bunnycore/Qandora-2.5-7B-Creative
Partial fine-tune vs bunnycore/Qandora-2.5-7B. Partial change: 86% of the weights changed (attention, mlp, norms), in 28 of 28 layers.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 8/57, MLP 84/84, Attention 114/196
7 derivatives checked
- QuantFactory/Qwen2.5-7B-HomerCreative-Mix-GGUF: Full fine-tune
- QuantFactory/Qwen2.5-7B-HomerAnvita-NerdMix-GGUF: Full fine-tune
- mradermacher/Qandora-2.5-7B-Creative-GGUF: Same weights, converted
- mradermacher/Qandora-2.5-7B-Creative-i1-GGUF: Quantization
- ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix: Full fine-tune
- ZeroXClem/Qwen2.5-7B-HomerCreative-Mix: Full fine-tune
- Theros/Qwen2.5-CreativeMix-7B: Full fine-tune