ClaudioItaly/Follex-7B-V2
Full fine-tune vs ATH-MaaS/Marco-o1. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Norms 57/57, MLP 84/84, Attention 196/196
2 derivatives checked
- mradermacher/Follex-7B-V2-i1-GGUF: Quantization
- mradermacher/Follex-7B-V2-GGUF: Same weights, converted