ML-DevOps | Crete a train pipeline for word2vec

[AlexisTercero55]

• [x] Use Word2Vec.exe https://github.com/AlexisTercero55/word2vec_TMB/releases/tag/v1.0.0 to generate vector embedings.
• [x] Configure train action un github pipeline
• [x] train over dataset used in Attention is all you need

[AlexisTercero55]

Attention is all you need dataset wmt 2014 english-german dataset

Dataset: https://nlp.stanford.edu/projects/nmt/

from the paper:

Sentences were encoded using byte-pair encoding.

see Massive Exploration of Neural Machine Translation Architectures

[AlexisTercero55]

Conclusions

Due byte-pair encoding needed for train transformer model we split this task into another task: which will achieve the required encoding:

12