xwinxu commited on
Commit
fb6f7f2
1 Parent(s): c25f366

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -40,6 +40,9 @@ Chocolate cake.
40
  ```
41
  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.
42
 
 
 
 
43
  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.
44
 
45
  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):
 
40
  ```
41
  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.
42
 
43
+ For models trained with our conditional variant, the tokenizers have additional tokens `<|good|>` and `<|bad|>` included in the embeddings.
44
+ To generate with these control tokens in the context, postpend either to the prompt.
45
+
46
  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.
47
 
48
  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):