YOYO-AI/Qwen3-EZO-8B-YOYO-slerp-128K
Full fine-tune vs AXCXEPT/Qwen3-EZO-8B-beta. Fine-tune: 97% of the weights changed, across 36 of 36 layers.
Tensors changed: Norms 142/145, MLP 105/108, Attention 140/144
2 derivatives checked
- mradermacher/Qwen3-EZO-8B-YOYO-slerp-128K-i1-GGUF: Quantization
- mradermacher/Qwen3-EZO-8B-YOYO-slerp-128K-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.