gte-base-en-v1.5
We introduce gte-v1.5 series, upgraded gte embeddings that support the context length of up to 8192, while further enhancing model performance. The models are built upon the transformer++ encoder backbone (BERT + RoPE + GLU).
Params
137 M
Context
8,192
Downloads 30d
458 K
Likes
72
Download history
daily snapshots · 23 days481 K399 K
Oct 2Oct 9Oct 17Oct 24
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 | 0.5 GB | 1.1 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
- NewModel
- Parameters
- 137 M
- Tensor type
- F32
- Context length
- 8,192
- Vocabulary
- 30,528
- Layers / heads
- 12 / 12
- Licence
- apache-2.0
- First seen on the Hub
- 2024-04-20
- Training datasets
- undisclosed
- MTEB ArguAna (reported)
- 78.094
- MTEB BIOSSES (reported)
- 83.604917042943
- MTEB ArxivClusteringP2P (reported)
- 47.508221208909
- MTEB ArxivClusteringS2S (reported)
- 42.046683825601
- MTEB BiorxivClusteringP2P (reported)
- 40.319238041671
- MTEB BiorxivClusteringS2S (reported)
- 37.552547125348
- MTEB AskUbuntuDupQuestions (reported)
- 74.37343358396
- MTEB Banking77Classification (reported)
- 86.702940492783
- MTEB CQADupstackAndroidRetrieval (reported)
- 30.567
- MTEB AmazonPolarityClassification (reported)
- 92.997097724052
- MTEB AmazonReviewsClassification (en) (reported)
- 52.98175784163
- MTEB AmazonCounterfactualClassification (en) (reported)
- 68.511015109986
- Added to our catalog
- 2026-10-02
Compare with any sentence-similarity model