rebase
Browse files- added_tokens.json +0 -40
- merges.txt +0 -0
- special_tokens_map.json +0 -6
- tokenizer.json +0 -0
- tokenizer_config.json +0 -10
- vocab.json +0 -0
added_tokens.json
DELETED
|
@@ -1,40 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"\t\t": 50294,
|
| 3 |
-
"\t\t\t": 50293,
|
| 4 |
-
"\t\t\t\t": 50292,
|
| 5 |
-
"\t\t\t\t\t": 50291,
|
| 6 |
-
"\t\t\t\t\t\t": 50290,
|
| 7 |
-
"\t\t\t\t\t\t\t": 50289,
|
| 8 |
-
"\t\t\t\t\t\t\t\t": 50288,
|
| 9 |
-
"\t\t\t\t\t\t\t\t\t": 50287,
|
| 10 |
-
" ": 50286,
|
| 11 |
-
" ": 50285,
|
| 12 |
-
" ": 50284,
|
| 13 |
-
" ": 50283,
|
| 14 |
-
" ": 50282,
|
| 15 |
-
" ": 50281,
|
| 16 |
-
" ": 50280,
|
| 17 |
-
" ": 50279,
|
| 18 |
-
" ": 50278,
|
| 19 |
-
" ": 50277,
|
| 20 |
-
" ": 50276,
|
| 21 |
-
" ": 50275,
|
| 22 |
-
" ": 50274,
|
| 23 |
-
" ": 50273,
|
| 24 |
-
" ": 50272,
|
| 25 |
-
" ": 50271,
|
| 26 |
-
" ": 50270,
|
| 27 |
-
" ": 50269,
|
| 28 |
-
" ": 50268,
|
| 29 |
-
" ": 50267,
|
| 30 |
-
" ": 50266,
|
| 31 |
-
" ": 50265,
|
| 32 |
-
" ": 50264,
|
| 33 |
-
" ": 50263,
|
| 34 |
-
" ": 50262,
|
| 35 |
-
" ": 50261,
|
| 36 |
-
" ": 50260,
|
| 37 |
-
" ": 50259,
|
| 38 |
-
" ": 50258,
|
| 39 |
-
" ": 50257
|
| 40 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
merges.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
DELETED
|
@@ -1,6 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"bos_token": "<|endoftext|>",
|
| 3 |
-
"eos_token": "<|endoftext|>",
|
| 4 |
-
"pad_token": 50256,
|
| 5 |
-
"unk_token": "<|endoftext|>"
|
| 6 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
DELETED
|
@@ -1,10 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
-
"bos_token": "<|endoftext|>",
|
| 4 |
-
"eos_token": "<|endoftext|>",
|
| 5 |
-
"model_max_length": 1024,
|
| 6 |
-
"name_or_path": "gpt2",
|
| 7 |
-
"special_tokens_map_file": null,
|
| 8 |
-
"tokenizer_class": "GPT2Tokenizer",
|
| 9 |
-
"unk_token": "<|endoftext|>"
|
| 10 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
vocab.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|