richardbenson91477/Lisa-v0.2-8b
LoRA-style vs Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of q_proj, v_proj changed, in 36 of 36 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 72/144, lm_head 0/1
2 derivatives checked
- mradermacher/Lisa-v0.2-8b-i1-GGUF: Quantization
- mradermacher/Lisa-v0.2-8b-GGUF: Same weights, converted