|  | |
| This repo contains the model checkpoints for: | |
| - model family <b>pythia1-4b</b> | |
| - optimized with the loss <b>SFT+DPO</b> | |
| - aligned using the SHP, Anthropic HH and Open Assistant datasets. | |
| Please refer to our code repository which contains intructions for training your own HALOs and links to our model cards. | |
| If you find this repo or the technical paper useful in your research, please feel free to cite [our work](http://halos.github.io/): | |
| ``` | |
| @misc{ethayarajh2023halos, | |
| url = {http://halos.github.io/}, | |
| author = {Ethayarajh, Kawin and Xu, Winnie, and Jurafsky, Dan and Kiela, Douwe}, | |
| title = {Human-Centered Loss Functions (HALOs)}, | |
| publisher = {Contextual AI Blog}, | |
| year = {2023}, | |
| } | |
| ``` |