Download measurement.json from WeReCooking/AesCode-32B-EXL3: direct link, hf CLI and curl.
- Browser
- Download file 80.6 kB
-
https://huggingface.co/WeReCooking/AesCode-32B-EXL3/resolve/main/measurement.json
- Command line
-
hf download hf://WeReCooking/AesCode-32B-EXL3/measurement.json
-
curl -L -o measurement.json https://huggingface.co/WeReCooking/AesCode-32B-EXL3/resolve/main/measurement.json
80.6 kB
| { | |
| "base": { | |
| "dir": "D:\\main\\program\\AI\\tmp\\exl3_aescode\\quants\\3.0bpw_H6", | |
| "bpw": 3.004301534673219 | |
| }, | |
| "alts": [ | |
| { | |
| "dir": "D:\\main\\program\\AI\\tmp\\exl3_aescode\\quants\\4.0bpw_H6", | |
| "bpw": 4.004301534673219 | |
| }, | |
| { | |
| "dir": "D:\\main\\program\\AI\\tmp\\exl3_aescode\\quants\\5.0bpw_H6", | |
| "bpw": 5.004301534673219 | |
| } | |
| ], | |
| "groups": [ | |
| { | |
| "idx": 0, | |
| "layers": [ | |
| "model.language_model.layers.0.self_attn.q_proj", | |
| "model.language_model.layers.0.self_attn.k_proj", | |
| "model.language_model.layers.0.self_attn.v_proj", | |
| "model.language_model.layers.0.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 0.005342455487698294, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": 0.002878085989505036, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 1, | |
| "layers": [ | |
| "model.language_model.layers.0.mlp.gate_proj", | |
| "model.language_model.layers.0.mlp.up_proj", | |
| "model.language_model.layers.0.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 0.0010677056852728128, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.050666560931131255, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 2, | |
| "layers": [ | |
| "model.language_model.layers.1.self_attn.q_proj", | |
| "model.language_model.layers.1.self_attn.k_proj", | |
| "model.language_model.layers.1.self_attn.v_proj", | |
| "model.language_model.layers.1.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.1397632632870227, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -0.15157142621465028, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 3, | |
| "layers": [ | |
| "model.language_model.layers.1.mlp.gate_proj", | |
| "model.language_model.layers.1.mlp.up_proj", | |
| "model.language_model.layers.1.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 0.0028491628821939174, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": 0.0034188396297395174, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 4, | |
| "layers": [ | |
| "model.language_model.layers.2.self_attn.q_proj", | |
| "model.language_model.layers.2.self_attn.k_proj", | |
| "model.language_model.layers.2.self_attn.v_proj", | |
| "model.language_model.layers.2.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.1418308971915394, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -0.011705041117966192, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 5, | |
| "layers": [ | |
| "model.language_model.layers.2.mlp.gate_proj", | |
| "model.language_model.layers.2.mlp.up_proj", | |
| "model.language_model.layers.2.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.0067629903089255206, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.00024901125580073513, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 6, | |
| "layers": [ | |
| "model.language_model.layers.3.self_attn.q_proj", | |
| "model.language_model.layers.3.self_attn.k_proj", | |
| "model.language_model.layers.3.self_attn.v_proj", | |
| "model.language_model.layers.3.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.0072793466039002, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -0.1536645043641329, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 7, | |
| "layers": [ | |
| "model.language_model.layers.3.mlp.gate_proj", | |
| "model.language_model.layers.3.mlp.up_proj", | |
| "model.language_model.layers.3.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.006463171308860205, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": 0.008568887179717405, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 8, | |
| "layers": [ | |
| "model.language_model.layers.4.self_attn.q_proj", | |
| "model.language_model.layers.4.self_attn.k_proj", | |
| "model.language_model.layers.4.self_attn.v_proj", | |
| "model.language_model.layers.4.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 0.004537224862724537, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": 0.0033987248782068324, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 9, | |
| "layers": [ | |
| "model.language_model.layers.4.mlp.gate_proj", | |
| "model.language_model.layers.4.mlp.up_proj", | |
| "model.language_model.layers.4.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 0.00795677597634492, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.1482118721585721, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 10, | |
| "layers": [ | |
| "model.language_model.layers.5.self_attn.q_proj", | |
| "model.language_model.layers.5.self_attn.k_proj", | |
| "model.language_model.layers.5.self_attn.v_proj", | |
| "model.language_model.layers.5.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.009429611032828689, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -0.014525620499625802, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 11, | |
| "layers": [ | |
| "model.language_model.layers.5.mlp.gate_proj", | |
| "model.language_model.layers.5.mlp.up_proj", | |
| "model.language_model.layers.5.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 0.002557756146416068, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": 0.004029345652088512, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 12, | |
| "layers": [ | |
| "model.language_model.layers.6.self_attn.q_proj", | |
| "model.language_model.layers.6.self_attn.k_proj", | |
| "model.language_model.layers.6.self_attn.v_proj", | |
| "model.language_model.layers.6.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.05095413839444518, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -0.060551986517384665, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 13, | |
| "layers": [ | |
| "model.language_model.layers.6.mlp.gate_proj", | |
| "model.language_model.layers.6.mlp.up_proj", | |
