Commit
•
a24145b
1
Parent(s):
a78f23e
Upload tokenizer
Browse files- merges.txt +0 -0
- special_tokens_map.json +0 -1
- tokenizer.json +0 -0
- tokenizer_config.json +1 -1
- vocab.json +0 -0
merges.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
CHANGED
|
@@ -13,7 +13,6 @@
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
-
"pad_token": "<|endoftext|>",
|
| 17 |
"unk_token": {
|
| 18 |
"content": "<|endoftext|>",
|
| 19 |
"lstrip": false,
|
|
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
|
|
|
| 16 |
"unk_token": {
|
| 17 |
"content": "<|endoftext|>",
|
| 18 |
"lstrip": false,
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -16,7 +16,7 @@
|
|
| 16 |
"eos_token": "<|endoftext|>",
|
| 17 |
"errors": "replace",
|
| 18 |
"model_max_length": 1024,
|
| 19 |
-
"pad_token":
|
| 20 |
"tokenizer_class": "GPT2Tokenizer",
|
| 21 |
"unk_token": "<|endoftext|>"
|
| 22 |
}
|
|
|
|
| 16 |
"eos_token": "<|endoftext|>",
|
| 17 |
"errors": "replace",
|
| 18 |
"model_max_length": 1024,
|
| 19 |
+
"pad_token": null,
|
| 20 |
"tokenizer_class": "GPT2Tokenizer",
|
| 21 |
"unk_token": "<|endoftext|>"
|
| 22 |
}
|
vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|