prithivMLmods/Viper-Coder-Hybrid-v1.2
Full fine-tune vs prithivMLmods/Viper-Coder-v1.1. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Norms 97/97, MLP 144/144, Attention 336/336
4 derivatives checked
- mradermacher/Viper-Coder-Hybrid-v1.2-i1-GGUF: Quantization
- mradermacher/Viper-Coder-Hybrid-v1.2-GGUF: Quantization
- MaziyarPanahi/Viper-Coder-Hybrid-v1.2-GGUF: Same weights, converted
- DevQuasar-9/prithivMLmods.Viper-Coder-Hybrid-v1.2-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.