Sarthak213/doosra-qwen3.5-4b-toolcalls-b
Adapter vs Qwen/Qwen3.5-4B. Sarthak213/doosra-qwen3.5-4b-toolcalls-b is a LoRA adapter, not full weights: rank 32, on down_proj, gate_proj, in_proj_a, in_proj_b, in_proj_qkv, in_proj_z, k_proj, o_proj… in 32 layers (248 adapted matrices). It modifies Qwen/Qwen3.5-4B at load time.