Downloads · 30 days
7
18% of all-time downloads
tiny-aya-earth-yoruba-lora
HusseinAlamutu/tiny-aya-earth-yoruba-lora
tiny-aya-earth-yoruba-lora is a text generation model from HusseinAlamutu. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
This repository contains a QLoRA fine-tuned adapter for CohereLabs/tiny-aya-earth (3.35B parameters), specialized on the Yorùbá (yo) instruction-following split of masakhane/african-ultrachat.
All-time downloads
38
Public
Repo size
387 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors363 MB · 66%
At a glance
- Task
- Text Generation
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Sep 9, 2026
- Updated
- Sep 9, 2026
- SHA
- 6d1a948b
Base models
Datasets
Model card
From the Hugging Face model README
TinyAya-Earth Yoruba LoRA Adapter
This repository contains a QLoRA fine-tuned adapter for CohereLabs/tiny-aya-earth (3.35B parameters), specialized on the Yorùbá (yo) instruction-following split of masakhane/african-ultrachat.
Model Details
- Developer: Hussein Alamutu
- Base Architecture: Dense decoder-only transformer with Grouped Query Attention (GQA), 36 layers, 8k context window.
- Base Model:
CohereLabs/tiny-aya-earth - Fine-Tuning Dataset:
masakhane/african-ultrachat(Yoruba split) - Training Method: QLoRA (4-bit NF4 base, rank 16, alpha 32)
- Primary Language: Yoruba (
yo) - License: Apache 2.0
- GitHub Repository: https://github.com/husseinalamutu/sovereign-k8s-llm
Intended Use
Designed for offline, sovereign inference on resource-constrained Kubernetes infrastructure when quantized to GGUF format and served via llama.cpp.
- Task
- Text Generation
- Library
- peft
- License
- apache-2.0
- Languages
- yo
- Created
- Sep 9, 2026
- Updated
- Sep 9, 2026