cstr
/

gte-small-GGUF

Feature Extraction

sentence-transformers

Model card Files Files and versions

gte-small — GGUF

GGUF conversion of thenlper/gte-small for CrispEmbed.

Architecture: BERT (12 layers, 384 hidden, 12 heads)
Embedding dim: 384
Pooling: Mean
Size: 128 MB (F32)
Verified: cos=0.999999 vs HF sentence-transformers

Downloads last month: -

GGUF

Model size

33.4M params

Architecture

bert

Hardware compatibility

Log In to add your hardware

32-bit

Model tree for cstr/gte-small-GGUF

Base model

thenlper/gte-small

Quantized

(9)

this model