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 

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 09:30:52 +01:00
parent 2aa45ef9e3
commit cb1f80704c
No known key found for this signature in database
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
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
The idea is that the makefile targets and scripts here can be used in the
development/conversion process assisting with things like: