efficient-splade-VI-BT-large-doc
Efficient SPLADE model for passage retrieval. This architecture uses two distinct models for query and document inference. This is the doc one, please also download the query one (https://huggingface.co/naver/efficient-splade-VI-BT-large-query). For additional details, please visit: paper: https://dl.acm.org/doi/10.1145/3477495.3531833 code: https://github.com/naver/splade MRR@10 (MS MARCO dev) R@1000 (MS MARCO dev)...
Params
—
Context
512
Downloads 30d
427 K
Likes
23
Commercial use: not allowed · cc-by-nc-sa-4.0
Not gated
SAFETENSORS
1 languages
View on Hugging Face ↗
Download history
daily snapshots · 13 days429 K384 K
Oct 29Nov 2Nov 6Nov 10
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 | fp16 | 0.0 GB | 0.5 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
- DistilBertForMaskedLM
- Context length
- 512
- Vocabulary
- 30,522
- Licence
- cc-by-nc-sa-4.0
- First seen on the Hub
- 2022-07-05
- Training datasets
- ms_marco
- Added to our catalog
- 2026-10-29
Compare with any feature-extraction model