mradermacher/malayalam-Llama-3.2-1B-instruct-GGUF
Adapter vs traromal/malayalam-Llama-3.2-1B-instruct. traromal/malayalam-Llama-3.2-1B-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 16 layers (112 adapted matrices). It modifies mradermacher/malayalam-Llama-3.2-1B-instruct-GGUF at load time.