Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

imatrix : fix wname for mul_mat_id ops #6271

Merged
merged 2 commits into from Mar 24, 2024
Merged

Conversation

ggerganov
Copy link
Owner

Fix a regression for computing the imatrix of MoE models introduced in #6083

The wname has to be updated with the expert weight name. Otherwise, master stops early:

Oops: inconsistent size for blk.0.ffn_down.0.weight,  (view) (4096 vs 14336)

Repro:

./imatrix -m ./models/mixtral-8x7b-32k-fast/ggml-model-f16.gguf -f build/wikitext-2-raw/wiki.train.raw

@ggerganov ggerganov merged commit a0e584d into master Mar 24, 2024
57 of 58 checks passed
@ggerganov ggerganov deleted the gg/fix-imatrix-mm-id-name branch March 24, 2024 14:18
probable1333 pushed a commit to probable1333/koboldcpp-rocm that referenced this pull request Mar 25, 2024
* imatrix : fix wname for mul_mat_id ops

* also filter tensor names in mul_mat_id ops

---------

Co-authored-by: slaren <slarengh@gmail.com>
hodlen pushed a commit to hodlen/llama.cpp that referenced this pull request Apr 1, 2024
* imatrix : fix wname for mul_mat_id ops

* also filter tensor names in mul_mat_id ops

---------

Co-authored-by: slaren <slarengh@gmail.com>
hodlen pushed a commit to hodlen/llama.cpp that referenced this pull request Apr 3, 2024
* imatrix : fix wname for mul_mat_id ops

* also filter tensor names in mul_mat_id ops

---------

Co-authored-by: slaren <slarengh@gmail.com>
tybalex pushed a commit to tybalex/function.cpp that referenced this pull request Apr 17, 2024
* imatrix : fix wname for mul_mat_id ops

* also filter tensor names in mul_mat_id ops

---------

Co-authored-by: slaren <slarengh@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

2 participants