View on huggingface.co 

model = AutoAdapterModel.from_pretrained("mrm8488/t5-small-finetuned-squadv2")
model.load_adapter("carnival13/t5-small-hpqa-ia3lo", source="hf")

Description

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

An adapter for the mrm8488/t5-small-finetuned-squadv2 model that was trained on the hotpot_qa dataset.

This adapter was created for usage with the adapter-transformers library.

Usage

First, install adapter-transformers:

pip install -U adapter-transformers

Note: adapter-transformers is a fork of transformers that acts as a drop-in replacement with adapter support. More

Now, the adapter can be loaded and activated like this:

from transformers import AutoAdapterModel

model = AutoAdapterModel.from_pretrained("mrm8488/t5-small-finetuned-squadv2")
adapter_name = model.load_adapter("carnival13/t5-small-hpqa-ia3lo", source="hf", set_active=True)

Architecture & Training

Evaluation results

Citation

Properties

Pre-trained model
mrm8488/t5-small-finetuned-squadv2
Adapter type
Task
Prediction Head
  Yes
Task
Question Answering
Dataset
HotpotQA

Architecture

{
  "alpha": 1,
  "architecture": "lora",
  "attn_matrices": [
    "k",
    "v"
  ],
  "composition_mode": "scale",
  "dropout": 0.0,
  "init_weights": "ia3",
  "intermediate_lora": true,
  "output_lora": false,
  "r": 1,
  "selfattn_lora": true,
  "use_gating": false
}

Citations

Task
@inproceedings{yang2018hotpotqa,
  title={{HotpotQA}: A Dataset for Diverse, Explainable Multi-hop Question Answering},
  author={Yang, Zhilin and Qi, Peng and Zhang, Saizheng and Bengio, Yoshua and Cohen, William W. and Salakhutdinov, Ruslan and Manning, Christopher D.},
  booktitle={Conference on Empirical Methods in Natural Language Processing ({EMNLP})},
  year={2018}
}