cstr/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 cstr/canary-qwen-2.5b-GGUF at load time.
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 cstr/canary-qwen-2.5b-GGUF at load time.