bge-reranker-v2-m3
Different from embedding model, reranker uses question and document as input and directly output similarity instead of embedding. You can get a relevance score by inputting query and passage to the reranker. And the score can be mapped to a float value in [0,1] by sigmoid function.
Params
570 M
Context
8,192
Downloads 30d
17.6 M
Likes
1,204
Download history
daily snapshots · 55 days
▲ 1.1 M in the last 30 days (5.8%)
18.7 M17.4 M
Aug 22Sep 1Sep 11Sep 20
19.3 M17.4 M
Jul 28Aug 15Sep 2Sep 20
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | f32 | 2.3 GB | 3.1 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Architecture
- XLMRobertaForSequenceClassification
- Parameters
- 570 M
- Tensor type
- F32
- Context length
- 8,192
- Vocabulary
- 250,002
- Layers / heads
- 24 / 16
- Licence
- apache-2.0
- First seen on the Hub
- 2024-03-15
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Compare with any text-classification model
Popular comparisons
Appears in