xwinxu commited on
Commit
3f91a79
1 Parent(s): 49ef62f

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -26,6 +26,9 @@ This repo contains the model checkpoints for:
26
  - optimized with the loss <b>SFT+PPO</b>
27
  - aligned using the SHP, Anthropic HH and Open Assistant datasets.
28
 
 
 
 
29
  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.
30
 
31
  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):
 
26
  - optimized with the loss <b>SFT+PPO</b>
27
  - aligned using the SHP, Anthropic HH and Open Assistant datasets.
28
 
29
+ To prompt archangel models, ensure that the format is consistent with that of TuluV2, i.e. `"<s>\n<|user|>\n" + <prompt> + "\n<|assistant|>\n</s>"`.
30
+ Note that the BOS / EOS tokens should be excluded if automatically added by your tokenizer during batch collation.
31
+
32
  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.
33
 
34
  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):