This model was converted to GGUF format from zeroentropy/zerank-1-reranker 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-1-Reranker produce garbage scores because of 4 issues:
Zerank 1 ships modeling_zeranker.py instead of 1_LogitScore directory.
Wrong Token Extracted -> yes (9693) vs the correct Yes (9454). Also, no false token on Zerank 1.
Wrong Scoring Formula -> Zerank 1 needs sigmoid(yes_logit / 5).
Slightly different chat template.
This GGUF fixes all 4 problems.
Original Model Card
Releasing zeroentropy/zerank-1
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 Salesforce/LlamaRank-v1 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 (Coming soon!) for more details.
For this model's smaller twin, see zerank-1-small, which we've fully open-sourced under an Apache 2.0 License.
Model Details
Property
Value
Parameters
4B
Context Length
32,768 tokens (32k)
Base Model
Qwen/Qwen3-4B
License
Apache-2.0
How to Use
python
1from sentence_transformers import CrossEncoder
23model = CrossEncoder("zeroentropy/zerank-1", trust_remote_code=True)45query_documents =[6("What is 2+2?","4"),7("What is 2+2?","The answer is definitely 1 million"),8]910scores = model.predict(query_documents)11print(scores)
The model can also be inferenced using ZeroEntropy's /models/rerank endpoint.
Evaluations
NDCG@10 scores between zerank-1 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.
