julien-c HF staff commited on
Commit
e0d87ec
1 Parent(s): 3adbf0e

Migrate model card from transformers-repo

Browse files

Read 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/jcblaise/electra-tagalog-small-uncased-generator/README.md

Files changed (1) hide show
  1. README.md +48 -0
README.md ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: tl
3
+ tags:
4
+ - electra
5
+ - tagalog
6
+ - filipino
7
+ license: gpl-3.0
8
+ inference: false
9
+ ---
10
+
11
+ # ELECTRA Tagalog Small Uncased Generator
12
+ Tagalog ELECTRA model pretrained with a large corpus scraped from the internet. This model is part of a larger research project. We open-source the model to allow greater usage within the Filipino NLP community.
13
+
14
+ This is the generator model used to sample synthetic text and pretrain the discriminator. Only use this model for retraining and mask-filling. For the actual model for downstream tasks, please refer to the discriminator models.
15
+
16
+ ## Usage
17
+ The model can be loaded and used in both PyTorch and TensorFlow through the HuggingFace Transformers package.
18
+
19
+ ```python
20
+ from transformers import TFAutoModel, AutoModel, AutoTokenizer
21
+
22
+ # TensorFlow
23
+ model = TFAutoModel.from_pretrained('jcblaise/electra-tagalog-small-uncased-generator', from_pt=True)
24
+ tokenizer = AutoTokenizer.from_pretrained('jcblaise/electra-tagalog-small-uncased-generator', do_lower_case=False)
25
+
26
+ # PyTorch
27
+ model = AutoModel.from_pretrained('jcblaise/electra-tagalog-small-uncased-generator')
28
+ tokenizer = AutoTokenizer.from_pretrained('jcblaise/electra-tagalog-small-uncased-generator', do_lower_case=False)
29
+ ```
30
+ Finetuning scripts and other utilities we use for our projects can be found in our centralized repository at https://github.com/jcblaisecruz02/Filipino-Text-Benchmarks
31
+
32
+ ## Citations
33
+ All model details and training setups can be found in our papers. If you use our model or find it useful in your projects, please cite our work:
34
+
35
+ ```
36
+ @article{cruz2020investigating,
37
+ title={Investigating the True Performance of Transformers in Low-Resource Languages: A Case Study in Automatic Corpus Creation},
38
+ author={Jan Christian Blaise Cruz and Jose Kristian Resabal and James Lin and Dan John Velasco and Charibeth Cheng},
39
+ journal={arXiv preprint arXiv:2010.11574},
40
+ year={2020}
41
+ }
42
+ ```
43
+
44
+ ## Data and Other Resources
45
+ Data used to train this model as well as other benchmark datasets in Filipino can be found in my website at https://blaisecruz.com
46
+
47
+ ## Contact
48
+ If you have questions, concerns, or if you just want to chat about NLP and low-resource languages in general, you may reach me through my work email at jan_christian_cruz@dlsu.edu.ph