Jolly-Q/SOG_10k_70B
Full fine-tune vs Sao10K/70B-L3.3-Cirrus-x1. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 161/161, MLP 240/240, Attention 320/320
2 derivatives checked
- mradermacher/SOG_10k_70B-i1-GGUF: Quantization
- mradermacher/SOG_10k_70B-GGUF: Quantization