Migrate model card from transformers-repo
Browse filesRead announcement at https://discuss.huggingface.co/t/announcement-all-model-cards-will-be-migrated-to-hf-co-model-repos/2755
Original file history: https://github.com/huggingface/transformers/commits/master/model_cards/distilbert-base-cased-README.md
README.md
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: en
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
datasets:
|
| 5 |
+
- bookcorpus
|
| 6 |
+
- wikipedia
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
# DistilBERT base model (cased)
|
| 10 |
+
|
| 11 |
+
This model is a distilled version of the [BERT base model](https://huggingface.co/bert-base-cased).
|
| 12 |
+
It was introduced in [this paper](https://arxiv.org/abs/1910.01108).
|
| 13 |
+
The code for the distillation process can be found
|
| 14 |
+
[here](https://github.com/huggingface/transformers/tree/master/examples/distillation).
|
| 15 |
+
This model is cased: it does make a difference between english and English.
|
| 16 |
+
|
| 17 |
+
All the training details on the pre-training, the uses, limitations and potential biases are the same as for [DistilBERT-base-uncased](https://huggingface.co/distilbert-base-uncased).
|
| 18 |
+
We highly encourage to check it if you want to know more.
|
| 19 |
+
|
| 20 |
+
## Evaluation results
|
| 21 |
+
|
| 22 |
+
When fine-tuned on downstream tasks, this model achieves the following results:
|
| 23 |
+
|
| 24 |
+
Glue test results:
|
| 25 |
+
|
| 26 |
+
| Task | MNLI | QQP | QNLI | SST-2 | CoLA | STS-B | MRPC | RTE |
|
| 27 |
+
|:----:|:----:|:----:|:----:|:-----:|:----:|:-----:|:----:|:----:|
|
| 28 |
+
| | 81.5 | 87.8 | 88.2 | 90.4 | 47.2 | 85.5 | 85.6 | 60.6 |
|
| 29 |
+
|
| 30 |
+
### BibTeX entry and citation info
|
| 31 |
+
|
| 32 |
+
```bibtex
|
| 33 |
+
@article{Sanh2019DistilBERTAD,
|
| 34 |
+
title={DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter},
|
| 35 |
+
author={Victor Sanh and Lysandre Debut and Julien Chaumond and Thomas Wolf},
|
| 36 |
+
journal={ArXiv},
|
| 37 |
+
year={2019},
|
| 38 |
+
volume={abs/1910.01108}
|
| 39 |
+
}
|
| 40 |
+
```
|