Tibeb is an Amharic-language AI assistant focused on financial literacy in the Ethiopian context. These adapters were trained using MLX LoRA on Apple Silicon.

Training Details

Base model: CohereForAI/aya-expanse-8b (4-bit quantized via mlx-community)
Method: LoRA (rank 16, all layers, cosine LR decay, AdamW)
Data: ~692K rows of Amharic instruction data (see dataset repo)
Hardware: Apple Silicon Mac (MLX backend)

v3 Config

Iterations: 20,000
Batch size: 1 (4x gradient accumulation = effective batch 4)
Learning rate: 1e-5 → 1e-6 (cosine decay, 500 warmup steps)
LoRA rank: 16, dropout: 0.05, scale: 32.0
Max sequence length: 512

Adapters

mlx-adapter-v3/ — v3 training (rank 16, all layers, cosine LR)
mlx-adapter/ — v2 training (rank 8, 16 layers)

Usage

python

from mlx_lm import load, generate

model, tokenizer = load(
    "mlx-community/aya-expanse-8b-4bit",
    adapter_path="nahommohan/tibeb-sft-adapter/mlx-adapter-v3"
)

prompt = "ስለ ቲ-ቢል ኢንቨስትመንት ንገረኝ"
response = generate(model, tokenizer, prompt=prompt, max_tokens=500)
print(response)

nahommohan/tibeb-sft-adapter

Tibeb SFT Adapter

Model Description

Training Details

v3 Config

Adapters

Usage

Links

nahommohan/
tibeb-sft-adapter