aakashMeghwar01/SindhiLM-Qwen-0.5B-v2
Adapter vs Qwen/Qwen2.5-0.5B-Instruct. aakashMeghwar01/SindhiLM-Qwen-0.5B-v2 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 24 layers (168 adapted matrices). It modifies Qwen/Qwen2.5-0.5B-Instruct at load time.