happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

model-conversion : add note about verifying previous models (#18082) 

This commit adds a note to the README in the model-conversion
examples, advising developers to verify that previous versions of models
pass logits verification before adding new models from the same family.
This commit is contained in:
Daniel Bevenius 2025-12-16 11:17:40 +01:00 committed by GitHub
parent db81d5ec4b
commit 9963b81f63
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 7 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
examples/model-conversion/README.md
View File

@ -10,6 +10,13 @@ and in some cases perplexity checked of the quantized model. And finally the
model/models need to the ggml-org on Hugging Face. This tool/example tries to model/models need to the ggml-org on Hugging Face. This tool/example tries to
help with this process. help with this process.
> 📝 **Note:** When adding a new model from an existing family, verify the
> previous version passes logits verification first. Existing models can have
> subtle numerical differences that don't affect generation quality but cause
> logits mismatches. Identifying these upfront whether they exist in llama.cpp,
> the conversion script, or in an upstream implementation, can save significant
> debugging time.
### Overview ### Overview
The idea is that the makefile targets and scripts here can be used in the The idea is that the makefile targets and scripts here can be used in the
development/conversion process assisting with things like: development/conversion process assisting with things like: