Occitan fine-tunes of Google's Gemma 4 models, trained with standard transformers + PEFT (not SFTTrainer)
Julien
julienp79
AI & ML interests
Training, Supervised Fine Tuning
Organizations
None yet
Trained with trl's SFTTrainer
-
julienp79/occitan-gemma-4-e2b-it-rslora-sfttrainer
Text Generation • 5B • Updated • 182 -
julienp79/occitan-gemma-4-e2b-it-lora-sfttrainer
Text Generation • 5B • Updated • 146 -
julienp79/occitan-gemma-4-12b-it-rslora-sfttrainer
Text Generation • 12B • Updated • 196 • 1 -
julienp79/occitan-gemma-4-12b-it-rslora-qat-sfttrainer
Text Generation • 12B • Updated • 194
Trained with transformers' trainer
Occitan fine-tunes of Google's Gemma 4 models, trained with standard transformers + PEFT (not SFTTrainer)
Trained with trl's SFTTrainer
-
julienp79/occitan-gemma-4-e2b-it-rslora-sfttrainer
Text Generation • 5B • Updated • 182 -
julienp79/occitan-gemma-4-e2b-it-lora-sfttrainer
Text Generation • 5B • Updated • 146 -
julienp79/occitan-gemma-4-12b-it-rslora-sfttrainer
Text Generation • 12B • Updated • 196 • 1 -
julienp79/occitan-gemma-4-12b-it-rslora-qat-sfttrainer
Text Generation • 12B • Updated • 194
Trained with trl's SFTTrainer
Trained with transformers' trainer