fpadovani/nld-100mb-after-nld_uniform-ckpt500_seed3407_seed3407

Full fine-tune vs fpadovani/ppt-nld_uniform-100mb_seed3407. Fine-tune: 100% of the weights changed, across 12 of 12 layers.

Tensors changed: Attention 48/48, Norms 25/50, MLP 48/48, Embeddings 1/1

On the Hub · Downloads on Model Pulse