YOYO-AI/Qwen3-8B-YOYO-nuslerp-plus
Full fine-tune vs Qwen/Qwen3-8B. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Norms 145/145, MLP 108/108, Attention 144/144
2 derivatives checked
- mradermacher/Qwen3-8B-YOYO-nuslerp-plus-i1-GGUF: Quantization
- mradermacher/Qwen3-8B-YOYO-nuslerp-plus-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.