Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Respect sequence_len in config for type: llama2_chat #926

Merged
merged 6 commits into from
Dec 12, 2023

Conversation

hamelsmu
Copy link
Collaborator

@hamelsmu hamelsmu commented Dec 9, 2023

It was hardcoded to 4096 I am not sure why? This updates it to pull from the config. Am I missing something? Maybe this type is deprecated and I shouldn't be using it?

cc: @winglian

It was hardcoded to `4096` I am not sure why?  This updates it to pull from the config. 

cc: @winglian
@hamelsmu
Copy link
Collaborator Author

hamelsmu commented Dec 9, 2023

I made an additional edit - It seems like sequence_len is a required value in the config, so it doesn't make sense to even override it. I also made sure that the pad_token is not hardcoded as well

If I were to guess I would think that this is a deprecated code path. But I really wanted this particular format

@hamelsmu hamelsmu merged commit f1de29d into axolotl-ai-cloud:main Dec 12, 2023
4 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

3 participants