llama.cpp
convert-hf : support bfloat16 conversion
#7158
Merged

convert-hf : support bfloat16 conversion #7158

compilade
compilade convert-hf : support bfloat16 conversion
6f8d2800
compilade gguf-py : flake8 fixes
59f5a27f
compilade convert-hf : add missing space after comma
3801db12
ggerganov
ggerganov approved these changes on 2024-05-09
ggerganov
mofosyne mofosyne added performance
mofosyne mofosyne added Review Complexity : Medium
bartowski1182
compilade
Galunid
Galunid commented on 2024-05-09
compilade convert-hf : get bit-exact same output as ./quantize
95930da3
compilade convert-hf : add --outtype auto-f16
58b515ca
teleprint-me
teleprint-me commented on 2024-05-09
compilade convert-hf : remove a semicolon because flake8 doesn't like it
d3d32a63
compilade convert-hf : support outtype templating in outfile name
e0af2df6
bartowski1182
compilade
bartowski1182
jart
bartowski1182
compilade compilade merged 5a419926 into master 1 year ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone