TareksGraveyard/Stylizer-V2-LLaMa-70B

Full fine-tune vs Sao10K/L3-70B-Euryale-v2.1. Fine-tune: 100% of the weights changed, across 80 of 80 layers.

Tensors changed: Norms 161/161, MLP 240/240, Attention 320/320

2 derivatives checked

• mradermacher/Stylizer-V2-LLaMa-70B-i1-GGUF: Quantization
• mradermacher/Stylizer-V2-LLaMa-70B-GGUF: Quantization

On the Hub · Downloads on Model Pulse