grimjim/Llama-3-Instruct-abliteration-LoRA-8B
Adapter vs failspy/Meta-Llama-3-8B-Instruct-abliterated-v3. grimjim/Llama-3-Instruct-abliteration-LoRA-8B is a LoRA adapter, not full weights: rank 32, 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 failspy/Meta-Llama-3-8B-Instruct-abliterated-v3 at load time.
6 derivatives checked
- QuantFactory/Llama-3.1-8B-Instruct-abliterated_via_adapter-GGUF: Adapter
- ngxson/Llama-3-Instruct-abliteration-LoRA-8B-F16-GGUF: Adapter
- grimjim/Llama-3.1-8B-Instruct-abliterated_via_adapter: Adapter
- v000000/SwallowMaid-8B-L3-SPPO-abliterated: Adapter
- mergekit-community/nsfw-i-mean-it-plz-kill-me-part2: Adapter
- mergekit-community/nsfw_merge_testv2: Adapter
1 other repos hold byte-for-byte identical weight files.