Teklia/doc-ufcn-generic-historical-line
Image Segmentation
•
Updated
•
19
Om
asach
AI & ML interests
None yet
Recent Activity
liked
a model
19 days ago
Teklia/doc-ufcn-generic-historical-line
liked
a model
about 1 month ago
stepfun-ai/GOT-OCR2_0
liked
a model
about 1 month ago
microsoft/Phi-3.5-vision-instruct
Organizations
asach's activity
liked
a
model
19 days ago
liked
2
models
about 1 month ago
liked
2
Spaces
about 1 month ago
liked
2
models
about 1 month ago
reacted to
grimjim's
post with ❤️
about 1 month ago
Post
2773
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
liked
2
models
3 months ago
liked
a
Space
3 months ago
liked
a
model
3 months ago
liked
a
model
4 months ago
liked
a
model
5 months ago
liked
a
model
7 months ago
liked
a
Space
9 months ago
liked
a
model
11 months ago
liked
a
dataset
11 months ago
liked
a
Space
12 months ago
liked
a
model
about 1 year ago
