Fix #218 - unable to load OpenELM #228
Merged
Conversation
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
Collaborator
davidkoski
commented
Mar 7, 2025
davidkoski
commented
- OpenELM had optional layers that were always created
- see Qwen 2.5 fails to load: Key weight not found in Linear #214
davidkoski
commented
Mar 7, 2025
| @ModuleInfo(key: "q_norm") var qNorm: RMSNorm | ||
| @ModuleInfo(key: "k_norm") var kNorm: RMSNorm | ||
| @ModuleInfo(key: "q_norm") var qNorm: RMSNorm? | ||
| @ModuleInfo(key: "k_norm") var kNorm: RMSNorm? |
There was a problem hiding this comment.
These really should have been optional based on the config.
davidkoski
commented
Mar 7, 2025
| if !args.shareInputOutputLayers { | ||
| self._lmHead.wrappedValue = Linear( | ||
| args.numTransformerLayers, args.vocabularySize, bias: false) | ||
| } |
There was a problem hiding this comment.
Same -- this was the reported key.
awni
reviewed
Mar 10, 2025
| out = lmHead(out) | ||
| } else { | ||
| out = matmul(out, transformer.embedTokens.weight.T) |
There was a problem hiding this comment.
Oh, good call -- it looks like there are quite a few uses of the bare property. I will file an issue for the rest.
There was a problem hiding this comment.
Oops, and I forgot to commit/push that. Well, I will hit it with #231
awni
approved these changes
Mar 10, 2025
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Outdated suggestions cannot be applied.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.