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 = "ሡለ ቲ-α‰’αˆ αŠ’αŠ•α‰¨αˆ΅α‰΅αˆ˜αŠ•α‰΅ αŠ•αŒˆαˆ¨αŠ"
response = generate(model, tokenizer, prompt=prompt, max_tokens=500)
print(response)

Links

Downloads last month

-

Downloads are not tracked for this model. How to track
MLX
Hardware compatibility
Log In to add your hardware

Quantized

Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for nahommohan/tibeb-sft-adapter

Adapter
(26)
this model