amine-private commited on
Commit
b16afc0
1 Parent(s): 7d523ab

Update from amine

Browse files
Files changed (5) hide show
  1. README.md +43 -0
  2. config.json +24 -0
  3. pytorch_model.bin +3 -0
  4. tokenizer_config.json +1 -0
  5. vocab.txt +0 -0
README.md ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: no
3
+
4
+ datasets: wikipedia
5
+
6
+ license: apache-2.0
7
+ ---
8
+
9
+ # distilbert-base-no-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-no-cased")
24
+ model = AutoModel.from_pretrained("Geotrend/distilbert-base-no-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": 23399
24
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dea2d6a4bd21f8c5ab90eaf8d05839f8cbc7a44d8c014f0f69ce13badbcc34b
3
+ size 246072692
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