Hugging Face's logo

HusseinAlamutu
/
tiny-aya-earth-yoruba-lora

Text Generation
PEFT
Safetensors
Yoruba
sovereign-ai
yoruba
lora
tiny-aya
kubernetes
conversational
Model card Files
xet
 Community
tiny-aya-earth-yoruba-lora / README.md
HusseinAlamutu's picture
HusseinAlamutu
Update README.md
6d1a948 verified
preview code
|
Raw
History Blame Contribute Delete
1.24 kB
metadata 
language:
  - yo
license: apache-2.0
tags:
  - sovereign-ai
  - yoruba
  - peft
  - lora
  - tiny-aya
  - kubernetes
base_model: CohereLabs/tiny-aya-earth
pipeline_tag: text-generation
datasets:
  - masakhane/african-ultrachat

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.