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 1 year ago
  • Cleanups, better output during conversion
    KerfuffleV2 committed 1 year ago
  • Fix vocab space conversion logic
    KerfuffleV2 committed 1 year ago
  • More vocab conversion fixes
    KerfuffleV2 committed 1 year ago
  • Add description to converted GGUF files
    KerfuffleV2 committed 1 year ago
  • Improve help text, expand warning
    KerfuffleV2 committed 1 year ago
  • Allow specifying name and description for output GGUF
    KerfuffleV2 committed 1 year ago
  • Allow overriding vocab and hyperparams from original model metadata
    KerfuffleV2 committed 1 year ago
  • Use correct params override var name
    KerfuffleV2 committed 1 year ago
  • Fix wrong type size for Q8_K
    KerfuffleV2 committed 1 year ago
  • Set default value for gguf add_tensor raw_shape KW arg
    KerfuffleV2 committed 1 year ago
  • File
    convert-llama-ggmlv3-to-gguf.py
  • File
    gguf.py

Loading comments...