AMAImedia/NOESIS-Qwen3-Forced-Aligner-0.6B-112LANG-BF16

Partial fine-tune vs Qwen/Qwen3-ForcedAligner-0.6B. Partial change: 82% of the weights changed (attention, mlp, other), in 28 of 28 layers.

Tensors changed: other 3/11, MLP 132/180, Norms 0/211, Attention 208/304, lm_head 0/1, Embeddings 0/1

1 derivatives checked