nightmedia/Qwen3-4B-Element4-Eva
Full fine-tune vs DavidAU/Qwen3-4B-Apollo-V0.1-4B-Thinking-Heretic-Abliterated. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 145/145, MLP 108/108, Attention 144/144
2 derivatives checked
- mradermacher/Qwen3-4B-Element4-Eva-i1-GGUF: Quantization
- mradermacher/Qwen3-4B-Element4-Eva-GGUF: Same weights, converted