prithivMLmods/Viper-OneCoder-UIGEN
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/Viper-OneCoder-UIGEN-GGUF: Quantization
- prithivMLmods/Raptor-X3: LoRA-style