You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Gemma 4 12B — Tajik E2 (fresh LoRA + merged)

Fresh LoRA (r=32 attn+MLP rsLoRA dropout 0.0) trained on top of Tohirju/gemma-4-12b-tajik-53p2-merged for one full epoch on our 1.23M Stage A (with wiki) + 6K Stage B, then merged into the base.

Parent base : Tohirju/gemma-4-12b-tajik-53p2-merged (53.67 on Zehnlab 6-MCQ)
Parent LoRA : Tohirju/gemma-4-12b-e2-lora

Downloads last month: 7

Safetensors

Model size

12B params

Tensor type

BF16

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Tohirju/gemma-4-12b-e2-merged

Base model

google/gemma-4-12B

Finetuned

unsloth/gemma-4-12b

Finetuned

Tohirju/gemma-4-12b-tajik-53p2-merged

Finetuned

(1)

this model