Downloads · 30 days
2
1% of all-time downloads
rai-gemma4-e2b-g4bal_a
tzchen07/rai-gemma4-e2b-g4bal_a
rai-gemma4-e2b-g4bal_a is a machine learning model from tzchen07. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
- Base: google/gemma-4-E2B-it - Method: full-SFT (final merged model; optimizer states not saved by the trainer) - Arm / iteration: g4bala / g4bal - Contents: model weights (root) · eval/ = raw inference outputs on th…
All-time downloads
146
Public
Parameters
5B
10.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors10.1 GB · 100%
At a glance
- Model type
- gemma4_text
- Access
- Public
- Created
- Jul 13, 2026
- Updated
- Jul 13, 2026
- SHA
- c744c1fb
Model card
From the Hugging Face model README
g4bal_a — RAI safety classifier (Atlassian responsible-ai campaign)
- Base:
google/gemma-4-E2B-it - Method: full-SFT (final merged model; optimizer states not saved by the trainer)
- Arm / iteration:
g4bal_a/g4bal - Contents: model weights (root) ·
eval/= raw inference outputs on the eval sets (v14, hello_v2_filtered, v200, robustnessv2) under policy prompts v3_1b / v3_1c ·artifacts/= training log - Eval-inference files uploaded: 10
Binary content-safety classifier; output = two lines Verdict: <category> / Reason: ....
- Type
- gemma4_text
- Created
- Jul 13, 2026
- Updated
- Jul 13, 2026