Rev

Bredvige
ยท

AI & ML interests

None yet

Recent Activity

Organizations

None yet

Bredvige's activity

updated a Space about 2 months ago
reacted to grimjim's post with ๐Ÿ”ฅ 2 months ago
view post
Post
2792
I'm (finally) releasing a Python script that trims excess weights in Gemma2 full-weight models that bloated by ~1B parameters due to an early mergekit bug.
https://github.com/jim-plus/Gemma2-mergekit-remediation

I'd noticed something was off when merges of Gemma2 9B models ended up having ~10B parameters. The current mergekit package is fine, but there are still bloated models on HF that could stand to be fixed.

The script assumes that it will be run from the same directory as the model weights, and will trim the unnecessary lm_head.weight tensor and corresponding index entry.
  • 2 replies
ยท
updated a model 2 months ago
reacted to nroggendorff's post with ๐Ÿ˜” 2 months ago
view post
Post
3712
im so tired
  • 3 replies
ยท
updated a model 3 months ago
updated a model 3 months ago
New activity in NeoPy/Sonic 3 months ago

Upload Sonic.zip

#1 opened 3 months ago by
Bredvige