Kukedlc/SuperMente-7B-v2

Full fine-tune vs NousResearch/Hermes-2-Pro-Mistral-7B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Norms 33/65, MLP 96/96, Attention 128/128

2 derivatives checked

• mradermacher/SuperMente-7B-v2-i1-GGUF: Quantization
• mradermacher/SuperMente-7B-v2-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse