cocktailpeanut/stable-audio-3-medium
Partial fine-tune vs stabilityai/stable-audio-3-medium-base. Partial change: 63% of the weights changed (attention, embeddings, norms, other), in 24 of 24 layers.
Tensors changed: Embeddings 111/111, other 125/262, Norms 168/456, Attention 120/168
2 other repos hold byte-for-byte identical weight files.