Upload tokenizer
Browse files- special_tokens_map.json +1 -7
- tokenizer.json +0 -0
- tokenizer_config.json +0 -6
special_tokens_map.json
CHANGED
|
@@ -1,9 +1,3 @@
|
|
| 1 |
{
|
| 2 |
-
"eos_token":
|
| 3 |
-
"content": "<|endoftext|>",
|
| 4 |
-
"lstrip": false,
|
| 5 |
-
"normalized": false,
|
| 6 |
-
"rstrip": false,
|
| 7 |
-
"single_word": false
|
| 8 |
-
}
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"eos_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -9,12 +9,6 @@
|
|
| 9 |
"special": true
|
| 10 |
}
|
| 11 |
},
|
| 12 |
-
"auto_map": {
|
| 13 |
-
"AutoTokenizer": [
|
| 14 |
-
"tokenizer_utils.CryptGPTTokenizer",
|
| 15 |
-
null
|
| 16 |
-
]
|
| 17 |
-
},
|
| 18 |
"clean_up_tokenization_spaces": true,
|
| 19 |
"eos_token": "<|endoftext|>",
|
| 20 |
"max_length": 1024,
|
|
|
|
| 9 |
"special": true
|
| 10 |
}
|
| 11 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
"clean_up_tokenization_spaces": true,
|
| 13 |
"eos_token": "<|endoftext|>",
|
| 14 |
"max_length": 1024,
|