llama : gemma3 : use output tensor if it exists in model weight #12506
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
ggerganov
approved these changes
Mar 22, 2025
Ivy233
pushed a commit
to Ivy233/llama.cpp
that referenced
this pull request
Mar 23, 2025
…-org#12506) * llama : gemma3 : use output tensor if it exists in model weight * also add to the llm_tensor_names
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Outdated suggestions cannot be applied.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.
Fix #12483
Some fine-tuned models have it, we should include it in the converted model to make sure it runs correctly.
While we can remove this as suggested in the issue, I think it's not worth the risk. We are not sure if the fine tuning code produces different token_embd and lm_head tensor or not.