Goekdeniz-Guelmez/Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1
Full fine-tune vs Qwen/Qwen2.5-1.5B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 196/196
5 derivatives checked
- Goekdeniz-Guelmez/Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1-gguf: Quantization
- mradermacher/Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v1-GGUF: Same weights, converted
- Goekdeniz-Guelmez/Josiefied-Qwen2.5-1.5B-Instruct-abliterated-v2: LoRA-style
- Goekdeniz-Guelmez/j.o.s.i.e.v4o-1.5b-dpo-stage1-v1: LoRA-style
- bunnycore/Qwen2.5-1.5B-Matrix: Full fine-tune