Downloads · 30 days
28
4% of all-time downloads
TheDrummer/Gemma-3-R1-4B-v1
Gemma-3-R1-4B-v1 is a machine learning model from TheDrummer. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
28
4% of all-time downloads
All-time downloads
748
Public
Parameters
4.3B
8.6 GB on disk
Likes
16
Public
Click a slice to open those files.
.safetensors8.6 GB · 100%
From the Hugging Face model README

You'll probably need to prefill <think> at the start of the assistant turn. Since it's not a special token, you can get creative with the reasoning tags with modifications like <evil_think> or <creative_think>.
Gemma 3 4B reasoning tune that unlocks more capabilities and less positivity! Should be vision capable.
Gemma 4B constantly surprises me for its size, this one's a blast. I'm impressed by this little fella.
Wow that is surprisingly deep. It actually is being witty and unique in it's prose not the usual gemma prose at all. Maybe Drummer really did create AGI.
I tried another swipe and it just shit out the index.html file, css, and javascript in one shot. Even has neat little animations when you click on stuff.

gemma-r1/4b/config-v1b