prithivMLmods/Raptor-X2
Full fine-tune vs prithivMLmods/Viper-Coder-v1.1. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 97/97, MLP 144/144, Attention 336/336
2 derivatives checked
- mradermacher/Raptor-X2-GGUF: Quantization
- DevQuasar-2/prithivMLmods.Raptor-X2-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.