Downloads · 30 days
13
12% of all-time downloads
efficientrag-labeler-mdeberta-v3-base
Necent/efficientrag-labeler-mdeberta-v3-base
efficientrag-labeler-mdeberta-v3-base is a token classification model from Necent. Use it when you need labels on individual words, such as names. The card lists the license as mit.
Labeler component of EfficientRAG — dual-headed DeBERTa model for multi-hop retrieval.
All-time downloads
109
Public
Parameters
279M
13.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt8.9 GB · 61%
At a glance
- Task
- Token Classification
- License
- mit
- Model type
- deberta-v2
- Access
- Public
- Created
- Mar 26, 2026
- Updated
- Apr 30, 2026
- SHA
- d0f8192d
Try a prompt
Base models
Model card
From the Hugging Face model README
EfficientRAG Labeler (mdeberta-v3-base)
Labeler component of EfficientRAG — dual-headed DeBERTa model for multi-hop retrieval.
What it does
Given a query and a retrieved chunk, the Labeler:
- Sequence classification: Is this chunk relevant (
CONTINUE) or irrelevant (TERMINATE)? - Token classification: Which tokens in the chunk are useful for answering?
Architecture
- Base:
microsoft/mdeberta-v3-base(86M params, multilingual) - Custom dual head:
DebertaForSequenceTokenClassification- Token head: binary per-token (useful/useless)
- Sequence head: binary per-chunk (CONTINUE/TERMINATE)
Training
| Data | 30,818 samples (HotpotQA EN + Dragon-derec RU) |
| Epochs | 2 |
| Batch size | 4 |
| LR | 5e-6 |
| Max length | 384 |
| Hardware | Apple M3 Pro, ~3.4 hours |
Usage
Results on DRAGON benchmark
| Metric | Baseline | EfficientRAG | Delta |
|---|---|---|---|
| MRR (multi-hop) | 0.736 | 0.798 | +0.062 |
| MRR (overall) | 0.783 | 0.822 | +0.040 |
| Precision | 0.187 | 0.582 | +0.395 |
Related
- Training data: Necent/efficientrag-labeler-training-data
- Filter model: Necent/efficientrag-filter-mdeberta-v3-base
- Paper: EfficientRAG (arXiv:2408.04259)
- Task
- Token Classification
- Type
- deberta-v2
- License
- mit
- Languages
- en, ru
- Created
- Mar 26, 2026
- Updated
- Apr 30, 2026