llama.cpp
convert.py : Update to support 70B HF format model files
#2427

Merged

convert.py : Update to support 70B HF format model files #2427

KerfuffleV2 merged 3 commits into ggml-org:master from master

convert.py : fix llama 2 70b conversion from Huggingface

e15a67d6

convert.py : fix of type and shorter code

01d16e1a

convert.py : shorten and simplify permute

9442c34f

KerfuffleV2 approved these changes on 2023-07-27

klosax approved these changes on 2023-07-27

KerfuffleV2 merged 7c529ced into master 2 years ago

Reviewers

klosax

KerfuffleV2

Assignees

No one assigned

Labels

None yet

Milestone

No milestone