Model reference · open weights

dpr-question_encoder-single-lfqa-wiki

Available as managed deployment Embeddings vblagoje · community Embeddings 1 variants 985 dl/mo

dpr-question_encoder-single-lfqa-wiki is an open-weight embedding model from vblagoje. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

Released byvblagoje
TypeEmbedding models
TaskEmbeddings
Parameters (lead)110M
Context512 tokens
Runs withtransformers
Released2022-03-02
Popularity985 downloads / month
LicenceOpen weights

About

What dpr-question_encoder-single-lfqa-wiki is

Introduction

The question encoder model based on DPRQuestionEncoder architecture. It uses the transformer's pooler outputs as question representations. See blog post for more details.

Read the full model card

Training

We trained vblagoje/dpr-question_encoder-single-lfqa-wiki using FAIR's dpr-scale in two stages. In the first stage, we used PAQ based pretrained checkpoint and fine-tuned the retriever on the question-answer pairs from the LFQA dataset. As dpr-scale requires DPR formatted training set input with positive, negative, and hard negative samples - we created a training file with an answer being positive, negatives being question unrelated answers, while hard negative samples were chosen from answers on questions between 0.55 and 0.65 of cosine similarity. In the second stage, we created a new DPR training set using positives, negatives, and hard negatives from the Wikipedia/Faiss index created in the first stage instead of LFQA dataset answers. More precisely, for each dataset question, we queried the first stage Wikipedia Faiss index and subsequently used SBert cross-encoder to score questions/answers (passage) pairs with topk=50. The cross-encoder selected the positive passage with the highest score, while the bottom seven answers were selected for hard-negatives. Negative samples were again chosen to be answers unrelated to a given dataset question. After creating a DPR formatted training file with Wikipedia sourced positive, negative, and hard negative passages, we trained DPR-based question/passage encoders using dpr-scale.

Performance

LFQA DPR-based retriever (vblagoje/dpr-question_encoder-single-lfqa-wiki and vblagoje/dpr-ctx_encoder-single-lfqa-wiki) slightly underperform 'state-of-the-art' Krishna et al. "Hurdles to Progress in Long-form Question Answering" REALM based retriever with KILT benchmark performance of 11.2 for R-precision and 19.5 for Recall@5.

Usage

from transformers import DPRContextEncoder, DPRContextEncoderTokenizer

model = DPRQuestionEncoder.from_pretrained("vblagoje/dpr-question_encoder-single-lfqa-wiki").to(device)
tokenizer = AutoTokenizer.from_pretrained("vblagoje/dpr-question_encoder-single-lfqa-wiki")

input_ids = tokenizer("Why do airplanes leave contrails in the sky?", return_tensors="pt")["input_ids"]
embeddings = model(input_ids).pooler_output

Author

From the published model card. Full card on the HuggingFace links in the sidebar.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys dpr-question-encoder-single-lfqa-wiki for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (dpr-question-encoder-single-lfqa-wiki below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/embeddings \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"dpr-question-encoder-single-lfqa-wiki","input":"text to embed"}'

Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms