Task Adapters

Hotpot Qa

HotpotQA is a new dataset with 113k Wikipedia-based question-answer pairs with four key features: (1) the questions require finding and reasoning over multiple supporting documents to answer; (2) the questions are diverse and not constrained to any pre-existing knowledge bases or knowledge schemas; (3) we provide sentence-level supporting facts required for reasoning, allowingQA systems to reason with strong supervisionand explain the predictions; (4) we offer a new type of factoid comparison questions to testQA systems’ ability to extract relevant facts and perform necessary comparison.

🤗 huggingface.co

AdapterHub/bert-base-uncased-pf-hotpotqa bert-base-uncased

huggingface.co Head:

# Adapter `AdapterHub/bert-base-uncased-pf-hotpotqa` for bert-base-uncased An [adapter](https://adapterhub.ml) for the `bert-base-uncased` model that was trained on the...

AdapterHub/roberta-base-pf-hotpotqa roberta-base

huggingface.co Head:

# Adapter `AdapterHub/roberta-base-pf-hotpotqa` for roberta-base An [adapter](https://adapterhub.ml) for the `roberta-base` model that was trained on the...

carnival13/t5-small-hpqa-ia3lo mrm8488/t5-small-finetuned-squadv2

huggingface.co Head:

# Adapter `carnival13/t5-small-hpqa-ia3lo` for mrm8488/t5-small-finetuned-squadv2 An [adapter](https://adapterhub.ml) for the `mrm8488/t5-small-finetuned-squadv2` model that was trained on the...

carnival13/t5-small-hpqa-lora mrm8488/t5-small-finetuned-squadv2

huggingface.co Head:

# Adapter `carnival13/t5-small-hpqa-lora` for mrm8488/t5-small-finetuned-squadv2 An [adapter](https://adapterhub.ml) for the `mrm8488/t5-small-finetuned-squadv2` model that was trained on the...