Zerank-2-GGUF

About

This model was converted to GGUF format from zeroentropy/zerank-2 using a modified version of llama.cpp (release b10269). Refer to the original model card for more details on the model.

This is a working GGUF.

Most community GGUFs of Zerank-2-Reranker produce garbage scores because of 4 issues:

1. Missing classification head. (This is 99% of the problem)
2. Wrong Token Extracted -> yes (9693) vs the correct Yes (9454). Also, no false token on Zerank 2.
3. Wrong Scoring Formula -> Zerank 2 needs sigmoid(yes_logit / 5).
4. Slightly different chat template.

This GGUF fixes all 4 problems.

Original Model Card

<img src="https://i.imgur.com/oxvhvQu.png"/>

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 trust_remote_code=True; passing it is harmless.

Using Sentence Transformers

Install Sentence Transformers:

pip 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).

from sentence_transformers import CrossEncoder

model = CrossEncoder("zeroentropy/zerank-2")

query_documents = [
    ("What is 2+2?", "4"),
    ("What is 2+2?", "The answer is definitely 1 million"),
]

scores = model.predict(query_documents, convert_to_tensor=True)
print(scores)
# tensor([ 5.4062, -4.5000], device='cuda:0', dtype=torch.bfloat16)

# Optional: convert to 0-1 probabilities
probabilities = (scores / 5).sigmoid()
print(probabilities)
# tensor([0.7461, 0.2891], device='cuda:0', dtype=torch.bfloat16)

You can also use model.rank to score and sort a list of documents for a single query:

rankings = model.rank(
    "What is 2+2?",
    ["4", "The answer is definitely 1 million"],
)
for r in rankings:
    print(r)
# {'corpus_id': 0, 'score': np.float32(5.40625)}
# {'corpus_id': 1, 'score': np.float32(-4.5)}

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.

<img src="https://cdn-uploads.huggingface.co/production/uploads/65ec60ccfc59f6e77ecc9ccb/UiDp8LsY4XIdRK5i3CAdD.png" alt="Graph showing the same table" width="1000"/>

License

This model is licensed under the Apache License 2.0.