Published June 5, 2023
| Version v2
Dataset
Open
Fine-Grained Human Feedback Gives Better Rewards for Language Model Training
Authors/Creators
- 1. University of Washington
- 2. Allen Institute for AI
- 3. University of Washington, Allen Institute for AI
Description
QA-Feedback used in the paper: Fine-Grained Human Feedback Gives Better Rewards for Language Model Training
Files
dev.json
Files
(64.2 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:24c35337c514c0322888be9753a6aba6
|
3.3 MB | Preview Download |
|
md5:25f5c85fe1f040e49ecd0bfa6d88c2c0
|
3.3 MB | Preview Download |
|
md5:c06fb0601640f1915e8318debf3716e7
|
2.5 kB | Preview Download |
|
md5:666c1bcba0b9fa1cc28012576ae08a2f
|
6.2 MB | Preview Download |
|
md5:1f16269b6fcbf73a7bcacbe967336849
|
25.7 MB | Preview Download |
|
md5:fcace67673438ec8c8cafd516dd9f1d2
|
6.8 MB | Preview Download |
|
md5:4949f2fd889057498b0871cd4efef5bb
|
19.0 MB | Preview Download |