Ornith-1.5-9B (BitsAndBytes 4-bit Reference Base)

Official community 4-bit (bitsandbytes NF4) base checkpoint of ornith-ai/Ornith-1.5-9B.

Reduces download size from 18.5 GB to ~5.5 GB while keeping full PEFT LoRA adapter attachability.

Downloads last month
24
Safetensors
Model size
9B params
Tensor type
BF16
·
U8
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for adarrshDev/Ornith-1.5-9B-bnb-4bit

Quantized
(71)
this model