Update code-gpt article for W_o rollout and logits (no softmax)#5668
Open
ahmadbasyouni10 wants to merge 1 commit intofeature/ml-solution-articles-newfrom
Open
Update code-gpt article for W_o rollout and logits (no softmax)#5668ahmadbasyouni10 wants to merge 1 commit intofeature/ml-solution-articles-newfrom
ahmadbasyouni10 wants to merge 1 commit intofeature/ml-solution-articles-newfrom
Conversation
- Remove softmax from solution, return raw logits - Add W_o output projection to inner MHA class - Update all explanatory text: probabilities → logits - Update shape table and key takeaways Made-with: Cursor
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Updates the Code GPT solution article to match the W_o output projection rollout and the softmax → logits change:
output_proj = nn.Linear(model_dim, model_dim, bias=False)to the innerMultiHeadedSelfAttentionclassThis is the companion to the neetcode.io PR that rolls out W_o to the Code GPT solution/starter code and updates the expected test output.