Tibeb SFT Adapter
LoRA adapters for Tibeb AI β Ethiopia's Amharic financial assistant, fine-tuned on Aya Expanse 8B.
Model Description
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 β 1e-6 (cosine decay, 500 warmup steps)
- LoRA rank: 16, dropout: 0.05, scale: 32.0
- Max sequence length: 512
Adapters
mlx-adapter-v3/β v3 training (rank 16, all layers, cosine LR)mlx-adapter/β v2 training (rank 8, 16 layers)
Usage
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 = "α΅α α²-α’α α’αα¨α΅α΅ααα΅ ααα¨α"
response = generate(model, tokenizer, prompt=prompt, max_tokens=500)
print(response)
Links
- Training pipeline: github.com/nahomar/tibeb-training
- Dataset: nahommohan/tibeb-training-data
Hardware compatibility
Log In to add your hardware
Quantized
Inference Providers NEW
This model isn't deployed by any Inference Provider. π Ask for provider support
Model tree for nahommohan/tibeb-sft-adapter
Base model
CohereLabs/aya-expanse-8b