glossia/Rambley-V2.2-64M-Embed

Rambley V2.1 350M Embed

Finetuned version of glossia/Rambley-V2.2-64M for embedding purposes on a subset of the nomic-embed training data.

Architecture

• Last-token pooling + L2 normalization
• 384 dimensional embeddings
• NO Matryoshka Representation Learning (embeddings will not maintain semantic relevance when truncated)
• NO quantization-aware training (embeddings may not maintain semantic relevance when quantized)
• See the original model card for details on the backbone architecture

Benchmarks

WIP

Detailed logs in glossia/Rambley-V2.2-64M-Embed-mteb-results

Usage

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("glossia/Rambley-V2.1-64M-Embed", trust_remote_code=True)
embeddings = model.encode(["Example text"])