Upload README.md with huggingface_hub

1fdf3e0 verified 9 days ago

1.67 kB

language:
  - en
  - ru
tags:
  - efficientrag
  - multi-hop-qa
  - token-classification
  - sequence-classification
  - deberta-v3
license: mit
base_model: microsoft/mdeberta-v3-base

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

Training data: Necent/efficientrag-labeler-training-data
Filter model: Necent/efficientrag-filter-mdeberta-v3-base
Paper: EfficientRAG (arXiv:2408.04259)

Necent
/

efficientrag-labeler-mdeberta-v3-base