Upload tokenizer
Browse files- special_tokens_map.json +7 -0
- tokenizer.json +1 -0
- tokenizer_config.json +1 -1
special_tokens_map.json
CHANGED
|
@@ -13,6 +13,13 @@
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
"unk_token": {
|
| 17 |
"content": "<unk>",
|
| 18 |
"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.json
CHANGED
|
@@ -134,6 +134,7 @@
|
|
| 134 |
"end_of_word_suffix": null,
|
| 135 |
"fuse_unk": true,
|
| 136 |
"byte_fallback": true,
|
|
|
|
| 137 |
"vocab": {
|
| 138 |
"<unk>": 0,
|
| 139 |
"<s>": 1,
|
|
|
|
| 134 |
"end_of_word_suffix": null,
|
| 135 |
"fuse_unk": true,
|
| 136 |
"byte_fallback": true,
|
| 137 |
+
"ignore_merges": false,
|
| 138 |
"vocab": {
|
| 139 |
"<unk>": 0,
|
| 140 |
"<s>": 1,
|
tokenizer_config.json
CHANGED
|
@@ -32,7 +32,7 @@
|
|
| 32 |
"eos_token": "</s>",
|
| 33 |
"legacy": false,
|
| 34 |
"model_max_length": 1000000000000000019884624838656,
|
| 35 |
-
"pad_token":
|
| 36 |
"padding_side": "right",
|
| 37 |
"sp_model_kwargs": {},
|
| 38 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
| 32 |
"eos_token": "</s>",
|
| 33 |
"legacy": false,
|
| 34 |
"model_max_length": 1000000000000000019884624838656,
|
| 35 |
+
"pad_token": "</s>",
|
| 36 |
"padding_side": "right",
|
| 37 |
"sp_model_kwargs": {},
|
| 38 |
"tokenizer_class": "LlamaTokenizer",
|