| "model.language_model.layers.6.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 0.0034258951433002727, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": 0.004030669433996076, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 14, | |
| "layers": [ | |
| "model.language_model.layers.7.self_attn.q_proj", | |
| "model.language_model.layers.7.self_attn.k_proj", | |
| "model.language_model.layers.7.self_attn.v_proj", | |
| "model.language_model.layers.7.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 0.00012257243506608173, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -2.733203582466759e-05, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 15, | |
| "layers": [ | |
| "model.language_model.layers.7.mlp.gate_proj", | |
| "model.language_model.layers.7.mlp.up_proj", | |
| "model.language_model.layers.7.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.00040053990669550177, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.00045577390119433403, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 16, | |
| "layers": [ | |
| "model.language_model.layers.8.self_attn.q_proj", | |
| "model.language_model.layers.8.self_attn.k_proj", | |
| "model.language_model.layers.8.self_attn.v_proj", | |
| "model.language_model.layers.8.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 3.334633074700277e-05, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -0.00012314599007368088, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 17, | |
| "layers": [ | |
| "model.language_model.layers.8.mlp.gate_proj", | |
| "model.language_model.layers.8.mlp.up_proj", | |
| "model.language_model.layers.8.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.00010292534716427326, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -7.305359467865702e-05, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 18, | |
| "layers": [ | |
| "model.language_model.layers.9.self_attn.q_proj", | |
| "model.language_model.layers.9.self_attn.k_proj", | |
| "model.language_model.layers.9.self_attn.v_proj", | |
| "model.language_model.layers.9.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 2.7341675013281552e-05, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": 9.749447926876709e-05, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 19, | |
| "layers": [ | |
| "model.language_model.layers.9.mlp.gate_proj", | |
| "model.language_model.layers.9.mlp.up_proj", | |
| "model.language_model.layers.9.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 0.0003252701833844074, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": 0.00020022029057142898, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 20, | |
| "layers": [ | |
| "model.language_model.layers.10.self_attn.q_proj", | |
| "model.language_model.layers.10.self_attn.k_proj", | |
| "model.language_model.layers.10.self_attn.v_proj", | |
| "model.language_model.layers.10.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 0.00011542919091878101, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": 7.19995703548082e-05, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 21, | |
| "layers": [ | |
| "model.language_model.layers.10.mlp.gate_proj", | |
| "model.language_model.layers.10.mlp.up_proj", | |
| "model.language_model.layers.10.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.0002729880623519587, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.00010036383755507305, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 22, | |
| "layers": [ | |
| "model.language_model.layers.11.self_attn.q_proj", | |
| "model.language_model.layers.11.self_attn.k_proj", | |
| "model.language_model.layers.11.self_attn.v_proj", | |
| "model.language_model.layers.11.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 4.468513652680639e-05, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": 5.694916471837841e-05, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 23, | |
| "layers": [ | |
| "model.language_model.layers.11.mlp.gate_proj", | |
| "model.language_model.layers.11.mlp.up_proj", | |
| "model.language_model.layers.11.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.000621724314987665, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.0003705095499754174, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 24, | |
| "layers": [ | |
| "model.language_model.layers.12.self_attn.q_proj", | |
| "model.language_model.layers.12.self_attn.k_proj", | |
| "model.language_model.layers.12.self_attn.v_proj", | |
| "model.language_model.layers.12.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 2.4668266996735744e-05, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -9.445403702557087e-05, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 25, | |
| "layers": [ | |
| "model.language_model.layers.12.mlp.gate_proj", | |
| "model.language_model.layers.12.mlp.up_proj", | |
| "model.language_model.layers.12.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.0003460992127657103, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.00034626852720975876, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 26, | |
| "layers": [ | |
| "model.language_model.layers.13.self_attn.q_proj", | |
| "model.language_model.layers.13.self_attn.k_proj", | |
| "model.language_model.layers.13.self_attn.v_proj", | |
| "model.language_model.layers.13.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.000152776110917352, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -0.00025113103911281187, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 27, | |
| "layers": [ | |
| "model.language_model.layers.13.mlp.gate_proj", | |
| "model.language_model.layers.13.mlp.up_proj", | |
| "model.language_model.layers.13.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.0007007658015936724, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.00030329353176059004, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 28, | |
| "layers": [ | |
| "model.language_model.layers.14.self_attn.q_proj", | |
| "model.language_model.layers.14.self_attn.k_proj", | |
| "model.language_model.layers.14.self_attn.v_proj", | |
| "model.language_model.layers.14.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 4.437807947396677e-05, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -2.7742749080073015e-05, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 29, | |
| "layers": [ | |
| "model.language_model.layers.14.mlp.gate_proj", | |
