MiniCPM5-1B-AutoRound-NVFP4-RTN / quantization_config.json
INC4AI's picture
Upload quantized model MiniCPM5-1B-AutoRound-NVFP4-RTN
248dc1e verified
{
"bits": 4,
"act_bits": 4,
"data_type": "nv_fp",
"act_data_type": "nv_fp4_with_static_gs",
"group_size": 16,
"act_group_size": 16,
"sym": true,
"act_sym": true,
"act_dynamic": true,
"enable_quanted_input": false,
"iters": 0,
"low_gpu_mem_usage": true,
"autoround_version": "0.13.0",
"block_name_to_quantize": "model.layers",
"quant_method": "auto-round",
"packing_format": "auto_round:llm_compressor",
"extra_config": {
"model.layers.0.self_attn.q_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.0.self_attn.k_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.0.self_attn.v_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.0.self_attn.o_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.1.self_attn.q_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.1.self_attn.k_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.1.self_attn.v_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.1.self_attn.o_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.2.self_attn.q_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.2.self_attn.k_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.2.self_attn.v_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.2.self_attn.o_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.3.self_attn.q_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.3.self_attn.k_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.3.self_attn.v_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.3.self_attn.o_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.4.self_attn.q_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.4.self_attn.k_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.4.self_attn.v_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.4.self_attn.o_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.5.self_attn.q_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.5.self_attn.k_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.5.self_attn.v_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.5.self_attn.o_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.6.self_attn.q_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.6.self_attn.k_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.6.self_attn.v_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.6.self_attn.o_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.7.self_attn.q_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.7.self_attn.k_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.7.self_attn.v_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.7.self_attn.o_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.8.self_attn.q_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.8.self_attn.k_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.8.self_attn.v_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.8.self_attn.o_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.9.self_attn.q_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.9.self_attn.k_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.9.self_attn.v_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.9.self_attn.o_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.10.self_attn.q_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.10.self_attn.k_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.10.self_attn.v_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.10.self_attn.o_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.11.self_attn.q_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.11.self_attn.k_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.11.self_attn.v_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.11.self_attn.o_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.12.self_attn.q_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.12.self_attn.k_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.12.self_attn.v_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.12.self_attn.o_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.13.self_attn.q_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.13.self_attn.k_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.13.self_attn.v_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.13.self_attn.o_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.14.self_attn.q_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.14.self_attn.k_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.14.self_attn.v_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.14.self_attn.o_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.15.self_attn.q_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.15.self_attn.k_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.15.self_attn.v_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.15.self_attn.o_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.16.self_attn.q_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.16.self_attn.k_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.16.self_attn.v_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.16.self_attn.o_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.17.self_attn.q_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.17.self_attn.k_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.17.self_attn.v_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.17.self_attn.o_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.18.self_attn.q_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.18.self_attn.k_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.18.self_attn.v_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.18.self_attn.o_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.19.self_attn.q_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.19.self_attn.k_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.19.self_attn.v_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.19.self_attn.o_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.20.self_attn.q_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.20.self_attn.k_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.20.self_attn.v_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.20.self_attn.o_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.21.self_attn.q_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.21.self_attn.k_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.21.self_attn.v_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.21.self_attn.o_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.22.self_attn.q_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.22.self_attn.k_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.22.self_attn.v_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.22.self_attn.o_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.23.self_attn.q_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.23.self_attn.k_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.23.self_attn.v_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
"model.layers.23.self_attn.o_proj": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
},
".*self_attn.*": {
"bits": 16,
"data_type": "float",
"act_bits": 16,
"act_data_type": "float"
}
}
}