mergekit-community/mergekit-model_stock-fpfjlqs
Adapter vs Azazelle/ANJIR-ADAPTER-128. Azazelle/ANJIR-ADAPTER-128 is a LoRA adapter, not full weights: rank 128, on down_proj, gate_proj, k_proj, lm_head, o_proj, q_proj, up_proj, v_proj in 32 layers (225 adapted matrices). It modifies mergekit-community/mergekit-model_stock-fpfjlqs at load time.
4 derivatives checked
- mradermacher/mergekit-model_stock-fpfjlqs-i1-GGUF: Quantization
- mradermacher/mergekit-model_stock-fpfjlqs-GGUF: Same weights, converted
- mergekit-community/nsfw_halp_im_burning_alive_call_911: Full fine-tune (fewer layers)
- mergekit-community/nsfw-i-hate-my-life-v1: Full fine-tune