File size: 1,824 Bytes
83696b5 c955da5 359f6c6 5bd56e4 c955da5 359f6c6 c2b4109 2b849e5 5bd56e4 82e5229 34fac78 359f6c6 8fa9d4d 359f6c6 8fa9d4d 359f6c6 8fa9d4d 359f6c6 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 |
---
license: apache-2.0
datasets:
- stanfordnlp/SHP
- Anthropic/hh-rlhf
- OpenAssistant/oasst1
language:
- en
metrics:
- accuracy
tags:
- human feedback
- rlhf
- preferences
- alignment
- HALO
- halos
- dpo
- rl
---
This repo contains the model checkpoints for:
- model family <b>EleutherAI/pythia-6.9b</b>
- optimized with the loss <b>KTO</b>
- aligned using the SHP, Anthropic HH and Open Assistant datasets.
To prompt Archangel models, ensure that the format is consistent with that of TuluV2.
For example, a prompt should be formatted as follows, where `<|user|>` corresponds to the human's role and `<|assistant|>` corresponds to the LLM's role.
The human should speak first:
```
<|user|>
Hi! I'm looking for a cake recipe.
<|assistant|>
What kind of cake?
<|user|>
Chocolate cake.
<|assistant|>
```
Note that a beginning-of-sequence (BOS) token is automatically added by all Archangel models during tokenization and does not have to be added by you. No end-of-sequence (EOS) token is added to the prompt.
Please refer to our [code repository](https://github.com/ContextualAI/HALOs) or [blog](https://contextual.ai/better-cheaper-faster-llm-alignment-with-kto/) 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](https://github.com/ContextualAI/HALOs/blob/main/assets/report.pdf):
```
@techreport{ethayarajh2023halos,
author = {Ethayarajh, Kawin and Xu, Winnie, and Jurafsky, Dan and Kiela, Douwe},
title = {Human-Centered Loss Functions (HALOs)},
institution = {Contextual AI},
note = {https://github.com/ContextualAI/HALOs/blob/main/assets/report.pdf},
year = {2023},
}
``` |