Upload tokenizer
Browse files- README.md +3 -0
- tokenizer_config.json +9 -1
README.md
CHANGED
|
@@ -1,3 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
| 1 |
library_name: transformers
|
| 2 |
tags:
|
| 3 |
- amharic
|
|
|
|
| 1 |
+
---
|
| 2 |
+
{}
|
| 3 |
+
---
|
| 4 |
library_name: transformers
|
| 5 |
tags:
|
| 6 |
- amharic
|
tokenizer_config.json
CHANGED
|
@@ -45,10 +45,18 @@
|
|
| 45 |
"clean_up_tokenization_spaces": true,
|
| 46 |
"cls_token": "<s>",
|
| 47 |
"eos_token": "</s>",
|
|
|
|
| 48 |
"mask_token": "<mask>",
|
|
|
|
| 49 |
"model_max_length": 512,
|
|
|
|
| 50 |
"pad_token": "<pad>",
|
|
|
|
|
|
|
| 51 |
"sep_token": "</s>",
|
| 52 |
-
"
|
|
|
|
|
|
|
|
|
|
| 53 |
"unk_token": "<unk>"
|
| 54 |
}
|
|
|
|
| 45 |
"clean_up_tokenization_spaces": true,
|
| 46 |
"cls_token": "<s>",
|
| 47 |
"eos_token": "</s>",
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
"mask_token": "<mask>",
|
| 50 |
+
"max_length": 128,
|
| 51 |
"model_max_length": 512,
|
| 52 |
+
"pad_to_multiple_of": null,
|
| 53 |
"pad_token": "<pad>",
|
| 54 |
+
"pad_token_type_id": 0,
|
| 55 |
+
"padding_side": "right",
|
| 56 |
"sep_token": "</s>",
|
| 57 |
+
"stride": 0,
|
| 58 |
+
"tokenizer_class": "XLMRobertaTokenizerFast",
|
| 59 |
+
"truncation_side": "right",
|
| 60 |
+
"truncation_strategy": "longest_first",
|
| 61 |
"unk_token": "<unk>"
|
| 62 |
}
|