Minish

5.5k+ GitHub stars

4M+ Package downloads 1.9M+ Monthly model downloads

Model2Vec State-of-the-art static embeddings distilled from any sentence transformer.

Docs Stars 2.1k Downloads 3.1M

SemHash Multimodal semantic deduplication, outlier filtering, and representative sampling.

Docs Stars 926 Downloads 378.5k

Vicinity Flexible nearest neighbor search with multiple backends and evaluation.

Docs Stars 342 Downloads 410.8k

Semble Fast and accurate code search for agents.

Docs Stars 1.8k Downloads 25k

Tokenlearn Pre-train Model2Vec models on large corpora with efficient embedding distillation.

Docs Stars 101 Downloads 7k

Model2Vec-rs High-performance Rust inference for Model2Vec models with low-overhead deployment.

Docs Stars 181 Downloads 32.1k