Delta-Vector/Hamanasu-Magnum-QwQ-32B
Full fine-tune vs Delta-Vector/Hamanasu-QwQ-V2-RP. Fine-tune: 98% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 0/1, Norms 126/129, MLP 192/192, Attention 448/448, lm_head 1/1
8 derivatives checked
- mradermacher/Hamanasu-Magnum-QwQ-32B-i1-GGUF: Quantization
- mradermacher/Hamanasu-Magnum-QwQ-32B-GGUF: Quantization
- Phr00t/Magnum-Hamanasu-Instruct-32B-GGUF: Full fine-tune
- Delta-Vector/Archaeo-32B: Full fine-tune
- Phr00t/Phr00tyMix-v1-32B: Full fine-tune
- Yobenboben/QwQ-32B-Mlem: Full fine-tune
- ThijsL202/EVA-Hamanasu-Magnum-QwQ-32B: Full fine-tune
- marcuscedricridia/Springer-32B-RP-3: Full fine-tune