llama.cpp
gguf-py : simplify support for quant types
#8838
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
5
Changes
View On
GitHub
gguf-py : simplify support for quant types
#8838
compilade
merged 5 commits into
master
from
compilade/gguf-py-quants-class
gguf-py : use classes for quants
1ac1a791
convert_hf : simplify internal quantization type selection
5e27e7e1
gguf-py : fix flake8 lint
861265b9
gguf-py : fix BF16 numpy view type
e82ff5a3
compilade
added
refactoring
compilade
added
Review Complexity : Low
compilade
added
python
compilade
commented on 2024-08-02
gguf-py : remove LlamaFileTypeMap
229c35cb
ggerganov
approved these changes on 2024-08-04
compilade
merged
3a14e003
into master
1 year ago
Login to write a write a comment.
Login via GitHub
Reviewers
ggerganov
Assignees
No one assigned
Labels
refactoring
Review Complexity : Low
python
Milestone
No milestone
Login to write a write a comment.
Login via GitHub