{ "base": { "dir": "/mnt/oiseauxai1data1/L3.3-70B-Loki-V2.0-2.5bpw-H8-EXL3", "bpw": 2.5022903965968712 }, "alts": [ { "dir": "/mnt/oiseauxai1data1/L3.3-70B-Loki-V2.0-8.0bpw-H8-EXL3", "bpw": 8.003025690714518 } ], "groups": [ { "idx": 0, "layers": [ "model.layers.0.self_attn.q_proj", "model.layers.0.self_attn.k_proj", "model.layers.0.self_attn.v_proj", "model.layers.0.self_attn.o_proj" ], "candidates": [ { "dkld": -0.0010143622756004222, "dbits": 738197504 } ] }, { "idx": 1, "layers": [ "model.layers.0.mlp.gate_proj", "model.layers.0.mlp.up_proj", "model.layers.0.mlp.down_proj" ], "candidates": [ { "dkld": -0.003894411772489559, "dbits": 3992977408 } ] }, { "idx": 2, "layers": [ "model.layers.1.self_attn.q_proj", "model.layers.1.self_attn.k_proj", "model.layers.1.self_attn.v_proj", "model.layers.1.self_attn.o_proj" ], "candidates": [ { "dkld": -0.002478840947151173, "dbits": 738197504 } ] }, { "idx": 3, "layers": [ "model.layers.1.mlp.gate_proj", "model.layers.1.mlp.up_proj", "model.layers.1.mlp.down_proj" ], "candidates": [ { "dkld": -0.008406519144773472, "dbits": 3992977408 } ] }, { "idx": 4, "layers": [ "model.layers.2.self_attn.q_proj", "model.layers.2.self_attn.k_proj", "model.layers.2.self_attn.v_proj", "model.layers.2.self_attn.o_proj" ], "candidates": [ { "dkld": -0.007515978068113327, "dbits": 905969664 } ] }, { "idx": 5, "layers": [ "model.layers.2.mlp.gate_proj", "model.layers.2.mlp.up_proj", "model.layers.2.mlp.down_proj" ], "candidates": [ { "dkld": -0.007623301446437858, "dbits": 3758096384 } ] }, { "idx": 6, "layers": [ "model.layers.3.self_attn.q_proj", "model.layers.3.self_attn.k_proj", "model.layers.3.self_attn.v_proj", "model.layers.3.self_attn.o_proj" ], "candidates": [ { "dkld": -0.0006781093776226377, "dbits": 738197504 } ] }, { "idx": 7, "layers": [ "model.layers.3.mlp.gate_proj", "model.layers.3.mlp.up_proj", "model.layers.3.mlp.down_proj" ], "candidates": [ { "dkld": -0.0062385156750678905, "dbits": 3992977408 } ] }, { "idx": 8, "layers": [ "model.layers.4.self_attn.q_proj", "model.layers.4.self_attn.k_proj", "model.layers.4.self_attn.v_proj", "model.layers.4.self_attn.o_proj" ], "candidates": [ { "dkld": -0.0007645055651664956, "dbits": 738197504 } ] }, { "idx": 9, "layers": [ "model.layers.4.mlp.gate_proj", "model.layers.4.mlp.up_proj", "model.layers.4.mlp.down_proj" ], "candidates": [ { "dkld": -0.005478079617023457, "dbits": 3992977408 } ] }, { "idx": 10, "layers": [ "model.layers.5.self_attn.q_proj", "model.layers.5.self_attn.k_proj", "model.layers.5.self_attn.v_proj", "model.layers.5.self_attn.o_proj" ], "candidates": [ { "dkld": -0.0027243249118328317, "dbits": 889192448 } ] }, { "idx": 11, "layers": [ "model.layers.5.mlp.gate_proj", "model.layers.5.mlp.up_proj", "model.layers.5.mlp.down_proj" ], "candidates": [ { "dkld": -0.007106652855873141, "dbits": 3758096384 } ] }, { "idx": 12, "layers": [ "model.layers.6.self_attn.q_proj", "model.layers.6.self_attn.k_proj", "model.layers.6.self_attn.v_proj", "model.layers.6.self_attn.o_proj" ], "candidates": [ { "dkld": -0.0016922049224376567, "dbits": 738197504 } ] }, { "idx": 13, "layers": [ "model.layers.6.mlp.gate_proj", "model.layers.6.mlp.up_proj", "model.layers.6.mlp.down_proj" ], "candidates": [ { "dkld": -0.005806773900985718, "dbits": 3992977408 } ] }, { "idx": 14, "layers": [ "model.layers.7.self_attn.q_proj", "model.layers.7.self_attn.k_proj", "model.layers.7.self_attn.v_proj", "model.layers.7.self_attn.o_proj" ], "candidates": [ { "dkld": -0.0007653512060642464, "dbits": 738197504 } ] }, { "idx": 15, "layers": [ "model.layers.7.mlp.gate_proj", "model.layers.7.mlp.up_proj", "model.layers.7.mlp.down_proj" ], "candidates": [ { "dkld": -0.0014602832496166118, "dbits": 3992977408 } ] }, { "idx": 16, "layers": [ "model.layers.8.self_attn.q_proj", "model.layers.8.self_attn.k_proj", "model.layers.8.self_attn.v_proj", "model.layers.8.self_attn.o_proj" ], "candidates": [ { "dkld": 0.001457507163286187, "dbits": 905969664 } ] }, { "idx": 17, "layers": [ "model.layers.8.mlp.gate_proj", "model.layers.8.mlp.up_proj", "model.layers.8.mlp.down_proj" ], "candidates": [ { "dkld": -0.0015748150646686665, "dbits": 3758096384 } ] }, { "idx": 18, "layers": [ "model.layers.9.self_attn.q_proj", "model.layers.9.self_attn.k_proj", "model.layers.9.self_attn.v_proj", "model.layers.9.self_attn.o_proj" ], "candidates": [ { "dkld": 0.00029479116201397426, "dbits": 738197504 } ] }, { "idx": 19, "layers": [ "model.layers.9.mlp.gate_proj", "model.layers.9.mlp.up_proj", "model.layers.9.mlp.down_proj" ], "candidates": [ { "dkld": -0.00462395101785662, "dbits": 3992977408 } ] }, { "idx": 20, "layers": [ "model.layers.10.self_attn.q_proj", "model.layers.10.self_attn.k_proj", "model.layers.10.self_attn.v_proj", "model.layers.10.self_attn.o_proj" ], "candidates": [ { "dkld": -0.001447424292564392, "dbits": 738197504 } ] }, { "idx": 21, "layers": [ "model.layers.10.mlp.gate_proj", "model.layers.10.mlp.up_proj", "model.layers.10.mlp.down_proj" ], "candidates": [ { "dkld": -0.004752121120691288, "dbits": 3992977408 } ] }, { "idx": 22, "layers": [ "model.layers.11.self_attn.q_proj", "model.layers.11.self_attn.k_proj", "model.layers.11.self_attn.v_proj", "model.layers.11.self_attn.o_proj" ], "candidates": [ { "dkld": -0.0006257966160774231, "dbits": 889192448 } ] }, { "idx": 23, "layers": [ "model.layers.11.mlp.gate_proj", "model.layers.11.mlp.up_proj", "model.layers.11.mlp.down_proj" ], "candidates": [ { "dkld": -0.00020415633916853748, "dbits": 3758096384 } ] }, { "idx": 24, "layers": [ "model.layers.12.self_attn.q_proj", "model.layers.12.self_attn.k_proj", "model.layers.12.self_attn.v_proj", "model.layers.12.self_attn.o_proj" ], "candidates": [ { "dkld": -0.0002484433352947235, "dbits": 738197504 } ] }, { "idx": 25, "layers": [ "model.layers.12.mlp.gate_proj", "model.layers.12.mlp.up_proj", "model.layers.12.mlp.down_proj" ], "candidates": [ { "dkld": -0.004421122372150421, "dbits": 3992977408 } ] }, { "idx": 26, "layers": [ "model.layers.13.self_attn.q_proj", "model.layers.13.self_attn.k_proj", "model.layers.13.self_attn.v_proj", "model.layers.13.self_attn.o_proj" ], "candidates": [ { "dkld": -0.0024481587111950254, "dbits": 738197504 } ] }, { "idx": 27, "layers": [ "model.layers.13.mlp.gate_proj", "model.layers.13.mlp.up_proj", "model.layers.13.mlp.down_proj" ], "candidates": [ { "dkld": -0.003287339210510276, "dbits": 3992977408 } ] }, { "idx": 28, "layers": [ "model.layers.14.self_attn.q_proj", "model.layers.14.self_attn.k_proj", "model.layers.14.self_attn.v_proj", "model.layers.14.self_attn.o_proj" ], "candidates": [ { "dkld": -0.002833143621683132, "dbits": 905969664 } ] }, { "idx": 29, "layers": [ "model.layers.14.mlp.gate_proj", "model.layers.14.mlp.up_proj", "model.layers.14.mlp.down_proj" ], "candidates": [ { "dkld": -0.0027410611510276794, "dbits": 3758096384 } ] }, { "idx": 30, "layers": [ "model.layers.15.self_attn.q_proj", "model.layers.15.self_attn.k_proj", "model.layers.15.self_attn.v_proj", "model.layers.15.self_attn.o_proj" ], "candidates": [ { "dkld": -0.0012485116720199474, "dbits": 738197504 } ] }, { "idx": 31, "layers": [ "model.layers.15.mlp.gate_proj", "model.layers.15.mlp.up_proj", "model.layers.15.mlp.down_proj" ], "candidates": [ { "dkld": -0.005960917472839389, "dbits": 3992977408 } ] }, { "idx": 32, "layers": [ "model.layers.16.self_attn.q_proj", "model.layers.16.self_attn.k_proj", "model.layers.16.self_attn.v_proj", "model.layers.16.self_attn.o_proj" ], "candidates": [ { "dkld": -0.0005834385752678251, "dbits": 738197504 } ] }, { "idx": 33, "layers": [ "model.layers.16.mlp.gate_proj", "model.layers.16.mlp.up_proj", "model.layers.16.mlp.down_proj" ], "candidates": [ { "dkld": -0.004872453212738048, "dbits": 3992977408 } ] }, { "idx": 34, "layers": [ "model.layers.17.self_attn.q_proj", "model.layers.17.self_attn.k_proj", "model.layers.17.self_attn.v_proj", "model.layers.17.self_attn.o_proj" ], "candidates": [ { "dkld": -0.0023185007274150737, "dbits": 889192448 } ] }, { "idx": 35, "layers": [ "model.layers.17.mlp.gate_proj", "model.layers.17.mlp.up_proj", "model.layers.17.mlp.down_proj" ], "candidates": [ { "dkld": -0.003230743855237972, "dbits": 3758096384 } ] }, { "idx": 36, "layers": [ "model.layers.18.self_attn.q_proj", "model.layers.18.self_attn.k_proj", "model.layers.18.self_attn.v_proj", "model.layers.18.self_attn.o_proj" ], "candidates": [ { "dkld": 0.00030917972326277576, "dbits": 738197504 } ] }, { "idx": 37, "layers": [ "model.layers.18.mlp.gate_proj", "model.layers.18.mlp.up_proj", "model.layers.18.mlp.down_proj" ], "candidates": [ { "dkld": -0.004292137920856476, "dbits": 3992977408 } ] }, { "idx": 38, "layers": [ "model.layers.19.self_attn.q_proj", "model.layers.19.self_attn.k_proj", "model.layers.19.self_attn.v_proj", "model.layers.19.self_attn.o_proj" ], "candidates": [ { "dkld": -0.0020743928849697446, "dbits": 738197504 } ] }, { "idx": 39, "layers": [ "model.layers.19.mlp.gate_proj", "model.layers.19.mlp.up_proj", "model.layers.19.mlp.down_proj" ], "candidates": [ { "dkld": -0.002803560346364975, "dbits": 3992977408 } ] }, { "idx": 40, "layers": [ "model.layers.20.self_attn.q_proj", "model.layers.20.self_attn.k_proj", "model.layers.20.self_attn.v_proj", "model.layers.20.self_attn.o_proj" ], "candidates": [ { "dkld": -0.002416776865720782, "dbits": 905969664 } ] }, { "idx": 41, "layers": [ "model.layers.20.mlp.gate_proj", "model.layers.20.mlp.up_proj", "model.layers.20.mlp.down_proj" ], "candidates": [ { "dkld": -0.0027277037501335366, "dbits": 3758096384 } ] }, { "idx": 42, "layers": [ "model.layers.21.self_attn.q_proj", "model.layers.21.self_attn.k_proj", "model.layers.21.self_attn.v_proj", "model.layers.21.self_attn.o_proj" ], "candidates": [ { "dkld": -0.0025502778589725494, "dbits": 738197504 } ] }, { "idx": 43, "layers": [ "model.layers.21.mlp.gate_proj", "model.layers.21.mlp.up_proj", "model.layers.21.mlp.down_proj" ], "candidates": [ { "dkld": -0.0014125540852547025, "dbits": 3992977408 } ] }, { "idx": 44, "layers": [ "model.layers.22.self_attn.q_proj", "model.layers.22.self_attn.k_proj", "model.layers.22.self_attn.v_proj", "model.layers.22.self_attn.o_proj" ], "candidates": [ { "dkld": -0.00022656917572022595, "dbits": 738197504 } ] }, { "idx": 45, "layers": [ "model.layers.22.mlp.gate_proj", "model.layers.22.mlp.up_proj", "model.layers.22.mlp.down_proj" ], "candidates": [ { "dkld": -0.006849564611911774, "dbits": 3992977408 } ] }, { "idx": 46, "layers": [ "model.layers.23.self_attn.q_proj", "model.layers.23.self_attn.k_proj", "model.layers.23.self_attn.v_proj", "model.layers.23.self_attn.o_proj" ], "candidates": [ { "dkld": -0.004920282214880001, "dbits": 889192448 } ] }, { "idx": 47, "layers": [ "model.layers.23.mlp.gate_proj", "model.layers.23.mlp.up_proj", "model.layers.23.mlp.down_proj" ], "candidates": [ { "dkld": -0.0031012043356895558, "dbits": 3758096384 } ] }, { "idx": 48, "layers": [ "model.layers.24.self_attn.q_proj", "model.layers.24.self_attn.k_proj", "model.layers.24.self_attn.v_proj", "model.layers.24.self_attn.o_proj" ], "candidates": [ { "dkld": 0.0002711758017540089, "dbits": 738197504 } ] }, { "idx": 49, "layers": [ "model.layers.24.mlp.gate_proj", "model.layers.24.mlp.up_proj", "model.layers.24.mlp.down_proj" ], "candidates": [ { "dkld": -0.007188382744789112, "dbits": 3992977408 } ] }, { "idx": 50, "layers": [ "model.layers.25.self_attn.q_proj", "model.layers.25.self_attn.k_proj", "model.layers.25.self_attn.v_proj", "model.layers.25.self_attn.o_proj" ], "candidates": [ { "dkld": -0.0012738853693008423, "dbits": 738197504 } ] }, { "idx": 51, "layers": [ "model.layers.25.mlp.gate_proj", "model.layers.25.mlp.up_proj", "model.layers.25.mlp.down_proj" ], "candidates": [ { "dkld": -0.009558118879795074, "dbits": 3992977408 } ] }, { "idx": 52, "layers": [ "model.layers.26.self_attn.q_proj", "model.layers.26.self_attn.k_proj", "model.layers.26.self_attn.v_proj", "model.layers.26.self_attn.o_proj" ], "candidates": [ { "dkld": 0.000494839251041379, "dbits": 905969664 } ] }, { "idx": 53, "layers": [ "model.layers.26.mlp.gate_proj", "model.layers.26.mlp.up_proj", "model.layers.26.mlp.down_proj" ], "candidates": [ { "dkld": -0.0024025678634643777, "dbits": 3758096384 } ] }, { "idx": 54, "layers": [ "model.layers.27.self_attn.q_proj", "model.layers.27.self_attn.k_proj", "model.layers.27.self_attn.v_proj", "model.layers.27.self_attn.o_proj" ], "candidates": [ { "dkld": -0.00167055204510691, "dbits": 738197504 } ] }, { "idx": 55, "layers": [ "model.layers.27.mlp.gate_proj", "model.layers.27.mlp.up_proj", "model.layers.27.mlp.down_proj" ], "candidates": [ { "dkld": -0.007491377741098426, "dbits": 3992977408 } ] }, { "idx": 56, "layers": [ "model.layers.28.self_attn.q_proj", "model.layers.28.self_attn.k_proj", "model.layers.28.self_attn.v_proj", "model.layers.28.self_attn.o_proj" ], "candidates": [ { "dkld": -0.0009922578930854908, "dbits": 738197504 } ] }, { "idx": 57, "layers": [ "model.layers.28.mlp.gate_proj", "model.layers.28.mlp.up_proj", "model.layers.28.mlp.down_proj" ], "candidates": [ { "dkld": -0.005037184804677963, "dbits": 3992977408 } ] }, { "idx": 58, "layers": [ "model.layers.29.self_attn.q_proj", "model.layers.29.self_attn.k_proj", "model.layers.29.self_attn.v_proj", "model.layers.29.self_attn.o_proj" ], "candidates": [ { "dkld": -0.0014149956405162811, "dbits": 889192448 } ] }, { "idx": 59, "layers": [ "model.layers.29.mlp.gate_proj", "model.layers.29.mlp.up_proj", "model.layers.29.mlp.down_proj" ], "candidates": [ { "dkld": -0.0019595958292484283, "dbits": 