mergekit-community/Fimburs11V3
Full fine-tune vs Cognitive-Machines-Labs/Dolus-14b-Mini. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Norms 97/97, MLP 144/144, Attention 192/192
4 derivatives checked
- mradermacher/Fimburs11V3-i1-GGUF: Quantization
- MaziyarPanahi/Fimburs11V3-GGUF: Quantization
- featherless-ai-quants/mergekit-community-Fimburs11V3-GGUF: Quantization
- mradermacher/Fimburs11V3-GGUF: Quantization