Repository navigation
Conversation
Owner
|
The manifest is legal (358 units, ~19.2 GiB estimated RAM vs 19.6 for the baseline), but it can't be scored yet. The validator isn't running, so pr-evaluator is queued. Leaving this open until the validator is set up. |
ikeige-coder
added
good first issue
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 join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Q4_K body with Q3_K MLPs in layers 16-67 to buy RAM back, while the quantization-sensitive parts stay precise: MLPs in layers 0-5 and 78-83 at Q6_K, all full-attention projections at Q6_K, GDN output projections at Q5_K, lm_head at Q6_K.
excore check: legal, 358 units, about 19.2 GiB estimated RAM (baseline V0: about 19.6 GiB).