FredrikBL/HermesFlashback-7B.1

Full fine-tune vs mlabonne/NeuralHermes-2.5-Mistral-7B. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

Tensors changed: Norms 25/65, MLP 93/96, Attention 124/128

1 derivatives checked

• mradermacher/HermesFlashback-7B.1-GGUF: Quantization

On the Hub · Downloads on Model Pulse