Downloads · 30 days
7
4% of all-time downloads
bge-reranker-v2-m3__trimm_vocab__bf16
Symato/bge-reranker-v2-m3__trimm_vocab__bf16
bge-reranker-v2-m3__trimm_vocab__bf16 is a machine learning model from Symato. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
183
Public
Parameters
359M
719 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors719 MB · 100%
At a glance
- Model type
- xlm-roberta
- Access
- Public
- Created
- Oct 18, 2024
- Updated
- Oct 18, 2024
- SHA
- 3be3f345
Model card
From the Hugging Face model README
model BAAI/bge-reranker-v2-m3
params 566705152
embeds 256002048
torch.bfloat16
model Symato/bge-reranker-v2-m3__trimm_vocab__bf16
params 359397376
embeds 47644672
torch.float16
Giảm vocab size từ 250002 / 46000 => 5.43 lần
=> embeddings giảm từ 256m xuống 47m
=> model size giảm từ 567m xuống 359m (còn 63%)
Phở bert large 370M, phở bert base 135M
- Type
- xlm-roberta
- Created
- Oct 18, 2024
- Updated
- Oct 18, 2024