| "model.language_model.layers.14.mlp.up_proj", | |
| "model.language_model.layers.14.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.00022678198292852558, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.0002609751652926373, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 30, | |
| "layers": [ | |
| "model.language_model.layers.15.self_attn.q_proj", | |
| "model.language_model.layers.15.self_attn.k_proj", | |
| "model.language_model.layers.15.self_attn.v_proj", | |
| "model.language_model.layers.15.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.00016537196934224285, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -0.00027730665169656277, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 31, | |
| "layers": [ | |
| "model.language_model.layers.15.mlp.gate_proj", | |
| "model.language_model.layers.15.mlp.up_proj", | |
| "model.language_model.layers.15.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.0002389888744801505, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.00022584153339266777, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 32, | |
| "layers": [ | |
| "model.language_model.layers.16.self_attn.q_proj", | |
| "model.language_model.layers.16.self_attn.k_proj", | |
| "model.language_model.layers.16.self_attn.v_proj", | |
| "model.language_model.layers.16.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 8.467026054859161e-05, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": 6.083534099160515e-05, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 33, | |
| "layers": [ | |
| "model.language_model.layers.16.mlp.gate_proj", | |
| "model.language_model.layers.16.mlp.up_proj", | |
| "model.language_model.layers.16.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.00029788915999234833, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.00023291488178076025, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 34, | |
| "layers": [ | |
| "model.language_model.layers.17.self_attn.q_proj", | |
| "model.language_model.layers.17.self_attn.k_proj", | |
| "model.language_model.layers.17.self_attn.v_proj", | |
| "model.language_model.layers.17.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.00013766633346679047, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -0.0002778722904622777, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 35, | |
| "layers": [ | |
| "model.language_model.layers.17.mlp.gate_proj", | |
| "model.language_model.layers.17.mlp.up_proj", | |
| "model.language_model.layers.17.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 3.100791946053505e-05, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -1.545818522574738e-05, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 36, | |
| "layers": [ | |
| "model.language_model.layers.18.self_attn.q_proj", | |
| "model.language_model.layers.18.self_attn.k_proj", | |
| "model.language_model.layers.18.self_attn.v_proj", | |
| "model.language_model.layers.18.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 2.829506993293207e-05, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -4.0968367829935515e-05, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 37, | |
| "layers": [ | |
| "model.language_model.layers.18.mlp.gate_proj", | |
| "model.language_model.layers.18.mlp.up_proj", | |
| "model.language_model.layers.18.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -8.97957943379879e-06, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.00019588181748986244, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 38, | |
| "layers": [ | |
| "model.language_model.layers.19.self_attn.q_proj", | |
| "model.language_model.layers.19.self_attn.k_proj", | |
| "model.language_model.layers.19.self_attn.v_proj", | |
| "model.language_model.layers.19.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 0.0001437588594853656, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": 0.0001899583265185245, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 39, | |
| "layers": [ | |
| "model.language_model.layers.19.mlp.gate_proj", | |
| "model.language_model.layers.19.mlp.up_proj", | |
| "model.language_model.layers.19.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.0001980282366275954, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.00021657398901880898, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 40, | |
| "layers": [ | |
| "model.language_model.layers.20.self_attn.q_proj", | |
| "model.language_model.layers.20.self_attn.k_proj", | |
| "model.language_model.layers.20.self_attn.v_proj", | |
| "model.language_model.layers.20.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.00013915137387812693, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -7.083872333168983e-05, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 41, | |
| "layers": [ | |
| "model.language_model.layers.20.mlp.gate_proj", | |
| "model.language_model.layers.20.mlp.up_proj", | |
| "model.language_model.layers.20.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -1.2000277638452017e-05, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -6.155669689178467e-05, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 42, | |
| "layers": [ | |
| "model.language_model.layers.21.self_attn.q_proj", | |
| "model.language_model.layers.21.self_attn.k_proj", | |
| "model.language_model.layers.21.self_attn.v_proj", | |
| "model.language_model.layers.21.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 0.00012218807823954903, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": 0.00018510879017410997, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 43, | |
| "layers": [ | |
| "model.language_model.layers.21.mlp.gate_proj", | |
| "model.language_model.layers.21.mlp.up_proj", | |
| "model.language_model.layers.21.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.00025624348782005146, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.0002975346054882033, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 44, | |
| "layers": [ | |
| "model.language_model.layers.22.self_attn.q_proj", | |
| "model.language_model.layers.22.self_attn.k_proj", | |
| "model.language_model.layers.22.self_attn.v_proj", | |
| "model.language_model.layers.22.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.00014645280316472054, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -0.0002074604388326573, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 45, | |
