Upload tokenizer
Browse files- tokenizer.json +2 -8
- tokenizer_config.json +1 -2
tokenizer.json
CHANGED
|
@@ -1,14 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": null,
|
| 4 |
-
"padding":
|
| 5 |
-
"strategy": "BatchLongest",
|
| 6 |
-
"direction": "Right",
|
| 7 |
-
"pad_to_multiple_of": null,
|
| 8 |
-
"pad_id": 0,
|
| 9 |
-
"pad_type_id": 0,
|
| 10 |
-
"pad_token": "<pad>"
|
| 11 |
-
},
|
| 12 |
"added_tokens": [
|
| 13 |
{
|
| 14 |
"id": 0,
|
|
@@ -557,6 +550,7 @@
|
|
| 557 |
"continuing_subword_prefix": null,
|
| 558 |
"end_of_word_suffix": null,
|
| 559 |
"fuse_unk": true,
|
|
|
|
| 560 |
"vocab": {
|
| 561 |
"<pad>": 0,
|
| 562 |
"</s>": 1,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": null,
|
| 4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
|
|
|
| 550 |
"continuing_subword_prefix": null,
|
| 551 |
"end_of_word_suffix": null,
|
| 552 |
"fuse_unk": true,
|
| 553 |
+
"byte_fallback": false,
|
| 554 |
"vocab": {
|
| 555 |
"<pad>": 0,
|
| 556 |
"</s>": 1,
|
tokenizer_config.json
CHANGED
|
@@ -49,13 +49,12 @@
|
|
| 49 |
"<extra_id_46>",
|
| 50 |
"<extra_id_47>"
|
| 51 |
],
|
|
|
|
| 52 |
"eos_token": "</s>",
|
| 53 |
"extra_ids": 48,
|
| 54 |
"model_max_length": 1000000000000000019884624838656,
|
| 55 |
-
"name_or_path": "./trained/transx",
|
| 56 |
"pad_token": "<pad>",
|
| 57 |
"sp_model_kwargs": {},
|
| 58 |
-
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--VietAI--envit5-translation/snapshots/840bc88104d5a4277af740eaedb024df8c3093e7/special_tokens_map.json",
|
| 59 |
"tokenizer_class": "T5Tokenizer",
|
| 60 |
"unk_token": "<unk>"
|
| 61 |
}
|
|
|
|
| 49 |
"<extra_id_46>",
|
| 50 |
"<extra_id_47>"
|
| 51 |
],
|
| 52 |
+
"clean_up_tokenization_spaces": true,
|
| 53 |
"eos_token": "</s>",
|
| 54 |
"extra_ids": 48,
|
| 55 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 56 |
"pad_token": "<pad>",
|
| 57 |
"sp_model_kwargs": {},
|
|
|
|
| 58 |
"tokenizer_class": "T5Tokenizer",
|
| 59 |
"unk_token": "<unk>"
|
| 60 |
}
|