Downloads · 30 days
29
0% of all-time downloads
distilbert-word2vec_256k-MLM_best
vocab-transformers/distilbert-word2vec_256k-MLM_best
distilbert-word2vec_256k-MLM_best is a fill-mask model from vocab-transformers. Use it when you need the model to fill a missing word. It is set up for transformers.
This model has a word2vec token embedding matrix with 256k entries. The word2vec was trained on 100GB data from C4, MSMARCO, News, Wikipedia, S2ORC, for 3 epochs.
All-time downloads
20.7K
Public
Repo size
1.9 GB
Likes
4
Public
Repo makeup
Click a slice to open those files.
.bin962 MB · 99%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- distilbert
- Access
- Public
- Created
- Apr 11, 2022
- Updated
- Apr 11, 2022
- SHA
- ee249caa
Try a prompt
Model card
From the Hugging Face model README
DistilBERT with word2vec token embeddings
This model has a word2vec token embedding matrix with 256k entries. The word2vec was trained on 100GB data from C4, MSMARCO, News, Wikipedia, S2ORC, for 3 epochs.
Then the model was trained on this dataset with MLM for 1.37M steps (batch size 64). The token embeddings were NOT updated.
For the initial word2vec weights with Gensim see: https://huggingface.co/vocab-transformers/distilbert-word2vec_256k-MLM_1M/tree/main/word2vec
- Task
- Fill-Mask
- Library
- transformers
- Type
- distilbert
- Created
- Apr 11, 2022
- Updated
- Apr 11, 2022