automerger/T3qm7xPercival_01-7B

Full fine-tune vs AurelPx/Percival_01-7b-slerp. Fine-tune: 93% of the weights changed, across 32 of 32 layers.

Tensors changed: MLP 90/96, Attention 115/128, Norms 18/65, Embeddings 1/1, lm_head 1/1

1 derivatives checked

• MaziyarPanahi/T3qm7xPercival_01-7B-GGUF: Quantization

On the Hub · Downloads on Model Pulse