senaro
/

atlas-gemma4-31b-trm7

Image-Text-to-Text

Model card Files Files and versions

Experimental Model NOT POST-TRAINED, SFT OR DPO

The purpose of this model was to produce a visualisation of the loss landscape for the Gemma4 31B model.

Downloads last month: 62

Safetensors

Model size

31B params

Tensor type

BF16

·

Model tree for senaro/atlas-gemma4-31b-trm7

Base model

google/gemma-4-31B

Finetuned

google/gemma-4-31B-it

Finetuned

(212)

this model

Finetunes

Dataset used to train senaro/atlas-gemma4-31b-trm7