MisterAI/bigscience_bloom-560m
Full fine-tune vs bigscience/bloom-560m. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: MLP 96/96, Norms 98/98, Attention 96/96, Embeddings 3/3
Full fine-tune vs bigscience/bloom-560m. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: MLP 96/96, Norms 98/98, Attention 96/96, Embeddings 3/3