grimjim/Llama-3.1-8B-Instruct-abliterated_via_adapter
Adapter vs grimjim/Llama-3-Instruct-abliteration-LoRA-8B. 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 grimjim/Llama-3.1-8B-Instruct-abliterated_via_adapter at load time.
5 derivatives checked
- featherless-ai-quants/grimjim-Llama-3.1-8B-Instruct-abliterated_via_adapter-GGUF: Quantization
- mradermacher/Llama-3.1-8B-Instruct-abliterated_via_adapter-GGUF: Same weights, converted
- grimjim/Llama-3.1-8B-Instruct-abliterated_via_adapter-GGUF: Quantization
- DeltaIV/llama31-eros: LoRA-style
- grimjim/Llama-3.1-Supernova-Lite-Instruct-merge-abliterated-8B: Partial fine-tune
1 other repos hold byte-for-byte identical weight files.