tim-lawson's picture
Push model using huggingface_hub.
5cad6a8 verified
raw
history blame contribute delete
147 Bytes
{
"auxk": 256,
"dead_steps_threshold": 76,
"dead_threshold": 0.001,
"k": 16,
"n_inputs": 512,
"n_latents": 512,
"standardize": true
}