mradermacher/mistral-malayalam-GGUF
Adapter vs traromal/mistral-malayalam. traromal/mistral-malayalam 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/mistral-malayalam-GGUF at load time.