Commit
•
eba526e
1
Parent(s):
d7da358
Update from amine
Browse files- README.md +43 -0
- config.json +24 -0
- pytorch_model.bin +3 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language: sw
|
3 |
+
|
4 |
+
datasets: wikipedia
|
5 |
+
|
6 |
+
license: apache-2.0
|
7 |
+
---
|
8 |
+
|
9 |
+
# distilbert-base-sw-cased
|
10 |
+
|
11 |
+
We are sharing smaller versions of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) that handle a custom number of languages.
|
12 |
+
|
13 |
+
Our versions give exactly the same representations produced by the original model which preserves the original accuracy.
|
14 |
+
|
15 |
+
|
16 |
+
For more information please visit our paper: [Load What You Need: Smaller Versions of Multilingual BERT](https://www.aclweb.org/anthology/2020.sustainlp-1.16.pdf).
|
17 |
+
|
18 |
+
## How to use
|
19 |
+
|
20 |
+
```python
|
21 |
+
from transformers import AutoTokenizer, AutoModel
|
22 |
+
|
23 |
+
tokenizer = AutoTokenizer.from_pretrained("Geotrend/distilbert-base-sw-cased")
|
24 |
+
model = AutoModel.from_pretrained("Geotrend/distilbert-base-sw-cased")
|
25 |
+
|
26 |
+
```
|
27 |
+
|
28 |
+
To generate other smaller versions of multilingual transformers please visit [our Github repo](https://github.com/Geotrend-research/smaller-transformers).
|
29 |
+
|
30 |
+
### How to cite
|
31 |
+
|
32 |
+
```bibtex
|
33 |
+
@inproceedings{smallermdistilbert,
|
34 |
+
title={Load What You Need: Smaller Versions of Mutlilingual BERT},
|
35 |
+
author={Abdaoui, Amine and Pradel, Camille and Sigel, Grégoire},
|
36 |
+
booktitle={SustaiNLP / EMNLP},
|
37 |
+
year={2020}
|
38 |
+
}
|
39 |
+
```
|
40 |
+
|
41 |
+
## Contact
|
42 |
+
|
43 |
+
Please contact amine@geotrend.fr for any question, feedback or request.
|
config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-multilingual-cased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForMaskedLM"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
+
"output_past": true,
|
17 |
+
"pad_token_id": 0,
|
18 |
+
"qa_dropout": 0.1,
|
19 |
+
"seq_classif_dropout": 0.2,
|
20 |
+
"sinusoidal_pos_embds": false,
|
21 |
+
"tie_weights_": true,
|
22 |
+
"transformers_version": "4.4.1",
|
23 |
+
"vocab_size": 16632
|
24 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3593fc6427f04825b7a4fafd8819102a1b412c80e5a0a1709a9523e7c4fbb243
|
3 |
+
size 225257472
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "model_max_length": 512}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|