No application file
💻
Rev
Bredvige
·
AI & ML interests
None yet
Recent Activity
updated
a Space
2 days ago
Bredvige/RVC
updated
a model
15 days ago
Bredvige/Test
Organizations
None yet
Bredvige's activity
updated
a
Space
2 days ago
reacted to
grimjim's
post with 🔥
11 days ago
Post
2641
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.
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
updated
a
model
15 days ago
reacted to
nroggendorff's
post with 😔
17 days ago
Post
3667
im so tired
- 3 replies
liked
a
model
18 days ago
updated
a
model
19 days ago
liked
a
Space
19 days ago
updated
a
model
19 days ago
Upload Sonic.zip
#1 opened 19 days ago
by
Bredvige