| "layers": [ | |
| "model.language_model.layers.22.mlp.gate_proj", | |
| "model.language_model.layers.22.mlp.up_proj", | |
| "model.language_model.layers.22.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -2.5052111596035598e-06, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": 8.436250500379328e-05, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 46, | |
| "layers": [ | |
| "model.language_model.layers.23.self_attn.q_proj", | |
| "model.language_model.layers.23.self_attn.k_proj", | |
| "model.language_model.layers.23.self_attn.v_proj", | |
| "model.language_model.layers.23.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -7.000300101936419e-05, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -5.9204548597341367e-05, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 47, | |
| "layers": [ | |
| "model.language_model.layers.23.mlp.gate_proj", | |
| "model.language_model.layers.23.mlp.up_proj", | |
| "model.language_model.layers.23.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.0003282364923506975, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.0002834261395037174, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 48, | |
| "layers": [ | |
| "model.language_model.layers.24.self_attn.q_proj", | |
| "model.language_model.layers.24.self_attn.k_proj", | |
| "model.language_model.layers.24.self_attn.v_proj", | |
| "model.language_model.layers.24.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.00010582348331811264, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": 4.957020282744806e-05, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 49, | |
| "layers": [ | |
| "model.language_model.layers.24.mlp.gate_proj", | |
| "model.language_model.layers.24.mlp.up_proj", | |
| "model.language_model.layers.24.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -4.923101514578421e-05, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -7.321541197599646e-05, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 50, | |
| "layers": [ | |
| "model.language_model.layers.25.self_attn.q_proj", | |
| "model.language_model.layers.25.self_attn.k_proj", | |
| "model.language_model.layers.25.self_attn.v_proj", | |
| "model.language_model.layers.25.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 1.7680786550039462e-05, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -0.00017909421585501906, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 51, | |
| "layers": [ | |
| "model.language_model.layers.25.mlp.gate_proj", | |
| "model.language_model.layers.25.mlp.up_proj", | |
| "model.language_model.layers.25.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 0.0002028619870543258, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": 0.0002154889516532421, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 52, | |
| "layers": [ | |
| "model.language_model.layers.26.self_attn.q_proj", | |
| "model.language_model.layers.26.self_attn.k_proj", | |
| "model.language_model.layers.26.self_attn.v_proj", | |
| "model.language_model.layers.26.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -2.6849750429408514e-05, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -0.00013140486553311903, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 53, | |
| "layers": [ | |
| "model.language_model.layers.26.mlp.gate_proj", | |
| "model.language_model.layers.26.mlp.up_proj", | |
| "model.language_model.layers.26.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -9.225751273334026e-05, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.00036976165138186134, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 54, | |
| "layers": [ | |
| "model.language_model.layers.27.self_attn.q_proj", | |
| "model.language_model.layers.27.self_attn.k_proj", | |
| "model.language_model.layers.27.self_attn.v_proj", | |
| "model.language_model.layers.27.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 0.00020883963443338316, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": 8.990662172436714e-05, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 55, | |
| "layers": [ | |
| "model.language_model.layers.27.mlp.gate_proj", | |
| "model.language_model.layers.27.mlp.up_proj", | |
| "model.language_model.layers.27.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 2.523777075111311e-05, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.00022528180852532387, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 56, | |
| "layers": [ | |
| "model.language_model.layers.28.self_attn.q_proj", | |
| "model.language_model.layers.28.self_attn.k_proj", | |
| "model.language_model.layers.28.self_attn.v_proj", | |
| "model.language_model.layers.28.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -4.28589060902651e-05, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": 0.00010976642370222334, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 57, | |
| "layers": [ | |
| "model.language_model.layers.28.mlp.gate_proj", | |
| "model.language_model.layers.28.mlp.up_proj", | |
| "model.language_model.layers.28.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.00026168590411546067, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.0003445466049015744, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 58, | |
| "layers": [ | |
| "model.language_model.layers.29.self_attn.q_proj", | |
| "model.language_model.layers.29.self_attn.k_proj", | |
| "model.language_model.layers.29.self_attn.v_proj", | |
| "model.language_model.layers.29.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 6.120707839726847e-05, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": 0.00010455059818922918, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 59, | |
| "layers": [ | |
| "model.language_model.layers.29.mlp.gate_proj", | |
| "model.language_model.layers.29.mlp.up_proj", | |
| "model.language_model.layers.29.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.000123786833137296, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.0003314546775072813, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 60, | |
| "layers": [ | |
| "model.language_model.layers.30.self_attn.q_proj", | |
| "model.language_model.layers.30.self_attn.k_proj", | |
