Kukedlc/Neural-Cosmic-Boy-7B-slerp

Full fine-tune vs Kukedlc/Neural-Cosmic-7B-slerp. Fine-tune: 98% of the weights changed, across 32 of 32 layers.

Tensors changed: lm_head 1/1, Norms 33/65, MLP 96/96, Attention 124/128, Embeddings 0/1

1 derivatives checked

• mradermacher/Neural-Cosmic-Boy-7B-slerp-i1-GGUF: Quantization

On the Hub · Downloads on Model Pulse