256": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"50257": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50258": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50259": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50260": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50261": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50262": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50263": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50264": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50265": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50266": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50267": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50268": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50269": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50270": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50271": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50272": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50273": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50274": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50275": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50276": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50277": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50278": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50279": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50280": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50281": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50282": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50283": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50284": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50285": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50286": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50287": {
"content": "\t\t\t\t\t\t\t\t\t",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50288": {
"content": "\t\t\t\t\t\t\t\t",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50289": {
"content": "\t\t\t\t\t\t\t",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50290": {
"content": "\t\t\t\t\t\t",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50291": {
"content": "\t\t\t\t\t",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50292": {
"content": "\t\t\t\t",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50293": {
"content": "\t\t\t",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50294": {
"content": "\t\t",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
}
},
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"model_max_length": 2048,
"tokenizer_class": "CodeGenTokenizer",
"unk_token": "<|endoftext|>"
}

1
vocab.json Normal file
View File

File diff suppressed because one or more lines are too long