ZeroXClem/Qwen3-4B-Sky-High-Hermes
Full fine-tune vs DavidAU/Qwen3-4B-Instruct-2507-Polaris-Alpha-Distill-Heretic-Abliterated. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Norms 141/145, MLP 108/108, Attention 144/144
3 derivatives checked
- mradermacher/Qwen3-4B-Sky-High-Hermes-i1-GGUF: Quantization
- mradermacher/Qwen3-4B-Sky-High-Hermes-GGUF: Same weights, converted
- Goekdeniz-Guelmez/Qwen3-4B-Sky-High-Hermes-gabliterated: Abliterated