| | --- |
| | license: cc-by-4.0 |
| | --- |
| | |
| | # GenRead (MergeDPR): FiD model trained on TQA |
| |
|
| | -- This is the model checkpoint of GenRead [2], based on the T5-3B and trained on the TriviaQA [1]. |
| |
|
| | -- Hyperparameters: 8 x 80GB A100 GPUs; batch size 16; AdamW; LR 5e-5; best dev at 9000 steps |
| |
|
| | References: |
| |
|
| | [1] TriviaQA: A Large Scale Dataset for Reading Comprehension and Question Answering. ACL 2017 |
| |
|
| | [2] Generate rather than Retrieve: Large Language Models are Strong Context Generators. arXiv 2022 |
| |
|
| | ## Model performance |
| |
|
| | We evaluate it on the TriviaQA dataset, the EM score is 74.41. |
| |
|
| |
|
| | <a href="https://huggingface.co/exbert/?model=bert-base-uncased"> |
| | <img width="300px" src="https://cdn-media.huggingface.co/exbert/button.png"> |
| | </a> |
| | --- |
| | license: cc-by-4.0 |
| | --- |
| | |