| "model.language_model.layers.30.self_attn.v_proj", | |
| "model.language_model.layers.30.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 0.00029394258745013557, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": 0.00022767381742594406, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 61, | |
| "layers": [ | |
| "model.language_model.layers.30.mlp.gate_proj", | |
| "model.language_model.layers.30.mlp.up_proj", | |
| "model.language_model.layers.30.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.00012490730732681032, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.0001571818720549345, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 62, | |
| "layers": [ | |
| "model.language_model.layers.31.self_attn.q_proj", | |
| "model.language_model.layers.31.self_attn.k_proj", | |
| "model.language_model.layers.31.self_attn.v_proj", | |
| "model.language_model.layers.31.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.0004900929052382708, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -0.0005018283613026364, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 63, | |
| "layers": [ | |
| "model.language_model.layers.31.mlp.gate_proj", | |
| "model.language_model.layers.31.mlp.up_proj", | |
| "model.language_model.layers.31.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 0.00022143623791634481, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": 0.00010823202319443226, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 64, | |
| "layers": [ | |
| "model.language_model.layers.32.self_attn.q_proj", | |
| "model.language_model.layers.32.self_attn.k_proj", | |
| "model.language_model.layers.32.self_attn.v_proj", | |
| "model.language_model.layers.32.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.0003077854868024643, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -0.00022793915122748531, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 65, | |
| "layers": [ | |
| "model.language_model.layers.32.mlp.gate_proj", | |
| "model.language_model.layers.32.mlp.up_proj", | |
| "model.language_model.layers.32.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -1.8477952107798234e-05, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.00013991552405059893, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 66, | |
| "layers": [ | |
| "model.language_model.layers.33.self_attn.q_proj", | |
| "model.language_model.layers.33.self_attn.k_proj", | |
| "model.language_model.layers.33.self_attn.v_proj", | |
| "model.language_model.layers.33.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 0.0001139423344284074, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": 0.00010652639903127592, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 67, | |
| "layers": [ | |
| "model.language_model.layers.33.mlp.gate_proj", | |
| "model.language_model.layers.33.mlp.up_proj", | |
| "model.language_model.layers.33.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.00015837834216655966, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.00017344346269965172, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 68, | |
| "layers": [ | |
| "model.language_model.layers.34.self_attn.q_proj", | |
| "model.language_model.layers.34.self_attn.k_proj", | |
| "model.language_model.layers.34.self_attn.v_proj", | |
| "model.language_model.layers.34.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -2.0092679187677653e-05, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -4.768059588969309e-05, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 69, | |
| "layers": [ | |
| "model.language_model.layers.34.mlp.gate_proj", | |
| "model.language_model.layers.34.mlp.up_proj", | |
| "model.language_model.layers.34.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.00011453106999398388, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.00014291619881989792, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 70, | |
| "layers": [ | |
| "model.language_model.layers.35.self_attn.q_proj", | |
| "model.language_model.layers.35.self_attn.k_proj", | |
| "model.language_model.layers.35.self_attn.v_proj", | |
| "model.language_model.layers.35.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 0.00015730569139121853, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": 0.0002371510956436229, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 71, | |
| "layers": [ | |
| "model.language_model.layers.35.mlp.gate_proj", | |
| "model.language_model.layers.35.mlp.up_proj", | |
| "model.language_model.layers.35.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.00023716585710645277, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.0004655693657696358, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 72, | |
| "layers": [ | |
| "model.language_model.layers.36.self_attn.q_proj", | |
| "model.language_model.layers.36.self_attn.k_proj", | |
| "model.language_model.layers.36.self_attn.v_proj", | |
| "model.language_model.layers.36.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.00032587922178209383, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -0.0005042652599513697, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 73, | |
| "layers": [ | |
| "model.language_model.layers.36.mlp.gate_proj", | |
| "model.language_model.layers.36.mlp.up_proj", | |
| "model.language_model.layers.36.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.0006116618402302321, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.0006361586041748746, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 74, | |
| "layers": [ | |
| "model.language_model.layers.37.self_attn.q_proj", | |
| "model.language_model.layers.37.self_attn.k_proj", | |
| "model.language_model.layers.37.self_attn.v_proj", | |
| "model.language_model.layers.37.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 5.171378143131733e-05, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -1.6777683049445935e-05, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 75, | |
| "layers": [ | |
| "model.language_model.layers.37.mlp.gate_proj", | |
| "model.language_model.layers.37.mlp.up_proj", | |
| "model.language_model.layers.37.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.0006116549018770623, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.0006575850769877656, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 76, | |
