Upload tokenizer
Browse files- tokenizer.json +9 -0
- tokenizer_config.json +2 -1
tokenizer.json
CHANGED
|
@@ -29,6 +29,15 @@
|
|
| 29 |
"rstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
}
|
| 33 |
],
|
| 34 |
"normalizer": null,
|
|
|
|
| 29 |
"rstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"special": true
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"id": 3,
|
| 35 |
+
"content": "[PAD]",
|
| 36 |
+
"single_word": false,
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"special": true
|
| 41 |
}
|
| 42 |
],
|
| 43 |
"normalizer": null,
|
tokenizer_config.json
CHANGED
|
@@ -2,9 +2,10 @@
|
|
| 2 |
"add_prefix_space": null,
|
| 3 |
"backend": "tokenizers",
|
| 4 |
"bos_token": "<s>",
|
| 5 |
-
"clean_up_tokenization_spaces":
|
| 6 |
"eos_token": "</s>",
|
| 7 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 8 |
"tokenizer_class": "LlamaTokenizer",
|
| 9 |
"unk_token": "<unk>",
|
| 10 |
"use_default_system_prompt": false
|
|
|
|
| 2 |
"add_prefix_space": null,
|
| 3 |
"backend": "tokenizers",
|
| 4 |
"bos_token": "<s>",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
"eos_token": "</s>",
|
| 7 |
"model_max_length": 1000000000000000019884624838656,
|
| 8 |
+
"pad_token": "[PAD]",
|
| 9 |
"tokenizer_class": "LlamaTokenizer",
|
| 10 |
"unk_token": "<unk>",
|
| 11 |
"use_default_system_prompt": false
|