{"base_model": "meta-llama/Llama-3.2-3B", "compress_config": {"bits": 4, "group_size": -1, "sparsity": 0.5, "damp_percent": 0.01, "desc_act": false, "sym": false, "true_sequential": true, "lossless": "none", "prunen": 2, "prunem": 4, "block_size": 128}, "target_modules": ["self_attn.k_proj", "self_attn.v_proj", "self_attn.q_proj", "self_attn.o_proj", "mlp.up_proj", "mlp.gate_proj", "mlp.down_proj"]} |