Downloads · 30 days
35
10% of all-time downloads
eyla-gemma4-lora
Adiuk/eyla-gemma4-lora
eyla-gemma4-lora is a machine learning model from Adiuk. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for mlx.
MLX LoRA adapter checkpoints (training steps 100–500) fine-tuning Gemma-4-12B for Eyla agent tool-calling, plus a merged Q4KM GGUF (eyla-gemma4-q4km.gguf).
All-time downloads
356
Public
Repo size
5.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf5.3 GB · 94%
At a glance
- Library
- mlx
- Access
- Public
- Created
- Apr 13, 2026
- Updated
- Aug 16, 2026
- SHA
- 320824e8
Model card
From the Hugging Face model README
Eyla · Gemma-4-12B tool-calling LoRA (experimental)
MLX LoRA adapter checkpoints (training steps 100–500) fine-tuning Gemma-4-12B for
Eyla agent tool-calling, plus a merged Q4_K_M GGUF (eyla-gemma4-q4km.gguf).
Honest status: in our agent evals the stock Gemma-4-12B QAT outperformed this fine-tune (7/8 vs 1/8 tasks). Kept public for reproducibility; if you want a working Eyla tool-caller, use eyla-qwen3-8b-tools-v2 instead. Gemma license terms apply.
Author & research
- 🌐 Website: arifadito.com
- 💻 GitHub: github.com/Adiuk24
- 📄 Eyla identity paper: arXiv:2604.00009
- 🔧 Rust ML training verification tooling: gradient-flow-arbiter
- Library
- mlx
- Created
- Apr 13, 2026
- Updated
- Aug 16, 2026