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

Merged

Add script to convert GGMLv3 LLaMA models to GGUF #2682

ggerganov merged 11 commits into ggml-org:gguf from KerfuffleV2:feat-convert-ggml-to-gguf

KerfuffleV2 marked this pull request as ready for review 2 years ago

Green-Sky commented on 2023-08-20

klosax commented on 2023-08-20

First pass at converting GGMLv3 LLaMA models to GGUF

8afc1ef3

Cleanups, better output during conversion

f7e61fd1

Fix vocab space conversion logic

08959c88

More vocab conversion fixes

8083e20d

Add description to converted GGUF files

ff251343

Improve help text, expand warning

80912f07

Allow specifying name and description for output GGUF

f56db216

Allow overriding vocab and hyperparams from original model metadata

e854cd7d

Use correct params override var name

996aaca1

Fix wrong type size for Q8_K

f68aef54

KerfuffleV2 force pushed to f68aef54 2 years ago

ggerganov approved these changes on 2023-08-21

Set default value for gguf add_tensor raw_shape KW arg

05477604

ggerganov merged e06cbcee into gguf 2 years ago

KerfuffleV2 deleted the feat-convert-ggml-to-gguf branch 2 years ago

Reviewers

ggerganov

klosax

Green-Sky

Assignees

No one assigned

Labels

None yet

Milestone

No milestone