Felladrin/Minueza-32M-Chat
Full fine-tune vs Felladrin/Minueza-32M-Base. Fine-tune: 100% of the weights changed, across 10 of 10 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 21/21, MLP 30/30, Attention 40/40
Full fine-tune vs Felladrin/Minueza-32M-Base. Fine-tune: 100% of the weights changed, across 10 of 10 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 21/21, MLP 30/30, Attention 40/40