Downloads · 30 days
20
36% of all-time downloads
rasyosef/bert-mini-amharic-16k
bert-mini-amharic-16k is a fill-mask model from rasyosef. Use it when you need the model to fill a missing word. It is set up for transformers.
This model has the same architecture as bert-mini and was pretrained from scratch using the Amharic subsets of the oscar and mc4 datasets, on a total of 165 Million tokens. It achieves the following results on the eva…
Downloads · 30 days
20
36% of all-time downloads
All-time downloads
56
Public
Parameters
7.6M
30.3 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors30.3 MB · 98%
From the Hugging Face model README
This model has the same architecture as bert-mini and was pretrained from scratch using the Amharic subsets of the oscar and mc4 datasets, on a total of 165 Million tokens.
It achieves the following results on the evaluation set:
Loss: 2.59Perplexity: 13.33Even though this model only has 7.5 Million parameters, its perplexity score is comparable to the 36x larger 279 Million parameter xlm-roberta-base model on the same Amharic evaluation set.