Goekdeniz-Guelmez/j.o.s.i.e.v4o-7b-orpo-stage1-v1
LoRA-style vs Goekdeniz-Guelmez/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 28 of 28 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 84/84, Attention 112/196, lm_head 0/1
3 derivatives checked
- mradermacher/j.o.s.i.e.v4o-7b-orpo-stage1-v1-i1-GGUF: Quantization
- Goekdeniz-Guelmez/j.o.s.i.e.v4o-7b-orpo-stage1-v1-gguf: Quantization
- mradermacher/j.o.s.i.e.v4o-7b-orpo-stage1-v1-GGUF: Same weights, converted