powermove72/Notus-TheTop-7b-Slerp

Full fine-tune vs MaziyarPanahi/TheTop-5x7B-Instruct-S3-v0.1. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

Tensors changed: MLP 93/96, Norms 24/65, Attention 124/128, lm_head 1/1, Embeddings 1/1

1 derivatives checked

• mradermacher/Notus-TheTop-7b-Slerp-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse