Davlan commited on
Commit
125c9c0
1 Parent(s): 77eed1c

updating Readme

Browse files
Files changed (1) hide show
  1. README.md +7 -2
README.md CHANGED
@@ -12,11 +12,16 @@ Specifically, this model is a *bert-base-multilingual-cased* model that was fine
12
  ## Intended uses & limitations
13
  #### How to use
14
  You can use this model with Transformers *pipeline* for masked token prediction.
15
-
 
 
 
 
 
16
  #### Limitations and bias
17
  This model is limited by its training dataset of entity-annotated news articles from a specific span of time. This may not generalize well for all use cases in different domains.
18
  ## Training data
19
- This model was fine-tuned on Yorùbá corpus
20
 
21
  ## Training procedure
22
  This model was trained on a single NVIDIA V100 GPU
12
  ## Intended uses & limitations
13
  #### How to use
14
  You can use this model with Transformers *pipeline* for masked token prediction.
15
+ ```python
16
+ from transformers import pipeline
17
+ >>> from transformers import pipeline
18
+ >>> unmasker = pipeline('fill-mask', model='Davlan/bert-base-multilingual-cased-finetuned-yoruba')
19
+ >>> unmasker("Arẹmọ Phillip to jẹ ọkọ [MASK] Elizabeth to ti wa lori aisan ti dagbere faye lẹni ọdun mọkandilọgọrun")
20
+ ```
21
  #### Limitations and bias
22
  This model is limited by its training dataset of entity-annotated news articles from a specific span of time. This may not generalize well for all use cases in different domains.
23
  ## Training data
24
+ This model was fine-tuned on Bible, JW300, [Menyo-20k](https://huggingface.co/datasets/menyo20k_mt), [Yoruba Embedding corpus](https://huggingface.co/datasets/yoruba_text_c3) and [CC-Aligned](https://opus.nlpl.eu/), Wikipedia, news corpora (BBC Yoruba, VON Yoruba, Asejere, Alaroye), and other small datasets curated from friends.
25
 
26
  ## Training procedure
27
  This model was trained on a single NVIDIA V100 GPU