CombinHorizon/zetasepic-abliteratedV2-Qwen2.5-32B-Inst-BaseMerge-TIES
Full fine-tune vs Qwen/Qwen2.5-32B. Fine-tune: 100% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 1/1, Norms 128/129, MLP 192/192, Attention 448/448, lm_head 1/1
2 derivatives checked
- mradermacher/zetasepic-abliteratedV2-Qwen2.5-32B-Inst-BaseMerge-TIES-i1-GGUF: Quantization
- mradermacher/zetasepic-abliteratedV2-Qwen2.5-32B-Inst-BaseMerge-TIES-GGUF: Quantization
10 other repos hold byte-for-byte identical weight files.