mradermacher/Qwen2.5-1.5B-Vi-Alpaca-GGUF
Adapter vs thanhkt/Qwen2.5-1.5B-Vi-Alpaca. thanhkt/Qwen2.5-1.5B-Vi-Alpaca 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 28 layers (196 adapted matrices). It modifies mradermacher/Qwen2.5-1.5B-Vi-Alpaca-GGUF at load time.