refine gguf rtn algorithm and fix bugs #630
change to float32 as it's quite important
0165a542
Merge branch 'main' of https://github.com/intel/auto-round
7698ebe4
Merge branch 'main' of https://github.com/intel/auto-round
51475928
fix bug
743cc64d
wenhuach21
changed the title refine gguf rtn algorithms and fix bugs refine gguf rtn algorithm and fix bugs 1 year ago
support for customized embedding and lm-head bits
c3ba6fd4
Update auto_round/utils.py
1ddd09ce
fix line too long issue
a2c2e731
Merge branch 'fix_0701' of https://github.com/intel/auto-round into f…
f735faca
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub