Downloads · 30 days
4
3% of all-time downloads
rai-nemotron3-nano-n3sw_b4fp2
tzchen07/rai-nemotron3-nano-n3sw_b4fp2
rai-nemotron3-nano-n3sw_b4fp2 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: nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16 - Method: full-SFT (final merged model; optimizer states not saved by the trainer) - Arm / iteration: n3swb4fp2 / n3sweet - Contents: model weights (root) · eval/ = raw in…
All-time downloads
157
Public
Parameters
4B
11 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors10.9 GB · 99%
Parameter types
How the weights are stored.
BF162.5B · 62%
Model card
From the Hugging Face model README
n3sw_b4fp2 — RAI safety classifier (Atlassian responsible-ai campaign)
- Base:
nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16 - Method: full-SFT (final merged model; optimizer states not saved by the trainer)
- Arm / iteration:
n3sw_b4fp2/n3sweet - 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: ....
- Created
- Jul 13, 2026
- Updated
- Jul 13, 2026