ZeroXClem/Qwen2.5-7B-HomerAnvita-NerdMix
Full fine-tune vs bunnycore/Qandora-2.5-7B-Creative. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 196/196
5 derivatives checked
- QuantFactory/HomerCreativeAnvita-Mix-Qw7B-GGUF: Full fine-tune
- mradermacher/Qwen2.5-7B-HomerAnvita-NerdMix-i1-GGUF: Quantization
- mradermacher/Qwen2.5-7B-HomerAnvita-NerdMix-GGUF: Same weights, converted
- MaziyarPanahi/Qwen2.5-7B-HomerAnvita-NerdMix-GGUF: Same weights, converted
- suayptalha/HomerCreativeAnvita-Mix-Qw7B: Full fine-tune