djuna/L3.1-Noraian

Full fine-tune vs DreadPoor/Aurora_faustus-8B-LINEAR. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

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

2 derivatives checked

• mradermacher/L3.1-Noraian-i1-GGUF: Quantization
• mradermacher/L3.1-Noraian-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse