Update README.md
Browse files
README.md
CHANGED
|
@@ -16,10 +16,10 @@ widget:
|
|
| 16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
|
| 19 |
-
#
|
| 20 |
|
| 21 |
## About
|
| 22 |
-
|
| 23 |
This model is trained based on [BERT](https://arxiv.org/abs/1810.04805) model utilizing
|
| 24 |
Hugging Face's [Transformers]((https://huggingface.co/transformers)) library.
|
| 25 |
|
|
@@ -51,9 +51,9 @@ Finally, we have 28,121,693 sentences for the training process.
|
|
| 51 |
This pretraining data will not be opened to public due to Twitter policy.
|
| 52 |
|
| 53 |
## Model
|
| 54 |
-
| Model name
|
| 55 |
-
|
| 56 |
-
| `
|
| 57 |
|
| 58 |
## Evaluation Results
|
| 59 |
We train the data with 3 epochs and total steps of 296K for 12 days.
|
|
@@ -67,15 +67,15 @@ The following are the results obtained from the training:
|
|
| 67 |
### Load model and tokenizer
|
| 68 |
```python
|
| 69 |
from transformers import AutoTokenizer, AutoModel
|
| 70 |
-
tokenizer = AutoTokenizer.from_pretrained("fathan/
|
| 71 |
-
model = AutoModel.from_pretrained("fathan/
|
| 72 |
|
| 73 |
```
|
| 74 |
### Masked language model
|
| 75 |
```python
|
| 76 |
from transformers import pipeline
|
| 77 |
|
| 78 |
-
pretrained_model = "fathan/
|
| 79 |
|
| 80 |
fill_mask = pipeline(
|
| 81 |
"fill-mask",
|
|
|
|
| 16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
|
| 19 |
+
# IJEBERTweet: BERT-base
|
| 20 |
|
| 21 |
## About
|
| 22 |
+
This is a pre-trained masked language model for code-mixed Indonesian-Javanese-English tweets data.
|
| 23 |
This model is trained based on [BERT](https://arxiv.org/abs/1810.04805) model utilizing
|
| 24 |
Hugging Face's [Transformers]((https://huggingface.co/transformers)) library.
|
| 25 |
|
|
|
|
| 51 |
This pretraining data will not be opened to public due to Twitter policy.
|
| 52 |
|
| 53 |
## Model
|
| 54 |
+
| Model name | Architecture | Size of training data | Size of validation data |
|
| 55 |
+
|-----------------------------------|-----------------|----------------------------|-------------------------|
|
| 56 |
+
| `ijebertweet-codemixed-bert-base` | BERT | 2.24 GB of text | 249 MB of text |
|
| 57 |
|
| 58 |
## Evaluation Results
|
| 59 |
We train the data with 3 epochs and total steps of 296K for 12 days.
|
|
|
|
| 67 |
### Load model and tokenizer
|
| 68 |
```python
|
| 69 |
from transformers import AutoTokenizer, AutoModel
|
| 70 |
+
tokenizer = AutoTokenizer.from_pretrained("fathan/ijebertweet-codemixed-bert-base")
|
| 71 |
+
model = AutoModel.from_pretrained("fathan/ijebertweet-codemixed-bert-base")
|
| 72 |
|
| 73 |
```
|
| 74 |
### Masked language model
|
| 75 |
```python
|
| 76 |
from transformers import pipeline
|
| 77 |
|
| 78 |
+
pretrained_model = "fathan/ijebertweet-codemixed-bert-base"
|
| 79 |
|
| 80 |
fill_mask = pipeline(
|
| 81 |
"fill-mask",
|