Hugging Face does not say who downloads a model or with what. These are the proxies: API providers listing it, quantized builds, fine-tunes/adapters/merges, and Spaces that load it.
No API provider serves it, so its downloads are people running it themselves: 7 quantized builds.
Third-party measurements only; author-reported numbers stay in Reference, marked as such.
#24 of 33 on MTEB Reranking so far
45.3. Each tick is a model on this site with a measured MTEB Reranking row; author-reported numbers stay in Reference. MAP x100 (mean of 2 tasks). 2 tasks, split=test
Everything else, folded: the full tables, every source.
Benchmarks
3 rows
Benchmarks 3 rows
measured third-party leaderboard row (3)author-reported number from the model card or eval filesNo confidence intervals unless the source gave them; settings differ between rows, so compare within a benchmark, not across. Date = the benchmark's own date when it gives one, else when we read it.
Labels are evidence, not verdicts: measured a third-party leaderboard row for this model; author-reported a number the model author published in the card or eval files; structural a deterministic signal from the name, config or chat template, or a decision-model estimate. Each chip links to its source. All use cases.
Ranked by source signals (HN, Lobsters, authority domains, official posts) and recency. Summaries are generated from a stored copy of the article text; every sentence cites a span of that text, and nothing is shown that failed the citation check.
aws.amazon.com2024-06-09about the jina embeddings v2 familyHN 1 pts · 0 comments1,732 words
Jina Embeddings v2 supports an 8,192-tokens context length for processing long documents like legal text or product documentation. The jina-embeddings-v2-base-de model has a size of 322 MB with a performance score of 60.1% for information retrieval tasks.generated, cited
Jina AI released jina-embeddings-v2-small-en, an open-weight model for English text feature extraction under Apache License 2.0. The 33M parameter model uses a four-layer JinaBERT architecture with an 8,192-token context and fits on a single MI300X GPU for $1.85 an hour.written, reviewed, cited
The model is further trained on Jina AI's collection of more than 400 millions of sentence pairs and hard negatives.
Apache 2.0 requires users to keep the license and NOTICE files and state significant changes when redistributing.
The 8,192 token window allows a full contract or filing to be processed as one single piece of text.
Jina AI released jina-embeddings-v2-small-en, the smallest variant in the Jina Embeddings v2 family as of October 2024. The model is trained with 33 million parameters and generates 512-dimensional embeddings for English monolingual text. It supports a sequence length of up to 8192 tokens and is available under an Apache 2.0 license.written, reviewed, cited
The model supports multilingual queries in the sentence-transformer example despite being English-only.
jina-embeddings-v3 offers flexible embedding sizes with a default of 1024 dimensions.
The sentence-transformer integration requires setting normalize_embeddings=True during encoding.
ritvik19.medium.com2024-12-03about the jina embeddings v2 family
Papers
2 papers
Papers 2
arXiv links found in the model card and its tags. "Peer-reviewed" is shown only with evidence: a published venue in OpenAlex (measured) or the authors' own journal reference on arXiv (reported).
