OpenAssistant training changes [not intended for merging] #31
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…rameter in dataset config)
|
Great to see that most of the changes are now already part of the main repo. Once #40 has been merged this PR can be closed. |
andreaskoepf
force-pushed
the
local_changes
branch
2 times, most recently
from
32b421b to
b349025
Compare
andreaskoepf
force-pushed
the
local_changes
branch
2 times, most recently
from
460f107 to
9f21967
Compare
|
Closing this as Instruction Tuning PR is now ready to be merged. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR is for informational purposes to show the diff of local changes that I made for training on Open-Assistant data. Not intended for merge.
The content of the OA folder has now become a PR (LAION-AI/Open-Assistant#3654), it does not contain dependencies to megatron code (I created slightly modified copies of indexed_dataset.py and tokenizer.py to remove dependencies) but it is dependent on the
model_trainingmodule of Open-Assistant.Main changes I made which have not bee merged:
InstructionDatasetclassPlease let me know what you think could become valuable parts for the main project. I would be happy to create a clean PR for it.