| "layers": [ | |
| "model.language_model.layers.38.self_attn.q_proj", | |
| "model.language_model.layers.38.self_attn.k_proj", | |
| "model.language_model.layers.38.self_attn.v_proj", | |
| "model.language_model.layers.38.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.00017759450711310465, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -0.0003292498644441588, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 77, | |
| "layers": [ | |
| "model.language_model.layers.38.mlp.gate_proj", | |
| "model.language_model.layers.38.mlp.up_proj", | |
| "model.language_model.layers.38.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 9.779524989425581e-05, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": 0.00022586658596990272, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 78, | |
| "layers": [ | |
| "model.language_model.layers.39.self_attn.q_proj", | |
| "model.language_model.layers.39.self_attn.k_proj", | |
| "model.language_model.layers.39.self_attn.v_proj", | |
| "model.language_model.layers.39.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.00019017886370420456, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -0.00014174073003234144, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 79, | |
| "layers": [ | |
| "model.language_model.layers.39.mlp.gate_proj", | |
| "model.language_model.layers.39.mlp.up_proj", | |
| "model.language_model.layers.39.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 0.00011877082288264118, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.00013138423673808575, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 80, | |
| "layers": [ | |
| "model.language_model.layers.40.self_attn.q_proj", | |
| "model.language_model.layers.40.self_attn.k_proj", | |
| "model.language_model.layers.40.self_attn.v_proj", | |
| "model.language_model.layers.40.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 0.00014259032905100666, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": 0.0003622303716838138, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 81, | |
| "layers": [ | |
| "model.language_model.layers.40.mlp.gate_proj", | |
| "model.language_model.layers.40.mlp.up_proj", | |
| "model.language_model.layers.40.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.0004363835323601961, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.0004892456810921542, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 82, | |
| "layers": [ | |
| "model.language_model.layers.41.self_attn.q_proj", | |
| "model.language_model.layers.41.self_attn.k_proj", | |
| "model.language_model.layers.41.self_attn.v_proj", | |
| "model.language_model.layers.41.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.00037515051662923016, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -0.00036390214227141615, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 83, | |
| "layers": [ | |
| "model.language_model.layers.41.mlp.gate_proj", | |
| "model.language_model.layers.41.mlp.up_proj", | |
| "model.language_model.layers.41.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -2.6784790679829085e-05, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.0002820216584950852, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 84, | |
| "layers": [ | |
| "model.language_model.layers.42.self_attn.q_proj", | |
| "model.language_model.layers.42.self_attn.k_proj", | |
| "model.language_model.layers.42.self_attn.v_proj", | |
| "model.language_model.layers.42.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.0002433180809021107, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -0.00022505610249937136, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 85, | |
| "layers": [ | |
| "model.language_model.layers.42.mlp.gate_proj", | |
| "model.language_model.layers.42.mlp.up_proj", | |
| "model.language_model.layers.42.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.00030364627018572565, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.0002478116191923785, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 86, | |
| "layers": [ | |
| "model.language_model.layers.43.self_attn.q_proj", | |
| "model.language_model.layers.43.self_attn.k_proj", | |
| "model.language_model.layers.43.self_attn.v_proj", | |
| "model.language_model.layers.43.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 0.00013466081582008682, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": 7.684668526047878e-06, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 87, | |
| "layers": [ | |
| "model.language_model.layers.43.mlp.gate_proj", | |
| "model.language_model.layers.43.mlp.up_proj", | |
| "model.language_model.layers.43.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 2.2285990416981427e-05, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": 9.187171235658376e-06, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 88, | |
| "layers": [ | |
| "model.language_model.layers.44.self_attn.q_proj", | |
| "model.language_model.layers.44.self_attn.k_proj", | |
| "model.language_model.layers.44.self_attn.v_proj", | |
| "model.language_model.layers.44.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 0.0001239406876265836, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": 0.00019352706149219912, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 89, | |
| "layers": [ | |
| "model.language_model.layers.44.mlp.gate_proj", | |
| "model.language_model.layers.44.mlp.up_proj", | |
| "model.language_model.layers.44.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.00016605677083136872, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.00035673477686942734, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 90, | |
| "layers": [ | |
| "model.language_model.layers.45.self_attn.q_proj", | |
| "model.language_model.layers.45.self_attn.k_proj", | |
| "model.language_model.layers.45.self_attn.v_proj", | |
| "model.language_model.layers.45.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 0.00018179877661167465, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -9.876396507041418e-06, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 91, | |
| "layers": [ | |
| "model.language_model.layers.45.mlp.gate_proj", | |
| "model.language_model.layers.45.mlp.up_proj", | |
