s3nh/SeverusWestLake-7B-DPO

Full fine-tune vs FelixChao/Sectumsempra-7B-DPO. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 28/65, MLP 93/96, Attention 124/128, lm_head 1/1

1 derivatives checked

• mradermacher/SeverusWestLake-7B-DPO-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse