Commit
·
2f1b45c
1
Parent(s):
a300e1f
Update README.md
Browse files
README.md
CHANGED
|
@@ -36,6 +36,10 @@ license: mit
|
|
| 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.
|
|
|
|
| 36 |
|
| 37 |
# Model Card for the test-version of instructionBERT for Bertology
|
| 38 |
|
| 39 |
+
<img src="https://huggingface.co/Bachstelze/instructionBERTtest/blob/main/The_cinematic_puppet_Bert_from_sesame_street_carries_89f3c10a_273b.png"
|
| 40 |
+
alt="instruction BERT drawing" width="600"/>
|
| 41 |
+
|
| 42 |
+
|
| 43 |
A minimalistic instruction model with an already good analysed and pretrained encoder like BERT.
|
| 44 |
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).
|
| 45 |
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.
|