wangzhang/Llama-3-8B-Instruct-RR-Abliterated
LoRA-style vs GraySwanAI/Llama-3-8B-Instruct-RR. 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 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 74/96, Attention 122/128, lm_head 0/1
2 derivatives checked
- mradermacher/Llama-3-8B-Instruct-RR-Abliterated-i1-GGUF: Quantization
- mradermacher/Llama-3-8B-Instruct-RR-Abliterated-GGUF: Same weights, converted