Downloads · 30 days
0
twi-sft-v3-6
rossenburg/twi-sft-v3-6
twi-sft-v3-6 is a machine learning model from rossenburg. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
LoRA adapters for Sage v3.6, a Twi-speaking AI assistant fine-tuned from ghananlpcommunity/MiniCPM5-1B-Twi with MLX LoRA (rank 16, 2000 iterations).
Access
Public
Updated Sep 18, 2026
Repo size
29.9 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors29.9 MB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Sep 18, 2026
- Updated
- Sep 18, 2026
- SHA
- 840a3566
Base models
Model card
From the Hugging Face model README
Sage v3.6 LoRA adapters
LoRA adapters for Sage v3.6, a Twi-speaking AI assistant fine-tuned from
ghananlpcommunity/MiniCPM5-1B-Twi with MLX LoRA (rank 16, 2000 iterations).
Training: train loss 0.371, validation loss 0.245.
Usage (MLX)
from mlx_lm import load, generate
model, tokenizer = load(
"ghananlpcommunity/MiniCPM5-1B-Twi",
adapter_path="twi-sft-v3-6-adapters", # this repo's files
)
print(generate(model, tokenizer, prompt="### Instruction:\nMaakye!\n\n### Response:\n"))
- License
- apache-2.0
- Languages
- tw, aka
- Created
- Sep 18, 2026
- Updated
- Sep 18, 2026