Commit
•
974f8dd
1
Parent(s):
076f874
Update README.md
Browse files
README.md
CHANGED
@@ -11,4 +11,13 @@ tags:
|
|
11 |
|
12 |
A Bert implementation where most of the `torch.nn.linear` have been replaced with `KANLinear`.
|
13 |
|
14 |
-
Currently pretraining on [JackBAI/bert_pretrain_datasets](https://huggingface.co/datasets/JackBAI/bert_pretrain_datasets) on a RTX 4090. Will be do in 5 days from 13/05/2024. Until then :)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
|
12 |
A Bert implementation where most of the `torch.nn.linear` have been replaced with `KANLinear`.
|
13 |
|
14 |
+
Currently pretraining on [JackBAI/bert_pretrain_datasets](https://huggingface.co/datasets/JackBAI/bert_pretrain_datasets) on a RTX 4090. Will be do in 5 days from 13/05/2024. Until then :)
|
15 |
+
|
16 |
+
|
17 |
+
```python
|
18 |
+
from transformers import AutoModelForSequenceClassification, AutoTokenizer
|
19 |
+
|
20 |
+
model_path = 'isemmanuelolowe/BerKANT_171M'
|
21 |
+
model = AutoModelForSequenceClassification.from_pretrained(model_path, trust_remote_code=True)
|
22 |
+
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
23 |
+
```
|