Assume tied weights if lm_head/output weights is missing. #5824
Conversation
This file contains 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
|
@cebtenzzre . Great, I did not see those changes, and this change was intended to be a quick work-around until tied-weights are more properly supported, which sounds like is happening. I will look at those changes. |
This is to support model configurations with "tie_word_embeddings" set to true.
|
@cebtenzzre, Change updated in llama.cpp, with LLAMA tied-weights now being similar to other tied-weights. |
ggerganov
approved these changes
Mar 8, 2024
hazelnutcloud
pushed a commit
to hazelnutcloud/llama.cpp
that referenced
this pull request
Mar 10, 2024
…rganov#5824) This is to support model configurations with "tie_word_embeddings" set to true. Co-authored-by: Don Mahurin <2797413+dmahurin@users.noreply.github.com>
NeoZhangJianyu
pushed a commit
to NeoZhangJianyu/llama.cpp
that referenced
this pull request
Mar 12, 2024
…rganov#5824) This is to support model configurations with "tie_word_embeddings" set to true. Co-authored-by: Don Mahurin <2797413+dmahurin@users.noreply.github.com>
jordankanter
pushed a commit
to jordankanter/llama.cpp
that referenced
this pull request
Mar 13, 2024
…rganov#5824) This is to support model configurations with "tie_word_embeddings" set to true. Co-authored-by: Don Mahurin <2797413+dmahurin@users.noreply.github.com>
hodlen
pushed a commit
to hodlen/llama.cpp
that referenced
this pull request
Apr 1, 2024
…rganov#5824) This is to support model configurations with "tie_word_embeddings" set to true. Co-authored-by: Don Mahurin <2797413+dmahurin@users.noreply.github.com>
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Outdated suggestions cannot be applied.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 supports model configurations with "tie_word_embeddings", by using the embd_tokens weights if output/lm_head weights are missing (as they will be when weights are tied).
With this change, a tied model like the following can be converted to gguf.
https://huggingface.co/BEE-spoke-data/smol_llama-81M-tied