3758096384 } ] }, { "idx": 60, "layers": [ "model.layers.30.self_attn.q_proj", "model.layers.30.self_attn.k_proj", "model.layers.30.self_attn.v_proj", "model.layers.30.self_attn.o_proj" ], "candidates": [ { "dkld": -0.001704443246126175, "dbits": 738197504 } ] }, { "idx": 61, "layers": [ "model.layers.30.mlp.gate_proj", "model.layers.30.mlp.up_proj", "model.layers.30.mlp.down_proj" ], "candidates": [ { "dkld": -0.0029217399656772947, "dbits": 3992977408 } ] }, { "idx": 62, "layers": [ "model.layers.31.self_attn.q_proj", "model.layers.31.self_attn.k_proj", "model.layers.31.self_attn.v_proj", "model.layers.31.self_attn.o_proj" ], "candidates": [ { "dkld": -0.000850115716457378, "dbits": 738197504 } ] }, { "idx": 63, "layers": [ "model.layers.31.mlp.gate_proj", "model.layers.31.mlp.up_proj", "model.layers.31.mlp.down_proj" ], "candidates": [ { "dkld": -0.00159376859664917, "dbits": 3992977408 } ] }, { "idx": 64, "layers": [ "model.layers.32.self_attn.q_proj", "model.layers.32.self_attn.k_proj", "model.layers.32.self_attn.v_proj", "model.layers.32.self_attn.o_proj" ], "candidates": [ { "dkld": 0.00046491846442220375, "dbits": 905969664 } ] }, { "idx": 65, "layers": [ "model.layers.32.mlp.gate_proj", "model.layers.32.mlp.up_proj", "model.layers.32.mlp.down_proj" ], "candidates": [ { "dkld": -0.0024320557713508606, "dbits": 3758096384 } ] }, { "idx": 66, "layers": [ "model.layers.33.self_attn.q_proj", "model.layers.33.self_attn.k_proj", "model.layers.33.self_attn.v_proj", "model.layers.33.self_attn.o_proj" ], "candidates": [ { "dkld": 0.001894713193178188, "dbits": 738197504 } ] }, { "idx": 67, "layers": [ "model.layers.33.mlp.gate_proj", "model.layers.33.mlp.up_proj", "model.layers.33.mlp.down_proj" ], "candidates": [ { "dkld": -0.052855883538723, "dbits": 3992977408 } ] }, { "idx": 68, "layers": [ "model.layers.34.self_attn.q_proj", "model.layers.34.self_attn.k_proj", "model.layers.34.self_attn.v_proj", "model.layers.34.self_attn.o_proj" ], "candidates": [ { "dkld": -0.00030145272612575047, "dbits": 738197504 } ] }, { "idx": 69, "layers": [ "model.layers.34.mlp.gate_proj", "model.layers.34.mlp.up_proj", "model.layers.34.mlp.down_proj" ], "candidates": [ { "dkld": -0.004007309675216675, "dbits": 3992977408 } ] }, { "idx": 70, "layers": [ "model.layers.35.self_attn.q_proj", "model.layers.35.self_attn.k_proj", "model.layers.35.self_attn.v_proj", "model.layers.35.self_attn.o_proj" ], "candidates": [ { "dkld": -0.0014010682702064736, "dbits": 889192448 } ] }, { "idx": 71, "layers": [ "model.layers.35.mlp.gate_proj", "model.layers.35.mlp.up_proj", "model.layers.35.mlp.down_proj" ], "candidates": [ { "dkld": -0.0021455250680446625, "dbits": 3758096384 } ] }, { "idx": 72, "layers": [ "model.layers.36.self_attn.q_proj", "model.layers.36.self_attn.k_proj", "model.layers.36.self_attn.v_proj", "model.layers.36.self_attn.o_proj" ], "candidates": [ { "dkld": -0.0005367502570152172, "dbits": 738197504 } ] }, { "idx": 73, "layers": [ "model.layers.36.mlp.gate_proj", "model.layers.36.mlp.up_proj", "model.layers.36.mlp.down_proj" ], "candidates": [ { "dkld": -0.002586452662944827, "dbits": 3992977408 } ] }, { "idx": 74, "layers": [ "model.layers.37.self_attn.q_proj", "model.layers.37.self_attn.k_proj", "model.layers.37.self_attn.v_proj", "model.layers.37.self_attn.o_proj" ], "candidates": [ { "dkld": -0.00044670626521109424, "dbits": 738197504 } ] }, { "idx": 75, "layers": [ "model.layers.37.mlp.gate_proj", "model.layers.37.mlp.up_proj", "model.layers.37.mlp.down_proj" ], "candidates": [ { "dkld": -0.0016936622560024261, "dbits": 3992977408 } ] }, { "idx": 76, "layers": [ "model.layers.38.self_attn.q_proj", "model.layers.38.self_attn.k_proj", "model.layers.38.self_attn.v_proj", "model.layers.38.self_attn.o_proj" ], "candidates": [ { "dkld": -0.0008135810494422913, "dbits": 905969664 } ] }, { "idx": 77, "layers": [ "model.layers.38.mlp.gate_proj", "model.layers.38.mlp.up_proj", "model.layers.38.mlp.down_proj" ], "candidates": [ { "dkld": -0.001467446982860554, "dbits": 3758096384 } ] }, { "idx": 78, "layers": [ "model.layers.39.self_attn.q_proj", "model.layers.39.self_attn.k_proj", "model.layers.39.self_attn.v_proj", "model.layers.39.self_attn.o_proj" ], "candidates": [ { "dkld": -3.6989897489569934e-05, "dbits": 738197504 } ] }, { "idx": 79, "layers": [ "model.layers.39.mlp.gate_proj", "model.layers.39.mlp.up_proj", "model.layers.39.mlp.down_proj" ], "candidates": [ { "dkld": -0.0025940388441085815, "dbits": 3992977408 } ] }, { "idx": 