YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Oleander-150M (step 2500)

Hybrid GDN2 / gated-GQA small LM. Weights use the training-code parameter names (GDN2 layers follow flash-linear-attention GatedDeltaNet2 naming). A modeling file is required to load them with transformers.

Downloads last month
64
Safetensors
Model size
0.1B params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support