llama.cpp
convert-hf : support bfloat16 conversion
#7158
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
7
Changes
View On
GitHub
convert-hf : support bfloat16 conversion
#7158
compilade
merged 7 commits into
master
from
compilade/lazy-bfloat16-convert-hf
convert-hf : support bfloat16 conversion
6f8d2800
gguf-py : flake8 fixes
59f5a27f
convert-hf : add missing space after comma
3801db12
ggerganov
approved these changes on 2024-05-09
mofosyne
added
performance
mofosyne
added
Review Complexity : Medium
Galunid
commented on 2024-05-09
convert-hf : get bit-exact same output as ./quantize
95930da3
convert-hf : add --outtype auto-f16
58b515ca
teleprint-me
commented on 2024-05-09
convert-hf : remove a semicolon because flake8 doesn't like it
d3d32a63
convert-hf : support outtype templating in outfile name
e0af2df6
compilade
merged
5a419926
into master
1 year ago
Login to write a write a comment.
Login via GitHub
Reviewers
ggerganov
Galunid
jart
bartowski1182
htdung167
teleprint-me
Assignees
No one assigned
Labels
performance
Review Complexity : Medium
Milestone
No milestone
Login to write a write a comment.
Login via GitHub