KaraKaraWarehouse/Eurstoria-106B
Full fine-tune (fewer layers) vs Sao10K/L3-70B-Euryale-v2.1. Sao10K/L3-70B-Euryale-v2.1 matches part of KaraKaraWarehouse/Eurstoria-106B (723 of its 1101 tensors; the rest of KaraKaraWarehouse/Eurstoria-106B has no counterpart). On the shared part: Fine-tune: 99% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 1/1, Norms 160/161, MLP 240/240, Attention 320/320, lm_head 0/1
2 derivatives checked
- mradermacher/Eurstoria-106B-i1-GGUF: Quantization
- mradermacher/Eurstoria-106B-GGUF: Quantization