Upload tokenizer
Browse files- merges.txt +0 -0
- tokenizer.json +0 -0
- tokenizer_config.json +2 -2
- vocab.json +0 -0
merges.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -4,7 +4,7 @@
|
|
| 4 |
"0": {
|
| 5 |
"content": "<|endoftext|>",
|
| 6 |
"lstrip": false,
|
| 7 |
-
"normalized":
|
| 8 |
"rstrip": false,
|
| 9 |
"single_word": false,
|
| 10 |
"special": true
|
|
@@ -13,7 +13,7 @@
|
|
| 13 |
"bos_token": "<|endoftext|>",
|
| 14 |
"clean_up_tokenization_spaces": true,
|
| 15 |
"eos_token": "<|endoftext|>",
|
| 16 |
-
"model_max_length":
|
| 17 |
"tokenizer_class": "GPT2Tokenizer",
|
| 18 |
"unk_token": "<|endoftext|>"
|
| 19 |
}
|
|
|
|
| 4 |
"0": {
|
| 5 |
"content": "<|endoftext|>",
|
| 6 |
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
"rstrip": false,
|
| 9 |
"single_word": false,
|
| 10 |
"special": true
|
|
|
|
| 13 |
"bos_token": "<|endoftext|>",
|
| 14 |
"clean_up_tokenization_spaces": true,
|
| 15 |
"eos_token": "<|endoftext|>",
|
| 16 |
+
"model_max_length": 1024,
|
| 17 |
"tokenizer_class": "GPT2Tokenizer",
|
| 18 |
"unk_token": "<|endoftext|>"
|
| 19 |
}
|
vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|