Downloads · 30 days
16
6% of all-time downloads
wabibito/Onyx-mE5-Small
Onyx-mE5-Small is a feature extraction model from wabibito. Use it when you need embeddings to search or compare text. It is set up for sentence-transformers. The card lists the license as mit.
4-bit MLX quantization of intfloat/multilingual-e5-small (MIT), for the Onyx on-device RAG embedder (OnyxEmbed). groupsize 64, bits 4 on the attention/FFN dense matrices + wordembeddings; LayerNorms, biases, and posit…
Downloads · 30 days
16
6% of all-time downloads
All-time downloads
269
Public
Parameters
118M
96.6 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors74.4 MB · 77%
How the weights are stored.
U32117M · 100%
From the Hugging Face model README
4-bit MLX quantization of intfloat/multilingual-e5-small (MIT), for the Onyx on-device RAG embedder (OnyxEmbed). group_size 64, bits 4 on the attention/FFN dense matrices + word_embeddings; LayerNorms, biases, and positional embeddings stay fp. ~71 MB (from ~449 MB fp32).
Usage keeps e5 conventions: mean pooling, and the query: / passage: prefixes. Verified recall-neutral
vs fp32 (English + cross-lingual). Inherits the base model MIT license.