Commits on Jun 12, 2024

1. Allow "weight: 0" in messages to mask them …

   Allow in message objects the additional key `weight`, which can be set
   to 0 (or 1) to cause that message to be masked out (or left unmasked)
   for training (similar to [1]). This is helpful for training the model to be robust and
   capable of error recovery upon a bad assistant message.
   A missing `weight` key defaults to weight 1, to guarantee downward compatibility.
   
   Extend `src/axolotl/prompters.py::_build_result` and
   `src/axolotl/prompt_strategies/sharegpt.py::SimpleShareGPTPromptTokenizingStrategy::get_conversation_thread`
   to return the turns with weights as additional tuple element.
   Do this in axolotl directly instead of modifying `fastchat.conversation`'s `Conversation`.
   
   Extend `src/axolotl/prompt_tokenizers.py::tokenize_prompt` to mask out tokens when weight is set to 0.
   
   Extend `tests/prompt_strategies/test_sharegpt.py` with four test cases that contain messages with `weight` keys.
   Switch names `test_w_train_on_input` and `test_no_train_on_input`.
   
   [1]: https://github.com/mistralai/mistral-finetune

   

   DavidFarago committed Jun 12, 2024
   Configuration menu

   • View commit details
   • Copy full SHA for 14428da
   • Browse repository at this point

   Copy the full SHA

   14428da View commit details

   Browse the repository at this point in the history