| "model.language_model.layers.45.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.0004525623749941643, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.00030217254534364857, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 92, | |
| "layers": [ | |
| "model.language_model.layers.46.self_attn.q_proj", | |
| "model.language_model.layers.46.self_attn.k_proj", | |
| "model.language_model.layers.46.self_attn.v_proj", | |
| "model.language_model.layers.46.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.00010313107632101137, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -1.639225520194687e-05, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 93, | |
| "layers": [ | |
| "model.language_model.layers.46.mlp.gate_proj", | |
| "model.language_model.layers.46.mlp.up_proj", | |
| "model.language_model.layers.46.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.00023827492259442806, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.0001679945271462202, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 94, | |
| "layers": [ | |
| "model.language_model.layers.47.self_attn.q_proj", | |
| "model.language_model.layers.47.self_attn.k_proj", | |
| "model.language_model.layers.47.self_attn.v_proj", | |
| "model.language_model.layers.47.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 0.00047768964432179373, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": 0.0004286430310457834, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 95, | |
| "layers": [ | |
| "model.language_model.layers.47.mlp.gate_proj", | |
| "model.language_model.layers.47.mlp.up_proj", | |
| "model.language_model.layers.47.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.0003748951479792817, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.00041852202266456917, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 96, | |
| "layers": [ | |
| "model.language_model.layers.48.self_attn.q_proj", | |
| "model.language_model.layers.48.self_attn.k_proj", | |
| "model.language_model.layers.48.self_attn.v_proj", | |
| "model.language_model.layers.48.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.00015185866504907608, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": 2.9604835435736998e-05, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 97, | |
| "layers": [ | |
| "model.language_model.layers.48.mlp.gate_proj", | |
| "model.language_model.layers.48.mlp.up_proj", | |
| "model.language_model.layers.48.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.000497997272759676, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.0005106110125780161, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 98, | |
| "layers": [ | |
| "model.language_model.layers.49.self_attn.q_proj", | |
| "model.language_model.layers.49.self_attn.k_proj", | |
| "model.language_model.layers.49.self_attn.v_proj", | |
| "model.language_model.layers.49.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.00013194279745221138, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -0.00026086703874173, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 99, | |
| "layers": [ | |
| "model.language_model.layers.49.mlp.gate_proj", | |
| "model.language_model.layers.49.mlp.up_proj", | |
| "model.language_model.layers.49.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 0.00028887651860712293, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": 8.507091552018009e-05, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 100, | |
| "layers": [ | |
| "model.language_model.layers.50.self_attn.q_proj", | |
| "model.language_model.layers.50.self_attn.k_proj", | |
| "model.language_model.layers.50.self_attn.v_proj", | |
| "model.language_model.layers.50.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 0.00041282796300945446, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": 0.00034878966398535494, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 101, | |
| "layers": [ | |
| "model.language_model.layers.50.mlp.gate_proj", | |
| "model.language_model.layers.50.mlp.up_proj", | |
| "model.language_model.layers.50.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.0003386356867849938, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.0005072795320302248, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 102, | |
| "layers": [ | |
| "model.language_model.layers.51.self_attn.q_proj", | |
| "model.language_model.layers.51.self_attn.k_proj", | |
| "model.language_model.layers.51.self_attn.v_proj", | |
| "model.language_model.layers.51.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 8.664890192447428e-05, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": 0.000201887823641278, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 103, | |
| "layers": [ | |
| "model.language_model.layers.51.mlp.gate_proj", | |
| "model.language_model.layers.51.mlp.up_proj", | |
| "model.language_model.layers.51.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.0009231174364686123, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.0008698628749698456, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 104, | |
| "layers": [ | |
| "model.language_model.layers.52.self_attn.q_proj", | |
| "model.language_model.layers.52.self_attn.k_proj", | |
| "model.language_model.layers.52.self_attn.v_proj", | |
| "model.language_model.layers.52.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 0.0006682481616735458, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": 0.00046845399774608776, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 105, | |
| "layers": [ | |
| "model.language_model.layers.52.mlp.gate_proj", | |
| "model.language_model.layers.52.mlp.up_proj", | |
| "model.language_model.layers.52.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.0005143266171216965, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.00028531067073345184, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 106, | |
| "layers": [ | |
| "model.language_model.layers.53.self_attn.q_proj", | |
| "model.language_model.layers.53.self_attn.k_proj", | |
| "model.language_model.layers.53.self_attn.v_proj", | |
| "model.language_model.layers.53.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.0011058779433369692, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -0.0008262845687568299, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 107, | |
