llama.cpp
Add script to convert GGMLv3 LLaMA models to GGUF
#2682

Merged

Commits

First pass at converting GGMLv3 LLaMA models to GGUF

KerfuffleV2 committed 2 years ago
Cleanups, better output during conversion

KerfuffleV2 committed 2 years ago
Fix vocab space conversion logic

KerfuffleV2 committed 2 years ago
More vocab conversion fixes

KerfuffleV2 committed 2 years ago
Add description to converted GGUF files

KerfuffleV2 committed 2 years ago
Improve help text, expand warning

KerfuffleV2 committed 2 years ago
Allow specifying name and description for output GGUF

KerfuffleV2 committed 2 years ago
Allow overriding vocab and hyperparams from original model metadata

KerfuffleV2 committed 2 years ago
Use correct params override var name

KerfuffleV2 committed 2 years ago
Fix wrong type size for Q8_K

KerfuffleV2 committed 2 years ago
Set default value for gguf add_tensor raw_shape KW arg

KerfuffleV2 committed 2 years ago