Commit
•
aca371f
1
Parent(s):
d3d3703
Upload tokenizer
Browse files- special_tokens_map.json +0 -7
- tokenizer_config.json +0 -1
special_tokens_map.json
CHANGED
|
@@ -13,13 +13,6 @@
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
-
"pad_token": {
|
| 17 |
-
"content": "<|endoftext|>",
|
| 18 |
-
"lstrip": false,
|
| 19 |
-
"normalized": false,
|
| 20 |
-
"rstrip": false,
|
| 21 |
-
"single_word": false
|
| 22 |
-
},
|
| 23 |
"unk_token": {
|
| 24 |
"content": "<|endoftext|>",
|
| 25 |
"lstrip": false,
|
|
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
"unk_token": {
|
| 17 |
"content": "<|endoftext|>",
|
| 18 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -318,7 +318,6 @@
|
|
| 318 |
"clean_up_tokenization_spaces": true,
|
| 319 |
"eos_token": "<|endoftext|>",
|
| 320 |
"model_max_length": 2048,
|
| 321 |
-
"pad_token": "<|endoftext|>",
|
| 322 |
"tokenizer_class": "CodeGenTokenizer",
|
| 323 |
"unk_token": "<|endoftext|>"
|
| 324 |
}
|
|
|
|
| 318 |
"clean_up_tokenization_spaces": true,
|
| 319 |
"eos_token": "<|endoftext|>",
|
| 320 |
"model_max_length": 2048,
|
|
|
|
| 321 |
"tokenizer_class": "CodeGenTokenizer",
|
| 322 |
"unk_token": "<|endoftext|>"
|
| 323 |
}
|