paulml/OGNO-7B
Full fine-tune vs eren23/dpo-binarized-NeutrixOmnibe-7B. Fine-tune: 97% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 64/65, MLP 93/96, Attention 124/128, lm_head 1/1
4 derivatives checked
- mradermacher/OGNO-7B-i1-GGUF: Quantization
- mradermacher/OGNO-7B-GGUF: Quantization
- MaziyarPanahi/OGNO-7B-GGUF: Same weights, converted
- yleo/ParrotMOgno-7B: LoRA-style