Upload tokenizer
Browse files- special_tokens_map.json +7 -1
- tokenizer_config.json +4 -0
special_tokens_map.json
CHANGED
|
@@ -13,7 +13,13 @@
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
"unk_token": {
|
| 18 |
"content": "<unk>",
|
| 19 |
"lstrip": false,
|
|
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
"unk_token": {
|
| 24 |
"content": "<unk>",
|
| 25 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -70,8 +70,12 @@
|
|
| 70 |
"bos_token": "<s>",
|
| 71 |
"clean_up_tokenization_spaces": false,
|
| 72 |
"eos_token": "</s>",
|
|
|
|
| 73 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 74 |
"pad_token": "</s>",
|
|
|
|
|
|
|
| 75 |
"sp_model_kwargs": {},
|
| 76 |
"tokenizer_class": "LlamaTokenizer",
|
| 77 |
"unk_token": "<unk>",
|
|
|
|
| 70 |
"bos_token": "<s>",
|
| 71 |
"clean_up_tokenization_spaces": false,
|
| 72 |
"eos_token": "</s>",
|
| 73 |
+
"max_length": null,
|
| 74 |
"model_max_length": 1000000000000000019884624838656,
|
| 75 |
+
"pad_to_multiple_of": null,
|
| 76 |
"pad_token": "</s>",
|
| 77 |
+
"pad_token_type_id": 0,
|
| 78 |
+
"padding_side": "left",
|
| 79 |
"sp_model_kwargs": {},
|
| 80 |
"tokenizer_class": "LlamaTokenizer",
|
| 81 |
"unk_token": "<unk>",
|