Huanghaonan88/Llama-3.1-8B-bnb-4bit-ShangHanLun
Adapter vs unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit. Huanghaonan88/Llama-3.1-8B-bnb-4bit-ShangHanLun is a LoRA adapter, not full weights: rank 16, on down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj in 32 layers (224 adapted matrices). It modifies unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit at load time.