| | --- |
| | license: cc-by-nc-4.0 |
| | language: |
| | - en |
| | base_model: |
| | - Qwen/Qwen3-4B |
| | pipeline_tag: text-ranking |
| | tags: |
| | - finance |
| | - legal |
| | - code |
| | - stem |
| | - medical |
| | library_name: sentence-transformers |
| | model_max_length: 32768 |
| | --- |
| | |
| | <img src="https://i.imgur.com/oxvhvQu.png"/> |
| |
|
| | # Releasing zeroentropy/zerank-1 |
| |
|
| | In search engines, [rerankers are crucial](https://www.zeroentropy.dev/blog/what-is-a-reranker-and-do-i-need-one) 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](https://huggingface.co/zeroentropy/zerank-1#evaluations) 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](https://en.wikipedia.org/wiki/Elo_rating_system). See our Technical Report (Coming soon!) for more details. |
| |
|
| | This model is released under a non-commercial license. If you'd like a commercial license, please contact us at contact@zeroentropy.dev. |
| |
|
| | For this model's smaller twin, see [zerank-1-small](https://huggingface.co/zeroentropy/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 | CC-BY-NC-4.0 | |
| |
|
| | ## How to Use |
| |
|
| | ```python |
| | from sentence_transformers import CrossEncoder |
| | |
| | model = CrossEncoder("zeroentropy/zerank-1", trust_remote_code=True) |
| | |
| | query_documents = [ |
| | ("What is 2+2?", "4"), |
| | ("What is 2+2?", "The answer is definitely 1 million"), |
| | ] |
| | |
| | scores = model.predict(query_documents) |
| | print(scores) |
| | ``` |
| |
|
| | The model can also be inferenced using ZeroEntropy's [/models/rerank](https://docs.zeroentropy.dev/api-reference/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. |
| |
|
| | | Task | Embedding | cohere-rerank-v3.5 | Salesforce/Llama-rank-v1 | zerank-1-small | **zerank-1** | |
| | |----------------|-----------|--------------------|--------------------------|----------------|--------------| |
| | | Code | 0.678 | 0.724 | 0.694 | 0.730 | **0.754** | |
| | | Conversational | 0.250 | 0.571 | 0.484 | 0.556 | **0.596** | |
| | | Finance | 0.839 | 0.824 | 0.828 | 0.861 | **0.894** | |
| | | Legal | 0.703 | 0.804 | 0.767 | 0.817 | **0.821** | |
| | | Medical | 0.619 | 0.750 | 0.719 | 0.773 | **0.796** | |
| | | STEM | 0.401 | 0.510 | 0.595 | 0.680 | **0.694** | |
| |
|
| | Comparing BM25 and Hybrid Search without and with zerank-1: Description Description |
