Commit
•
af3d486
1
Parent(s):
b963ed4
Delete tokenizer
Browse files
tokenizer/tokenizer_merges.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer/tokenizer_special_tokens_map.json
DELETED
|
@@ -1,6 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"bos_token": "<|startoftext|>",
|
| 3 |
-
"eos_token": "<|endoftext|>",
|
| 4 |
-
"pad_token": "<|endoftext|>",
|
| 5 |
-
"unk_token": "<|endoftext|>"
|
| 6 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer/tokenizer_tokenizer_config.json
DELETED
|
@@ -1,33 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
-
"bos_token": {
|
| 4 |
-
"__type": "AddedToken",
|
| 5 |
-
"content": "<|startoftext|>",
|
| 6 |
-
"lstrip": false,
|
| 7 |
-
"normalized": true,
|
| 8 |
-
"rstrip": false,
|
| 9 |
-
"single_word": false
|
| 10 |
-
},
|
| 11 |
-
"clean_up_tokenization_spaces": true,
|
| 12 |
-
"do_lower_case": true,
|
| 13 |
-
"eos_token": {
|
| 14 |
-
"__type": "AddedToken",
|
| 15 |
-
"content": "<|endoftext|>",
|
| 16 |
-
"lstrip": false,
|
| 17 |
-
"normalized": true,
|
| 18 |
-
"rstrip": false,
|
| 19 |
-
"single_word": false
|
| 20 |
-
},
|
| 21 |
-
"errors": "replace",
|
| 22 |
-
"model_max_length": 77,
|
| 23 |
-
"pad_token": "<|endoftext|>",
|
| 24 |
-
"tokenizer_class": "CLIPTokenizer",
|
| 25 |
-
"unk_token": {
|
| 26 |
-
"__type": "AddedToken",
|
| 27 |
-
"content": "<|endoftext|>",
|
| 28 |
-
"lstrip": false,
|
| 29 |
-
"normalized": true,
|
| 30 |
-
"rstrip": false,
|
| 31 |
-
"single_word": false
|
| 32 |
-
}
|
| 33 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer/tokenizer_vocab.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|