arcee-ai/Clown-DPO-Extended

Partial fine-tune vs CorticalStack/pastiche-crown-clown-7b-dare-dpo. Partial change: 84% of the weights changed (attention, mlp, norms), in 28 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 56/65, MLP 84/96, Attention 112/128, lm_head 0/1

1 derivatives checked

• mradermacher/Clown-DPO-Extended-GGUF: Quantization

On the Hub · Downloads on Model Pulse