80, "layers": [ "model.layers.40.self_attn.q_proj", "model.layers.40.self_attn.k_proj", "model.layers.40.self_attn.v_proj", "model.layers.40.self_attn.o_proj" ], "candidates": [ { "dkld": -9.927898645401001e-05, "dbits": 738197504 } ] }, { "idx": 81, "layers": [ "model.layers.40.mlp.gate_proj", "model.layers.40.mlp.up_proj", "model.layers.40.mlp.down_proj" ], "candidates": [ { "dkld": -0.0029502868652344083, "dbits": 3992977408 } ] }, { "idx": 82, "layers": [ "model.layers.41.self_attn.q_proj", "model.layers.41.self_attn.k_proj", "model.layers.41.self_attn.v_proj", "model.layers.41.self_attn.o_proj" ], "candidates": [ { "dkld": -0.0014719873666763639, "dbits": 889192448 } ] }, { "idx": 83, "layers": [ "model.layers.41.mlp.gate_proj", "model.layers.41.mlp.up_proj", "model.layers.41.mlp.down_proj" ], "candidates": [ { "dkld": -0.001874080300331149, "dbits": 3758096384 } ] }, { "idx": 84, "layers": [ "model.layers.42.self_attn.q_proj", "model.layers.42.self_attn.k_proj", "model.layers.42.self_attn.v_proj", "model.layers.42.self_attn.o_proj" ], "candidates": [ { "dkld": -0.00024567171931266785, "dbits": 738197504 } ] }, { "idx": 85, "layers": [ "model.layers.42.mlp.gate_proj", "model.layers.42.mlp.up_proj", "model.layers.42.mlp.down_proj" ], "candidates": [ { "dkld": -0.00040401890873908997, "dbits": 3992977408 } ] }, { "idx": 86, "layers": [ "model.layers.43.self_attn.q_proj", "model.layers.43.self_attn.k_proj", "model.layers.43.self_attn.v_proj", "model.layers.43.self_attn.o_proj" ], "candidates": [ { "dkld": -0.0002549886703491211, "dbits": 738197504 } ] }, { "idx": 87, "layers": [ "model.layers.43.mlp.gate_proj", "model.layers.43.mlp.up_proj", "model.layers.43.mlp.down_proj" ], "candidates": [ { "dkld": -0.0022446349263191556, "dbits": 3992977408 } ] }, { "idx": 88, "layers": [ "model.layers.44.self_attn.q_proj", "model.layers.44.self_attn.k_proj", "model.layers.44.self_attn.v_proj", "model.layers.44.self_attn.o_proj" ], "candidates": [ { "dkld": 0.0011071011424064747, "dbits": 905969664 } ] }, { "idx": 89, "layers": [ "model.layers.44.mlp.gate_proj", "model.layers.44.mlp.up_proj", "model.layers.44.mlp.down_proj" ], "candidates": [ { "dkld": -0.0011970192193985207, "dbits": 3758096384 } ] }, { "idx": 90, "layers": [ "model.layers.45.self_attn.q_proj", "model.layers.45.self_attn.k_proj", "model.layers.45.self_attn.v_proj", "model.layers.45.self_attn.o_proj" ], "candidates": [ { "dkld": 0.00023729130625721462, "dbits": 738197504 } ] }, { "idx": 91, "layers": [ "model.layers.45.mlp.gate_proj", "model.layers.45.mlp.up_proj", "model.layers.45.mlp.down_proj" ], "candidates": [ { "dkld": -0.0017736770212650188, "dbits": 3992977408 } ] }, { "idx": 92, "layers": [ "model.layers.46.self_attn.q_proj", "model.layers.46.self_attn.k_proj", "model.layers.46.self_attn.v_proj", "model.layers.46.self_attn.o_proj" ], "candidates": [ { "dkld": -0.0002747580409049877, "dbits": 738197504 } ] }, { "idx": 93, "layers": [ "model.layers.46.mlp.gate_proj", "model.layers.46.mlp.up_proj", "model.layers.46.mlp.down_proj" ], "candidates": [ { "dkld": -0.001975349336862553, "dbits": 3992977408 } ] }, { "idx": 94, "layers": [ "model.layers.47.self_attn.q_proj", "model.layers.47.self_attn.k_proj", "model.layers.47.self_attn.v_proj", "model.layers.47.self_attn.o_proj" ], "candidates": [ { "dkld": -0.00030905306339262806, "dbits": 889192448 } ] }, { "idx": 95, "layers": [ "model.layers.47.mlp.gate_proj", "model.layers.47.mlp.up_proj", "model.layers.47.mlp.down_proj" ], "candidates": [ { "dkld": -0.0007587954401970243, "dbits": 3758096384 } ] }, { "idx": 96, "layers": [ "model.layers.48.self_attn.q_proj", "model.layers.48.self_attn.k_proj", "model.layers.48.self_attn.v_proj", "model.layers.48.self_attn.o_proj" ], "candidates": [ { "dkld": 3.125369548795387e-05, "dbits": 738197504 } ] }, { "idx": 97, "layers": [ "model.layers.48.mlp.gate_proj", "model.layers.48.mlp.up_proj", "model.layers.48.mlp.down_proj" ], "candidates": [ { "dkld": -0.0019631803035736195, "dbits": 3992977408 } ] }, { "idx": 98, "layers": [ "model.layers.49.self_attn.q_proj", "model.layers.49.self_attn.k_proj", "model.layers.49.self_attn.v_proj", "model.layers.49.self_attn.o_proj" ], "candidates": [ { "dkld": -1.0006129742001768e-06, "dbits": 738197504 } ] }, { "idx": 99, "layers": [ "model.layers.49.mlp.gate_proj", "model.layers.49.mlp.up_proj", "model.layers.49.mlp.down_proj" ], "candidates": [ { "dkld": -0.001709944009780917, "dbits": 3992977408 } ] }, { "idx": 100, "layers": [ "model.layers.50.self_attn.q_proj", "model.layers.50.self_attn.k_proj", "model.layers.50.self_attn.v_proj", "model.layers.50.self_attn.o_proj" ], "candidates": [ { "dkld": -0.0010612852871418332, "dbits": 905969664 } ] }, { "idx": 101, "layers": [ "model.layers.50.mlp.gate_proj", "model.layers.50.mlp.up_proj", "model.layers.50.mlp.down_proj" ], "candidates": [ { "dkld": -0.0012442149221897347, "dbits": 3758096384 } ] }, { "idx": 102, "layers": [ "model.layers.51.self_attn.q_proj", "model.layers.51.self_attn.k_proj", "model.layers.51.self_attn.v_proj", "model.layers.51.self_attn.o_proj" ], "candidates": [ { "dkld": 5.979090929031372e-06, "dbits": 738197504 } ] }, { "idx": 103, "layers": [ "model.layers.51.mlp.gate_proj", "model.layers.51.mlp.up_proj", "model.layers.51.mlp.down_proj" ], "candidates": [ { "dkld": -0.002553432434797276, "dbits": 3992977408 } ] }, { "idx": 104, "layers": [ "model.layers.52.self_attn.q_proj", "model.layers.52.self_attn.k_proj", "model.layers.52.self_attn.v_proj", "model.layers.52.self_attn.o_proj" ], "candidates": [ { "dkld": 0.00014900416135787964, "dbits": 738197504 } ] }, { "idx": 105, "layers": [ "model.layers.52.mlp.gate_proj", "model.layers.52.mlp.up_proj", "model.layers.52.mlp.down_proj" ], "candidates": [ { "dkld": -0.0011335775256157143, "dbits": 3992977408 } ] }, { "idx": 106, "layers": [ "model.layers.53.self_attn.q_proj", "model.layers.53.self_attn.k_proj", "model.layers.53.self_attn.v_proj", "model.layers.53.self_attn.o_proj" ], "candidates": [ { "dkld": 0.0002890184521674999, "dbits": 889192448 } ] }, { "idx": 107, "layers": [ "model.layers.53.mlp.gate_proj", "model.layers.53.mlp.up_proj", "model.layers.53.mlp.down_proj" ], "candidates": [ { "dkld": -0.0009270764887333027, "dbits": 3758096384 } ] }, { "idx": 108, "layers": [ "model.layers.54.self_attn.q_proj", "model.layers.54.self_attn.k_proj", "model.layers.54.self_attn.v_proj", "model.layers.54.self_attn.o_proj" ], "candidates": [ { "dkld": -0.0002333708107471466, "dbits": 738197504 } ] }, { "idx": 109, "layers": [ "model.layers.54.mlp.gate_proj", "model.layers.54.mlp.up_proj", "model.layers.54.mlp.down_proj" ], "candidates": [ { "dkld": -0.0003963261842727661, "dbits": 3992977408 } ] }, { "idx": 110, "layers": [ "model.layers.55.self_attn.q_proj", "model.layers.55.self_attn.k_proj", "model.layers.55.self_attn.v_proj", "model.layers.55.self_attn.o_proj" ], "candidates": [ { "dkld": -0.00016106069087984398, "dbits": 738197504 } ] }, { "idx": 111, "layers": [ "model.layers.55.mlp.gate_proj", "model.layers.55.mlp.up_proj", "model.layers.55.mlp.down_proj" ], "candidates": [ { "dkld": -0.0012215971946716309, "dbits": 3992977408 } ] }, { "idx": 112, "layers": [ "model.layers.56.self_attn.q_proj", "model.layers.56.self_attn.k_proj", "model.layers.56.self_attn.v_proj", "model.layers.56.self_attn.o_proj" ], "candidates": [ { "dkld": -0.0006153158843517637, "dbits": 905969664 } ] }, { "idx": 113, "layers": [ "model.layers.56.mlp.gate_proj", "model.layers.56.mlp.up_proj", "model.layers.56.mlp.down_proj" ], "candidates": [ { "dkld": -0.0016429744660854673, "dbits": 3758096384 } ] }, { "idx": 114, "layers": [ "model.layers.57.self_attn.q_proj", "model.layers.57.self_attn.k_proj", "model.layers.57.self_attn.v_proj", "model.layers.57.self_attn.o_proj" ], "candidates": [ { "dkld": 0.0001778826117515564, "dbits": 738197504 } ] }, { "idx": 115, "layers": [ "model.layers.57.mlp.gate_proj", "model.layers.57.mlp.up_proj", "model.layers.57.mlp.down_proj" ], "candidates": [ { "dkld": -0.0022293925285339355, "dbits": 3992977408 } ] }, { "idx": 116, "layers": [ "model.layers.58.self_attn.q_proj", "model.layers.58.self_attn.k_proj", "model.layers.58.self_attn.v_proj", "model.layers.58.self_attn.o_proj" ], "candidates": [ { "dkld": -0.00014604702591897167, "dbits": 738197504 } ] }, { "idx": 117, "layers": [ "model.layers.58.mlp.gate_proj", "model.layers.58.mlp.up_proj", "model.layers.58.mlp.down_proj" ], "candidates": [ { "dkld": -0.002245902270078648, "dbits": 3992977408 } ] }, { "idx": 118, "layers": [ "model.layers.59.self_attn.q_proj", "model.layers.59.self_attn.k_proj", "model.layers.59.self_attn.v_proj", "model.layers.59.self_attn.o_proj" ], "candidates": [ { "dkld": -0.0006127975881100034, "dbits": 889192448 } ] }, { "idx": 119, "layers": [ "model.layers.59.mlp.gate_proj", "model.layers.59.mlp.up_proj", "model.layers.59.mlp.down_proj" ], "candidates": [ { "dkld": -0.0006488725543022378, "dbits": 3758096384 } ] }, { "idx": 120, "layers": [ "model.layers.60.self_attn.q_proj", "model.layers.60.self_attn.k_proj", "model.layers.60.self_attn.v_proj", "model.layers.60.self_attn.o_proj" ], "candidates": [ { "dkld": -0.00037203654646872364, "dbits": 738197504 } ] }, { "idx": 121, "layers": [ "model.layers.60.mlp.gate_proj", "model.layers.60.mlp.up_proj", "model.layers.60.mlp.down_proj" ], "candidates": [ { "dkld": -0.001387310028076183, "dbits": 3992977408 } ] }, { "idx": 122, "layers": [ "model.layers.61.self_attn.q_proj", "model.layers.61.self_attn.k_proj", "model.layers.61.self_attn.v_proj", "model.layers.61.self_attn.o_proj" ], "candidates": [ { "dkld": -6.945207715036705e-05, "dbits": 738197504 } ] }, { "idx": 123, "layers": [ "model.layers.61.mlp.gate_proj", "model.layers.61.mlp.up_proj", "model.layers.61.mlp.down_proj" ], "candidates": [ { "dkld": -0.0016146205365658028, "dbits": 3992977408 } ] }, { "idx": 124, "layers": [ "model.layers.62.self_attn.q_proj", "model.layers.62.self_attn.k_proj", "model.layers.62.self_attn.v_proj", "model.layers.62.self_attn.o_proj" ], "candidates": [ { "dkld": -0.000191771984100364, "dbits": 905969664 } ] }, { "idx": 125, "layers": [ "model.layers.62.mlp.gate_proj", "model.layers.62.mlp.up_proj", "model.layers.62.mlp.down_proj" ], "candidates": [ { "dkld": -0.00017061755061148487, "dbits": 3758096384 } ] }, { "idx": 126, "layers": [ "model.layers.63.self_attn.q_proj", "model.layers.63.self_attn.k_proj", "model.layers.63.self_attn.v_proj", "model.layers.63.self_attn.o_proj" ], "candidates": [ { "dkld": 0.0001552104949951172, "dbits": 738197504 } ] }, { "idx": 127, "layers": [ "model.layers.63.mlp.gate_proj", "model.layers.63.mlp.up_proj", "model.layers.63.mlp.down_proj" ], "candidates": [ { "dkld": -0.0008582346141338681, "dbits": 3992977408 } ] }, { "idx": 128, "layers": [ "model.layers.64.self_attn.q_proj", "model.layers.64.self_attn.k_proj", "model.layers.64.self_attn.v_proj", "model.layers.64.self_attn.o_proj" ], "candidates": [ { "dkld": -5.263239145281151e-05, "dbits": 738197504 } ] }, { "idx": 129, "layers": [ "model.layers.64.mlp.gate_proj", "model.layers.64.mlp.up_proj", "model.layers.64.mlp.down_proj" ], "candidates": [ { "dkld": -0.0011672548949718808, "dbits": 3992977408 } ] }, { "idx": 130, "layers": [ "model.layers.65.self_attn.q_proj", "model.layers.65.self_attn.k_proj", "model.layers.65.self_attn.v_proj", "model.layers.65.self_attn.o_proj" ], "candidates": [ { "dkld": 5.4321438074100836e-05, "dbits": 889192448 } ] }, { "idx": 131, "layers": [ "model.layers.65.mlp.gate_proj", "model.layers.65.mlp.up_proj", "model.layers.65.mlp.down_proj" ], "candidates": [ { "dkld": -0.0024182021617889515, "dbits": 3758096384 } ] }, { "idx": 132, "layers": [ "model.layers.66.self_attn.q_proj", "model.layers.66.self_attn.k_proj", "model.layers.66.self_attn.v_proj", "model.layers.66.self_attn.o_proj" ], "candidates": [ { "dkld": 0.00020356997847553737, "dbits": 738197504 } ] }, { "idx": 133, "layers": [ "model.layers.66.mlp.gate_proj", "model.layers.66.mlp.up_proj", "model.layers.66.mlp.down_proj" ], "candidates": [ { "dkld": -0.0022752024233341217, "dbits": 3992977408 } ] }, { "idx": 134, "layers": [ "model.layers.67.self_attn.q_proj", "model.layers.67.self_attn.k_proj", "model.layers.67.self_attn.v_proj", "model.layers.67.self_attn.o_proj" ], "candidates": [ { "dkld": -0.00012925267219543457, "dbits": 738197504 } ] }, { "idx": 135, "layers": [ "model.layers.67.mlp.gate_proj", "model.layers.67.mlp.up_proj", "model.layers.67.mlp.down_proj" ], "candidates": [ { "dkld": -0.0015775948762893899, "dbits": 3992977408 } ] }, { "idx": 136, "layers": [ "model.layers.68.self_attn.q_proj", "model.layers.68.self_attn.k_proj", "model.layers.68.self_attn.v_proj", "model.layers.68.self_attn.o_proj" ], "candidates": [ { "dkld": 0.0008239254355430492, "dbits": 905969664 } ] }, { "idx": 137, "layers": [ "model.layers.68.mlp.gate_proj", "model.layers.68.mlp.up_proj", "model.layers.68.mlp.down_proj" ], "candidates": [ { "dkld": -0.0015405334532260784, "dbits": 3758096384 } ] }, { "idx": 138, "layers": [ "model.layers.69.self_attn.q_proj", "model.layers.69.self_attn.k_proj", "model.layers.69.self_attn.v_proj", "model.layers.69.self_attn.o_proj" ], "candidates": [ { "dkld": 0.0003462061285972595, "dbits": 738197504 } ] }, { "idx": 139, "layers": [ "model.layers.69.mlp.gate_proj", "model.layers.69.mlp.up_proj", "model.layers.69.mlp.down_proj" ], "candidates": [ { "dkld": -0.002347015589475643, "dbits": 3992977408 } ] }, { "idx": 140, "layers": [ "model.layers.70.self_attn.q_proj", "model.layers.70.self_attn.k_proj", "model.layers.70.self_attn.v_proj", "model.layers.70.self_attn.o_proj" ], "candidates": [ { "dkld": -0.0006616875529289468, "dbits": 738197504 } ] }, { "idx": 141, "layers": [ "model.layers.70.mlp.gate_proj", "model.layers.70.mlp.up_proj", "model.layers.70.mlp.down_proj" ], "candidates": [ { "dkld": -0.0012796513736247905, "dbits": 3992977408 } ] }, { "idx": 142, "layers": [ "model.layers.71.self_attn.q_proj", "model.layers.71.self_attn.k_proj", "model.layers.71.self_attn.v_proj", "model.layers.71.self_attn.o_proj" ], "candidates": [ { "dkld": 0.00013310834765434265, "dbits": 889192448 } ] }, { "idx": 143, "layers": [ "model.layers.71.mlp.gate_proj", "model.layers.71.mlp.up_proj", "model.layers.71.mlp.down_proj" ], "candidates": [ { "dkld": -0.0006833486258983612, "dbits": 3758096384 } ] }, { "idx": 144, "layers": [ "model.layers.72.self_attn.q_proj", "model.layers.72.self_attn.k_proj", "model.layers.72.self_attn.v_proj", "model.layers.72.self_attn.o_proj" ], "candidates": [ { "dkld": 0.0005676642060279957, "dbits": 738197504 } ] }, { "idx": 145, "layers": [ "model.layers.72.mlp.gate_proj", "model.layers.72.mlp.up_proj", "model.layers.72.mlp.down_proj" ], "candidates": [ { "dkld": -0.0004349157214164623, "dbits": 3992977408 } ] }, { "idx": 146, "layers": [ "model.layers.73.self_attn.q_proj", "model.layers.73.self_attn.k_proj", "model.layers.73.self_attn.v_proj", "model.layers.73.self_attn.o_proj" ], "candidates": [ { "dkld": 0.0004612252116203419, "dbits": 738197504 } ] }, { "idx": 147, "layers": [ "model.layers.73.mlp.gate_proj", "model.layers.73.mlp.up_proj", "model.layers.73.mlp.down_proj" ], "candidates": [ { "dkld": -0.0011448636651039124, "dbits": 3992977408 } ] }, { "idx": 148, "layers": [ "model.layers.74.self_attn.q_proj", "model.layers.74.self_attn.k_proj", "model.layers.74.self_attn.v_proj", "model.layers.74.self_attn.o_proj" ], "candidates": [ { "dkld": -0.0007353387773036957, "dbits": 905969664 } ] }, { "idx": 149, "layers": [ "model.layers.74.mlp.gate_proj", "model.layers.74.mlp.up_proj", "model.layers.74.mlp.down_proj" ], "candidates": [ { "dkld": -0.0005259498953819608, "dbits": 3758096384 } ] }, { "idx": 150, "layers": [ "model.layers.75.self_attn.q_proj", "model.layers.75.self_attn.k_proj", "model.layers.75.self_attn.v_proj", "model.layers.75.self_attn.o_proj" ], "candidates": [ { "dkld": -0.0006746903061866649, "dbits": 738197504 } ] }, { "idx": 151, "layers": [ "model.layers.75.mlp.gate_proj", "model.layers.75.mlp.up_proj", "model.layers.75.mlp.down_proj" ], "candidates": [ { "dkld": -0.003875626623630557, "dbits": 3992977408 } ] }, { "idx": 152, "layers": [ "model.layers.76.self_attn.q_proj", "model.layers.76.self_attn.k_proj", "model.layers.76.self_attn.v_proj", "model.layers.76.self_attn.o_proj" ], "candidates": [ { "dkld": 0.00046416595578191444, "dbits": 738197504 } ] }, { "idx": 153, "layers": [ "model.layers.76.mlp.gate_proj", "model.layers.76.mlp.up_proj", "model.layers.76.mlp.down_proj" ], "candidates": [ { "dkld": -0.0033396854996681213, "dbits": 3992977408 } ] }, { "idx": 154, "layers": [ "model.layers.77.self_attn.q_proj", "model.layers.77.self_attn.k_proj", "model.layers.77.self_attn.v_proj", "model.layers.77.self_attn.o_proj" ], "candidates": [ { "dkld": -0.002440282702446006, "dbits": 889192448 } ] }, { "idx": 155, "layers": [ "model.layers.77.mlp.gate_proj", "model.layers.77.mlp.up_proj", "model.layers.77.mlp.down_proj" ], "candidates": [ { "dkld": -0.0019791118800639995, "dbits": 3758096384 } ] }, { "idx": 156, "layers": [ "model.layers.78.self_attn.q_proj", "model.layers.78.self_attn.k_proj", "model.layers.78.self_attn.v_proj", "model.layers.78.self_attn.o_proj" ], "candidates": [ { "dkld": -5.7355314493190424e-05, "dbits": 738197504 } ] }, { "idx": 157, "layers": [ "model.layers.78.mlp.gate_proj", "model.layers.78.mlp.up_proj", "model.layers.78.mlp.down_proj" ], "candidates": [ { "dkld": -0.004291430115699768, "dbits": 3992977408 } ] }, { "idx": 158, "layers": [ "model.layers.79.self_attn.q_proj", "model.layers.79.self_attn.k_proj", "model.layers.79.self_attn.v_proj", "model.layers.79.self_attn.o_proj" ], "candidates": [ { "dkld": 0.0003275744616985099, "dbits": 738197504 } ] }, { "idx": 159, "layers": [ "model.layers.79.mlp.gate_proj", "model.layers.79.mlp.up_proj", "model.layers.79.mlp.down_proj" ], "candidates": [ { "dkld": -0.004522088915109634, "dbits": 3992977408 } ] } ], "base_kld": 0.3534683778882027, "arch_string": "LlamaForCausalLM" }