Nexesenex/Llama_3.x_70b_Trojka_V2
Full fine-tune vs Steelskull/L3.3-Electra-R1-70b. 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/Llama_3.x_70b_Trojka_V2-i1-GGUF: Quantization
- mradermacher/Llama_3.x_70b_Trojka_V2-GGUF: Quantization