CombinHorizon/Josiefied-abliteratedV4-Qwen2.5-14B-Inst-BaseMerge-TIES
Partial fine-tune vs Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4. Partial change: 84% of the weights changed (attention, lm_head, mlp, norms), in 48 of 48 layers.
Tensors changed: Embeddings 0/1, Norms 31/97, MLP 127/144, Attention 265/336, lm_head 1/1
2 derivatives checked
- mradermacher/Josiefied-abliteratedV4-Qwen2.5-14B-Inst-BaseMerge-TIES-GGUF: Quantization
- MaziyarPanahi/Josiefied-abliteratedV4-Qwen2.5-14B-Inst-BaseMerge-TIES-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.