jeiku/BuRPInfinity_9B

Full fine-tune vs ChaoticNeutrals/BuRP_7B. Fine-tune: 98% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 64/65, MLP 96/96, Attention 124/128, lm_head 0/1

1 derivatives checked

On the Hub · Downloads on Model Pulse