Azazelle/L3-RP_io

Partial fine-tune vs ResplendentAI/Aura_Uncensored_l3_8B. Partial change: 87% of the weights changed (attention, mlp, norms), in 32 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 12/65, MLP 96/96, Attention 128/128, lm_head 0/1

2 derivatives checked

• mradermacher/L3-RP_io-GGUF: Same weights, converted
• featherless-ai-quants/Azazelle-L3-RP_io-GGUF: Quantization

On the Hub · Downloads on Model Pulse