Closed
Conversation
Refer to another commit cause you can't find RMSNorm impl in the current mlx-llm repo (it's replaced by mlx fast impl).
* Possible typo in week1-01-attention Hello, was going through the book! I'm not 100% sure of this, but after going through the tests for day1-task2, it looks like the w_qkv matrices and w_o matrix have their shape reversed. I confirmed by checking the mlx.nn.layers.linear.Linear weight, which is of shape `[Output, Input]`. Since w_qkv's output is HxD and input is E, the shape should be `[H x D, E]`. * Oops fix another typo
This reverts commit 4db096e.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 revert "fix: Use non-traditional RoPE in Qwen2 test case. (#56)".
The original test case corresponds to the correct implementation, which use non-traditional RoPE, should not be modified