| license: apache-2.0 | |
| base_model: Qwen/Qwen3-4B | |
| tags: | |
| - text-ranking | |
| - reranker | |
| - sentence-transformers | |
| - safetensors | |
| - english | |
| language: | |
| - en | |
| # zerank-1-small-seq | |
| Internal DevRev mirror of [zeroentropy/zerank-1-small](https://huggingface.co/zeroentropy/zerank-1-small). | |
| Original model by [ZeroEntropy](https://huggingface.co/zeroentropy) — released under Apache 2.0. | |
| ## Model details | |
| | Property | Value | | |
| |----------|-------| | |
| | Parameters | 1.7B | | |
| | Context length | 32,768 tokens | | |
| | Base model | Qwen/Qwen3-4B | | |
| | Tensor type | BF16 | | |
| | License | Apache-2.0 | | |
| ## Usage | |
| ```python | |
| from sentence_transformers import CrossEncoder | |
| model = CrossEncoder("devrev/zerank-1-small-seq") | |
| query = "Which planet is known as the Red Planet?" | |
| passages = [ | |
| "Venus is often called Earth's twin...", | |
| "Mars, known for its reddish appearance, is often referred to as the Red Planet.", | |
| ] | |
| scores = model.predict([(query, passage) for passage in passages]) | |
| print(scores) | |
| ``` | |
| ## Performance (NDCG@10) | |
| | Domain | Score | | |
| |--------|-------| | |
| | Finance | 0.861 | | |
| | Legal | 0.817 | | |
| | Medical | 0.773 | | |
| | Code | 0.730 | | |
| | STEM | 0.680 | | |
| | Conversational | 0.556 | | |