Hi, thanks for the great work.
In the HF Repo, slat_encoder.ckpt mismatch with slat_encoder.yaml
It seems like a decoder weight:
input_layer.weight: model (768, 1024), ckpt (768, 8)
out_layer.weight: model (16, 768), ckpt (448, 768)
out_layer.bias: model (16,), ckpt (448,)
Hi, thanks for the great work.
In the HF Repo, slat_encoder.ckpt mismatch with slat_encoder.yaml
It seems like a decoder weight:
input_layer.weight: model (768, 1024), ckpt (768, 8)
out_layer.weight: model (16, 768), ckpt (448, 768)
out_layer.bias: model (16,), ckpt (448,)