Upload tokenizer
Browse files- special_tokens_map.json +0 -1
- tokenizer.json +0 -0
- tokenizer_config.json +1 -5
special_tokens_map.json
CHANGED
|
@@ -13,7 +13,6 @@
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
-
"pad_token": "</s>",
|
| 17 |
"unk_token": {
|
| 18 |
"content": "<unk>",
|
| 19 |
"lstrip": false,
|
|
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
|
|
|
| 16 |
"unk_token": {
|
| 17 |
"content": "<unk>",
|
| 18 |
"lstrip": false,
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -30,15 +30,11 @@
|
|
| 30 |
"clean_up_tokenization_spaces": false,
|
| 31 |
"eos_token": "</s>",
|
| 32 |
"legacy": false,
|
| 33 |
-
"max_length": 128,
|
| 34 |
"model_max_length": 1000000000000000019884624838656,
|
| 35 |
-
"pad_token":
|
| 36 |
"padding_side": "right",
|
| 37 |
"sp_model_kwargs": {},
|
| 38 |
-
"stride": 0,
|
| 39 |
"tokenizer_class": "LlamaTokenizer",
|
| 40 |
-
"truncation_side": "right",
|
| 41 |
-
"truncation_strategy": "longest_first",
|
| 42 |
"unk_token": "<unk>",
|
| 43 |
"use_default_system_prompt": false
|
| 44 |
}
|
|
|
|
| 30 |
"clean_up_tokenization_spaces": false,
|
| 31 |
"eos_token": "</s>",
|
| 32 |
"legacy": false,
|
|
|
|
| 33 |
"model_max_length": 1000000000000000019884624838656,
|
| 34 |
+
"pad_token": null,
|
| 35 |
"padding_side": "right",
|
| 36 |
"sp_model_kwargs": {},
|
|
|
|
| 37 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
|
|
|
| 38 |
"unk_token": "<unk>",
|
| 39 |
"use_default_system_prompt": false
|
| 40 |
}
|