Naphula/DarkForest-20B-v2.0-Erebus-Edition
Full fine-tune (fewer layers) vs KoboldAI/LLaMA2-13B-Erebus-v3. KoboldAI/LLaMA2-13B-Erebus-v3 matches part of Naphula/DarkForest-20B-v2.0-Erebus-Edition (363 of its 561 tensors; the rest of Naphula/DarkForest-20B-v2.0-Erebus-Edition has no counterpart). On the shared part: Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 81/81, MLP 120/120, Attention 160/160, lm_head 1/1
2 derivatives checked
- mradermacher/DarkForest-20B-v2.0-Erebus-Edition-i1-GGUF: Quantization
- mradermacher/DarkForest-20B-v2.0-Erebus-Edition-GGUF: Quantization