FredrikBL/NeuralFlashback-ties

Full fine-tune vs mlabonne/NeuralHermes-2.5-Mistral-7B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Norms 29/65, MLP 96/96, Attention 128/128

1 derivatives checked

• mradermacher/NeuralFlashback-ties-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse