Model reference · open weights
zerank-2-reranker is an open-weight embedding model from zeroentropy, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
Releasing zeroentropy/zerank-2 In search engines, rerankers are crucial for improving the accuracy of your retrieval system. However, SOTA rerankers are closed-source and proprietary. At ZeroEntropy, we've trained a SOTA reranker outperforming closed-source competitors, and we're launching our model here on HuggingFace. This reranker outperforms proprietary rerankers such as cohere-rerank-v3.5 and gemini-2.5-flash across a wide variety of domains, including finance, legal, code, STEM, medical, and conversational data. At ZeroEntropy we've developed an innovative multi-stage pipeline that models query-document relevance scores as adjusted Elo ratings. See our Technical Report (https://arxiv.org/abs/2509.12541 ) for more details. This model is released under the Apache License 2.0. Model Details How to Use Breaking change (May 2026): model.predict() now returns raw "Yes" logits instead of sigmoid'd probabilities in [0, 1]. Rankings are unchanged. To recover the previous 0-1 score, apply (scores / 5).sigmoid() — see the example below. Loading no longer requires trustremotecode=True; passing it is harmless. Using Sentence Transformers Install Sentence Transformers: Then load the model and score query/document pairs. model.predict returns the raw "Yes" logit per pair; rankings can be used directly. To map the logits to a 0-1 score range, apply a temperature-scaled sigmoid: sigmoid(score / 5). You can also use model.rank to score and sort a list of documents for a single query: The model can also be inferenced using ZeroEntropy's /models/rerank endpoint, and on AWS Marketplace. Evaluations NDCG@10 scores between zerank-2 and competing closed-source proprietary rerankers. Since we are evaluating rerankers, OpenAI's text-embedding-3-small is used as an initial retriever for the Top 100 candidate documents. License This model is licensed under the Apache License 2.0.
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | zeroentropy |
|---|---|
| Type | Embedding models |
| Parameters (lead) | 4.0B |
| Context | 40k tokens |
| Variants | 1 |
| Runs with | sentence-transformers |
| Based on | Qwen/Qwen3-4B |
| Released | 2025-11-19 |
| Popularity | 634k downloads / month |
| Likes | 116 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| zerank-2-reranker | 4.0B | BF16 | ~9.3 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys zerank-2-reranker for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (zerank-2-reranker below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/embeddings \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"zerank-2-reranker","input":"text to embed"}'
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗
Explore