marcuscedricridia/absolute-o1-7b
Full fine-tune vs Xiaojian9992024/Qwen2.5-THREADRIPPER-Small. Fine-tune: 96% of the weights changed, across 28 of 28 layers.
Tensors changed: Norms 55/57, MLP 81/84, Attention 187/196
2 derivatives checked
- mradermacher/absolute-o1-7b-i1-GGUF: Quantization
- mradermacher/absolute-o1-7b-GGUF: Same weights, converted