handy-computer/canary-qwen-2.5b-gguf
Adapter vs nvidia/canary-qwen-2.5b. nvidia/canary-qwen-2.5b is a LoRA adapter, not full weights: rank 128, on q_proj, v_proj in 32 layers (56 adapted matrices). It modifies handy-computer/canary-qwen-2.5b-gguf at load time.