Goekdeniz-Guelmez/Josiefied-Qwen3-14B-abliterated-v3
Full fine-tune vs Qwen/Qwen3-14B. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 0/161, MLP 120/120, Attention 160/160, lm_head 1/1
9 derivatives checked
- bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-14B-abliterated-v3-GGUF: Same weights, converted
- mlx-community/Josiefied-Qwen3-14B-abliterated-v3-4bit: Quantization
- mradermacher/Josiefied-Qwen3-14B-abliterated-v3-i1-GGUF: Quantization
- mradermacher/Josiefied-Qwen3-14B-abliterated-v3-GGUF: Quantization
- mlx-community/Josiefied-Qwen3-14B-abliterated-v3-8bit: Quantization
- alib97/Josiefied-Qwen3-14B-abliterated-v3-mlx-4Bit: Quantization
- mlx-community/Josiefied-Qwen3-14B-abliterated-v3-6bit: Quantization
- tetsajin/Josiefied-Qwen3-14B-abliterated-v3-Q6_K-GGUF: Quantization
- DavidAU/Qwen3-The-Josiefied-Omega-Directive-22B-uncensored-abliterated: Partial fine-tune (fewer layers)