llama.cpp
Gguf: write tensors in a single pass
#2644
Merged

Gguf: write tensors in a single pass #2644

ggerganov merged 12 commits into gguf from gguf-write-single-pass
monatis
monatis gguf : single pass for writing tensors + refactoring writer
f31e9230
monatis gguf : single pass for writing tensors + refactoring writer
dce07c31
monatis gguf : single pass for writing tensors + refactoring writer
5f97a48f
monatis
monatis
ggerganov
monatis gguf : fix conflicts
2f8fc92d
monatis gguf : style fixes in simple conversion script
22c61c5b
monatis
klosax
monatis
klosax
klosax
monatis gguf : refactor gptneox conversion script
9f02694c
monatis gguf : rename h5 to hf (for HuggingFace)
f7170417
klosax
monatis gguf : refactor pth to gguf conversion script
1d93d04c
monatis
monatis gguf : rm file_type key and method
4dbce7d0
ggerganov gguf.py : fix vertical alignment
e426b3cf
ggerganov Merge branch 'gguf' into gguf-write-single-pass
307e09cd
ggerganov gguf.py : indentation
6a9e6375
ggerganov
ggerganov approved these changes on 2023-08-17
ggerganov ggerganov merged fc3a5232 into gguf 2 years ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone