Downloads · 30 days
33
5% of all-time downloads
lmloss-opt-rm-1.3b
HiTZ/lmloss-opt-rm-1.3b
lmloss-opt-rm-1.3b is a text generation model from HiTZ. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
This is a fine tuned OPT 1.3b model for reward modelling. The finetuning has been done on top of the full SLF5K dataset following the method presented in the paper Training Language Models with Language Feedback at Sc…
All-time downloads
653
Public
Repo size
2.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin2.6 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- mit
- Model type
- opt
- Access
- Public
- Created
- Jan 23, 2023
- Updated
- Apr 7, 2023
- SHA
- 580bb860
Try a prompt
Model card
From the Hugging Face model README
LM Loss OPT RM
This is a fine tuned OPT 1.3b model for reward modelling. The finetuning has been done on top of the full SLF5K dataset following the method presented in the paper Training Language Models with Language Feedback at Scale. The main results can be seen in the following table:
| Model | # Params | Validation Accuracy (in %) |
|---|---|---|
| OPT LM Loss | 13B | 73.4 +/- 1.9 |
| OPT LM Loss | 1.3B | 69.6 +/- 2.0 |
| OPT RM Loss | 13B | 71.8 +/- 2.0 |
If using this model, please cite the following paper:
@article{scheurer2023training,
title={Training Language Models with Language Feedback at Scale},
author={Scheurer, J{\'e}r{\'e}my and Campos, Jon Ander and Korbak, Tomasz and Chan, Jun Shern and Chen, Angelica and Cho, Kyunghyun and Perez, Ethan},
journal={arXiv preprint arXiv:2303.16755},
year={2023}
}
- Task
- Text Generation
- Library
- transformers
- Type
- opt
- License
- mit
- Languages
- en
- Created
- Jan 23, 2023
- Updated
- Apr 7, 2023