mvpmaster/PearlMath-lafted-7b-slerp

Full fine-tune vs mvpmaster/MistralDpoPearl-7b-slerp. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

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

1 derivatives checked

• mradermacher/PearlMath-lafted-7b-slerp-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse