skip to content
gigarouter gigarouter
models / embeddings · coming soon

SLX-v0.1

brahmairesearch/slx-v0.1

published Aug 2024 · updated Aug 2024

SLX-v0.1 is an embedding model that maps sentences and paragraphs into a 384-dimensional dense vector space for semantic search, clustering, and similarity tasks.

est. price
~$0.008
/ 1M tokens · estimated, set at launch
API providers
0
downloads / mo
215
license
apache-2.0

specs

TaskEmbedding
ArchitectureMiniLM-L6-H384-uncased (6-layer MiniLM, 384 hidden)
Output Dimension384
Max Sequence Length256 tokens (truncated)
LicenseNot specified

about this model

SLX-v0.1 is an embedding model that maps sentences and short paragraphs into a 384-dimensional dense vector space for semantic search, clustering, and similarity tasks. It is built on the nreimers/MiniLM-L6-H384-uncased backbone and fine-tuned with a contrastive learning objective followed by transfer learning from dunzhang/stella_en_400M_v5 using an internally curated English dataset. Input text longer than 256 word pieces is truncated by default.

The model produces normalized sentence embeddings optimized for cosine similarity comparison. It is hosted by GigaRouter as a managed, OpenAI-compatible API, requiring no local installation or dependency management.

best for

FAQ

What is the maximum input length for SLX-v0.1?

Input text longer than 256 word pieces (tokens) will be truncated by default.

What output dimensionality does SLX-v0.1 produce?

It produces a 384-dimensional dense vector for each input sentence or paragraph.

How was SLX-v0.1 trained?

It was fine-tuned using contrastive learning with cross-entropy loss, then transfer learned from the stella_en_400M_v5 model on an internally curated English dataset.

How can I call SLX-v0.1 via the gigarouter API?

Use the gigarouter OpenAI-compatible endpoint with your API key; send a request with the model name 'brahmairesearch/slx-v0.1' and the input text.

What is the underlying base model for SLX-v0.1?

It is based on the pre-trained model nreimers/MiniLM-L6-H384-uncased.

not yet live

We're benchmarking and onboarding SLX-v0.1 as a hosted, OpenAI-compatible API. Sign in for free credit and be ready when it lands, or tell us you want it and we'll prioritize it.

related embeddings models

compare all →