This repository was archived by the owner on Jun 24, 2024. It is now read-only.
Merged
Conversation
added 2 commits
March 23, 2023 06:17
Collaborator
|
Thanks for the PR! But I think this implements the same changes as #61? 😅 |
Author
Collaborator
|
Right! It was easy to miss 😄 Now that #61 was just merged, would you mind updating your changes on top of this? Happy to merge the PR even if it's just the buffer size change |
This reverts commit 733ef07.
Author
|
@setzer22 should be done ^^ |
setzer22
approved these changes
Mar 23, 2023
Collaborator
setzer22
left a comment
setzer22
left a comment
There was a problem hiding this comment.
Thanks! I just added a little explanatory comment, we should be good to merge
ghost
changed the title
Closed
This file contains hidden or 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
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Import fixes for magic (#59 (comment)).
Fix 65B model error (#65).
A better fix for the memory allocation issue is probably possible, but this works without any impact on memory for any model (tested 7B: 4G, 13B: 5G, 30B: 20G, 65B: 39G).