Delta-Vector/Nanuq-R1-14B
Full fine-tune vs snwy/frankenqwen3-8B-235B-dense-conversion-interleaved-untuned. Fine-tune: 100% of the weights changed, across 64 of 64 layers.
Tensors changed: Norms 247/257, MLP 192/192, Attention 256/256, lm_head 1/1, Embeddings 1/1
3 derivatives checked
- mradermacher/Nanuq-R1-14B-i1-GGUF: Quantization
- mradermacher/Nanuq-R1-14B-GGUF: Quantization
- Koitenshin/Nanuq-R1-14B-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.