Bachstelze
commited on
Commit
•
4ba7123
1
Parent(s):
380ab22
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,30 @@
|
|
1 |
---
|
|
|
|
|
|
|
2 |
license: mit
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
tags:
|
3 |
+
- text2text-generation
|
4 |
+
|
5 |
license: mit
|
6 |
---
|
7 |
+
datasets:
|
8 |
+
- CohereForAI/aya_dataset
|
9 |
+
|
10 |
+
|
11 |
+
license: mit
|
12 |
+
---
|
13 |
+
# Model Card of instructionMBERTv1 for Bertology
|
14 |
+
|
15 |
+
A minimalistic instruction model with an already good analysed and pretrained encoder like roBERTa.
|
16 |
+
So we can research the [Bertology](https://aclanthology.org/2020.tacl-1.54.pdf) with instruction-tuned models, [look at the attention](https://colab.research.google.com/drive/1mNP7c0RzABnoUgE6isq8FTp-NuYNtrcH?usp=sharing) and investigate [what happens to BERT embeddings during fine-tuning](https://aclanthology.org/2020.blackboxnlp-1.4.pdf).
|
17 |
+
|
18 |
+
The training code is released at the [instructionBERT repository](https://gitlab.com/Bachstelze/instructionbert).
|
19 |
+
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.
|
20 |
+
|
21 |
+
## Training parameters
|
22 |
+
|
23 |
+
- base model: "google-bert/bert-base-multilingual-cased"
|
24 |
+
- trained for 8 epochs
|
25 |
+
- batch size of 16
|
26 |
+
- 20000 warm-up steps
|
27 |
+
- learning rate of 0.0001
|
28 |
+
|
29 |
+
## Purpose of instructionMBERT
|
30 |
+
InstructionMBERT is intended for research purposes. The model-generated text should be treated as a starting point rather than a definitive solution for potential use cases. Users should be cautious when employing these models in their applications.
|