Aratako/Qwen3-30B-A3B-ERP-v0.1
Full fine-tune vs Aratako/Qwen3-30B-A3B-NSFW-JP. Fine-tune: 94% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 0/1, Norms 179/193, MLP 2613/2613, Attention 192/192, lm_head 1/1
3 derivatives checked
- Aratako/Qwen3-30B-A3B-ERP-v0.1-GGUF: Quantization
- mradermacher/Qwen3-30B-A3B-ERP-v0.1-i1-GGUF: Quantization
- mradermacher/Qwen3-30B-A3B-ERP-v0.1-GGUF: Quantization