indiejoseph
commited on
Commit
•
a473699
1
Parent(s):
998e451
Update README.md
Browse files
README.md
CHANGED
@@ -2,9 +2,15 @@
|
|
2 |
base_model: /notebooks/cantonese/bert-base-cantonese
|
3 |
tags:
|
4 |
- generated_from_trainer
|
|
|
|
|
5 |
model-index:
|
6 |
- name: bert-base-cantonese
|
7 |
results: []
|
|
|
|
|
|
|
|
|
8 |
---
|
9 |
|
10 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -12,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
12 |
|
13 |
# bert-base-cantonese
|
14 |
|
15 |
-
This model is a
|
16 |
|
17 |
## Model description
|
18 |
|
19 |
-
|
20 |
|
21 |
## Intended uses & limitations
|
22 |
|
@@ -39,7 +45,7 @@ The following hyperparameters were used during training:
|
|
39 |
- total_train_batch_size: 192
|
40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
- lr_scheduler_type: linear
|
42 |
-
- num_epochs:
|
43 |
|
44 |
### Training results
|
45 |
|
@@ -50,4 +56,4 @@ The following hyperparameters were used during training:
|
|
50 |
- Transformers 4.34.0.dev0
|
51 |
- Pytorch 2.0.1+cu118
|
52 |
- Datasets 2.14.5
|
53 |
-
- Tokenizers 0.14.0
|
|
|
2 |
base_model: /notebooks/cantonese/bert-base-cantonese
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
+
- Cantonese
|
6 |
+
- bert
|
7 |
model-index:
|
8 |
- name: bert-base-cantonese
|
9 |
results: []
|
10 |
+
license: cc-by-4.0
|
11 |
+
language:
|
12 |
+
- yue
|
13 |
+
pipeline_tag: fill-mask
|
14 |
---
|
15 |
|
16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
18 |
|
19 |
# bert-base-cantonese
|
20 |
|
21 |
+
This model is a continue pre-train version of [indiejoseph/cantonese/bert-base-cantonese](https://huggingface.co//notebooks/cantonese/bert-base-cantonese) on [indiejoseph/wikipedia-zh-yue-filtered](https://huggingface.co/datasets/indiejoseph/wikipedia-zh-yue-filtered).
|
22 |
|
23 |
## Model description
|
24 |
|
25 |
+
This model has extended 500 more Chinese characters which very common in Cantonese, such as `冧`, `噉`, `麪`, `笪`, `冚`, `乸` etc, and continue pre-trained with [indiejoseph/wikipedia-zh-yue-filtered](https://huggingface.co/datasets/indiejoseph/wikipedia-zh-yue-filtered)
|
26 |
|
27 |
## Intended uses & limitations
|
28 |
|
|
|
45 |
- total_train_batch_size: 192
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: linear
|
48 |
+
- num_epochs: 10
|
49 |
|
50 |
### Training results
|
51 |
|
|
|
56 |
- Transformers 4.34.0.dev0
|
57 |
- Pytorch 2.0.1+cu118
|
58 |
- Datasets 2.14.5
|
59 |
+
- Tokenizers 0.14.0
|