mradermacher/Qwen2.5-3B-MultiChat-Vi-GGUF
Adapter vs thanhkt/Qwen2.5-3B-MultiChat-Vi. thanhkt/Qwen2.5-3B-MultiChat-Vi 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 36 layers (252 adapted matrices). It modifies mradermacher/Qwen2.5-3B-MultiChat-Vi-GGUF at load time.