tuantran1632001/Psyfighter2-Orca2-13B-ties
Full fine-tune vs KoboldAI/LLaMA2-13B-Psyfighter2. Fine-tune: 96% of the weights changed, across 39 of 40 layers.
Tensors changed: Embeddings 0/1, Norms 79/81, MLP 117/120, Attention 156/160, lm_head 1/1
3 derivatives checked
- mradermacher/Psyfighter2-Orca2-13B-ties-i1-GGUF: Quantization
- tuantran1632001/Psyfighter2-Orca2-13B-ties-GGUF: Same weights, converted
- mradermacher/Psyfighter2-Orca2-13B-ties-GGUF: Quantization