mayacinka/yam-pastiche-7B-franken

Full fine-tune vs CorticalStack/pastiche-crown-clown-7b-dare-dpo. Fine-tune: 92% of the weights changed, across 30 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 60/65, MLP 90/96, Attention 120/128, lm_head 0/1

1 derivatives checked

• mradermacher/yam-pastiche-7B-franken-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse