Upload tokenizer
Browse files- added_tokens.json +26 -0
- merges.txt +0 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +10 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
" ": 64000,
|
| 3 |
+
" ": 64001,
|
| 4 |
+
" ": 64002,
|
| 5 |
+
" ": 64003,
|
| 6 |
+
" ": 64004,
|
| 7 |
+
" ": 64005,
|
| 8 |
+
" ": 64006,
|
| 9 |
+
" ": 64007,
|
| 10 |
+
" ": 64008,
|
| 11 |
+
" ": 64009,
|
| 12 |
+
" ": 64010,
|
| 13 |
+
" ": 64011,
|
| 14 |
+
" ": 64012,
|
| 15 |
+
" ": 64013,
|
| 16 |
+
" ": 64014,
|
| 17 |
+
" ": 64015,
|
| 18 |
+
" ": 64016,
|
| 19 |
+
" ": 64017,
|
| 20 |
+
" ": 64018,
|
| 21 |
+
" ": 64019,
|
| 22 |
+
" ": 64020,
|
| 23 |
+
" ": 64021,
|
| 24 |
+
" ": 64022,
|
| 25 |
+
" ": 64023
|
| 26 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "<pad>",
|
| 5 |
+
"unk_token": "<unk>"
|
| 6 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
+
"pad_token": "<pad>",
|
| 8 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 9 |
+
"unk_token": "<unk>"
|
| 10 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|