mradermacher/TwinLlama-3.1-8B-instruct-GGUF
Adapter vs vonewman/TwinLlama-3.1-8B-instruct. vonewman/TwinLlama-3.1-8B-instruct 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 mradermacher/TwinLlama-3.1-8B-instruct-GGUF at load time.