Skip to content

PJMixers-Dev

Gemma-3-Starshine-Earthen-v0.4-12B-QLoRA

PJMixers-Dev/Gemma-3-Starshine-Earthen-v0.4-12B-QLoRA

Gemma-3-Starshine-Earthen-v0.4-12B-QLoRA is a text generation model from PJMixers-Dev. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as gemma.

ToastyPigeon/Gemma-3-Starshine-12B was trained at 8K with batch size 4 gradient accumulation 1, so each step was 32,768 tokens (including any padding tokens). It was trained for 100 steps, adding up to a total of 3,27…

Downloads · 30 days

7

18% of all-time downloads

All-time downloads

38

Public

Repo size

2.1 GB

Likes

0

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1 GB · 96%

At a glance

Task
Text Generation
Library
peft
License
gemma
Model type
gemma3
Access
Public
Created
Jun 12, 2025
Updated
Jun 12, 2025
SHA
6809a405

Try a prompt

Base models

Task
Text Generation
Library
peft
Type
gemma3
License
gemma
Languages
en
Created
Jun 12, 2025
Updated
Jun 12, 2025