stepfun-ai/GOT-OCR2_0
Image-Text-to-Text
•
Updated
•
727k
•
1.32k
Om
asach
AI & ML interests
None yet
Recent Activity
liked
a model
6 days ago
stepfun-ai/GOT-OCR2_0
liked
a model
6 days ago
microsoft/Phi-3.5-vision-instruct
liked
a Space
6 days ago
opencompass/open_vlm_leaderboard
Organizations
asach's activity
liked
2
models
6 days ago
liked
2
Spaces
6 days ago
liked
2
models
6 days ago
reacted to
grimjim's
post with ❤️
6 days ago
Post
2589
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
2 months ago
liked
a
Space
2 months ago
liked
a
model
2 months ago
liked
a
model
3 months ago
liked
a
model
4 months ago
liked
a
model
6 months ago
liked
a
Space
8 months ago
liked
a
model
10 months ago
liked
a
dataset
10 months ago
liked
a
Space
11 months ago
liked
a
model
11 months ago
updated
a
dataset
11 months ago