theekshana
commited on
Commit
•
13484fe
1
Parent(s):
c150e94
Upload tokenizer
Browse files- README.md +1 -1
- tokenizer_config.json +8 -1
README.md
CHANGED
@@ -1,12 +1,12 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model: albert-base-v2
|
4 |
tags:
|
5 |
- classification
|
6 |
- sentiment
|
7 |
- sinhala
|
8 |
- news data
|
9 |
- generated_from_trainer
|
|
|
10 |
model-index:
|
11 |
- name: sinhala_albert
|
12 |
results: []
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
3 |
tags:
|
4 |
- classification
|
5 |
- sentiment
|
6 |
- sinhala
|
7 |
- news data
|
8 |
- generated_from_trainer
|
9 |
+
base_model: albert-base-v2
|
10 |
model-index:
|
11 |
- name: sinhala_albert
|
12 |
results: []
|
tokenizer_config.json
CHANGED
@@ -44,9 +44,16 @@
|
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
"mask_token": "[MASK]",
|
47 |
-
"
|
|
|
|
|
48 |
"pad_token": "[PAD]",
|
|
|
|
|
49 |
"sep_token": "[SEP]",
|
|
|
50 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
|
|
|
|
51 |
"unk_token": "[UNK]"
|
52 |
}
|
|
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
"mask_token": "[MASK]",
|
47 |
+
"max_length": 64,
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_to_multiple_of": null,
|
50 |
"pad_token": "[PAD]",
|
51 |
+
"pad_token_type_id": 0,
|
52 |
+
"padding_side": "right",
|
53 |
"sep_token": "[SEP]",
|
54 |
+
"stride": 0,
|
55 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
56 |
+
"truncation_side": "right",
|
57 |
+
"truncation_strategy": "longest_first",
|
58 |
"unk_token": "[UNK]"
|
59 |
}
|