Commit
•
3b68880
1
Parent(s):
2217d4c
Update README.md
Browse files
README.md
CHANGED
@@ -34,4 +34,9 @@ datasets:
|
|
34 |
license: mit
|
35 |
---
|
36 |
|
37 |
-
# Model Card for the test-version of instructionBERT
|
|
|
|
|
|
|
|
|
|
|
|
34 |
license: mit
|
35 |
---
|
36 |
|
37 |
+
# Model Card for the test-version of instructionBERT for Bertology
|
38 |
+
|
39 |
+
A minimalistic instruction model with an already good analysed and pretrained encoder like BERT.
|
40 |
+
So we can research the [Bertology](https://aclanthology.org/2020.tacl-1.54.pdf) with instruction-tuned models and investigate [what happens to BERT embeddings during fine-tuning](https://aclanthology.org/2020.blackboxnlp-1.4.pdf).
|
41 |
+
We used the Huggingface API for [warm-starting](https://huggingface.co/blog/warm-starting-encoder-decoder) [BertGeneration](https://huggingface.co/docs/transformers/model_doc/bert-generation) with [Encoder-Decoder-Models](https://huggingface.co/docs/transformers/v4.35.2/en/model_doc/encoder-decoder) for this purpose.
|
42 |
+
|