Add some metadata to help people find this
#1
by
tomaarsen
HF staff
- opened
README.md
CHANGED
|
@@ -1,3 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
This is a version of [ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) distilled down to 16 layers out of 22.
|
| 2 |
This reduces the number of parameters from 149M to 119M; however, practically speaking, since the embedding params
|
| 3 |
do not contribute greatly to latency, the effect is reducing the "trunk" of the model from 110M params to 80M params.
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
base_model:
|
| 5 |
+
- answerdotai/ModernBERT-base
|
| 6 |
+
pipeline_tag: fill-mask
|
| 7 |
+
tags:
|
| 8 |
+
- transformers
|
| 9 |
+
- modernbert
|
| 10 |
+
---
|
| 11 |
This is a version of [ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) distilled down to 16 layers out of 22.
|
| 12 |
This reduces the number of parameters from 149M to 119M; however, practically speaking, since the embedding params
|
| 13 |
do not contribute greatly to latency, the effect is reducing the "trunk" of the model from 110M params to 80M params.
|