shadowml/BeagleSempra-7B

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 65/65, MLP 93/96, Attention 124/128, lm_head 1/1

1 derivatives checked

• shadowml/BeagSake-7B: Full fine-tune

On the Hub · Downloads on Model Pulse