zelus82/JuliusCesar-72B-BeyonderV.0
Full fine-tune (fewer layers) vs davidkim205/Rhea-72b-v0.5. zelus82/JuliusCesar-72B-BeyonderV.0 matches part of davidkim205/Rhea-72b-v0.5 (363 of its 1043 tensors; the rest of davidkim205/Rhea-72b-v0.5 has no counterpart). On the shared part: Fine-tune: 94% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 0/1, Norms 0/81, MLP 117/120, Attention 156/160, lm_head 1/1
1 derivatives checked
- mradermacher/JuliusCesar-72B-BeyonderV.0-GGUF: Quantization