| "layers": [ | |
| "model.language_model.layers.53.mlp.gate_proj", | |
| "model.language_model.layers.53.mlp.up_proj", | |
| "model.language_model.layers.53.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.0005857495125383139, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.0007907640654593873, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 108, | |
| "layers": [ | |
| "model.language_model.layers.54.self_attn.q_proj", | |
| "model.language_model.layers.54.self_attn.k_proj", | |
| "model.language_model.layers.54.self_attn.v_proj", | |
| "model.language_model.layers.54.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.0003247374668717551, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -0.00047106938436627943, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 109, | |
| "layers": [ | |
| "model.language_model.layers.54.mlp.gate_proj", | |
| "model.language_model.layers.54.mlp.up_proj", | |
| "model.language_model.layers.54.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.0006814375985413901, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.0006852156948298216, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 110, | |
| "layers": [ | |
| "model.language_model.layers.55.self_attn.q_proj", | |
| "model.language_model.layers.55.self_attn.k_proj", | |
| "model.language_model.layers.55.self_attn.v_proj", | |
| "model.language_model.layers.55.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.0008712090086192004, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -0.000794619973748939, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 111, | |
| "layers": [ | |
| "model.language_model.layers.55.mlp.gate_proj", | |
| "model.language_model.layers.55.mlp.up_proj", | |
| "model.language_model.layers.55.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.0004104899242520499, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.0003673459868878126, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 112, | |
| "layers": [ | |
| "model.language_model.layers.56.self_attn.q_proj", | |
| "model.language_model.layers.56.self_attn.k_proj", | |
| "model.language_model.layers.56.self_attn.v_proj", | |
| "model.language_model.layers.56.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -8.137007243932959e-05, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -0.0005230564158409945, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 113, | |
| "layers": [ | |
| "model.language_model.layers.56.mlp.gate_proj", | |
| "model.language_model.layers.56.mlp.up_proj", | |
| "model.language_model.layers.56.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.0007926002144813538, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.0004942396190017462, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 114, | |
| "layers": [ | |
| "model.language_model.layers.57.self_attn.q_proj", | |
| "model.language_model.layers.57.self_attn.k_proj", | |
| "model.language_model.layers.57.self_attn.v_proj", | |
| "model.language_model.layers.57.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -4.884987138212282e-05, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -0.00027763238176703453, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 115, | |
| "layers": [ | |
| "model.language_model.layers.57.mlp.gate_proj", | |
| "model.language_model.layers.57.mlp.up_proj", | |
| "model.language_model.layers.57.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.0007438508328050375, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.0007115922868251856, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 116, | |
| "layers": [ | |
| "model.language_model.layers.58.self_attn.q_proj", | |
| "model.language_model.layers.58.self_attn.k_proj", | |
| "model.language_model.layers.58.self_attn.v_proj", | |
| "model.language_model.layers.58.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.00016308482736349106, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -0.0003048637881875038, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 117, | |
| "layers": [ | |
| "model.language_model.layers.58.mlp.gate_proj", | |
| "model.language_model.layers.58.mlp.up_proj", | |
| "model.language_model.layers.58.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.0008469442371279168, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.000874680187553184, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 118, | |
| "layers": [ | |
| "model.language_model.layers.59.self_attn.q_proj", | |
| "model.language_model.layers.59.self_attn.k_proj", | |
| "model.language_model.layers.59.self_attn.v_proj", | |
| "model.language_model.layers.59.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 2.2697122767562083e-05, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -0.0004360306076705567, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 119, | |
| "layers": [ | |
| "model.language_model.layers.59.mlp.gate_proj", | |
| "model.language_model.layers.59.mlp.up_proj", | |
| "model.language_model.layers.59.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.0005720941349864062, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.0006580702494830004, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 120, | |
| "layers": [ | |
| "model.language_model.layers.60.self_attn.q_proj", | |
| "model.language_model.layers.60.self_attn.k_proj", | |
| "model.language_model.layers.60.self_attn.v_proj", | |
| "model.language_model.layers.60.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.001185041572898643, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -0.0012297863606363646, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 121, | |
| "layers": [ | |
| "model.language_model.layers.60.mlp.gate_proj", | |
| "model.language_model.layers.60.mlp.up_proj", | |
| "model.language_model.layers.60.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.00043576946482062895, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.00037752632051707424, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 122, | |
| "layers": [ | |
| "model.language_model.layers.61.self_attn.q_proj", | |
| "model.language_model.layers.61.self_attn.k_proj", | |
| "model.language_model.layers.61.self_attn.v_proj", | |
| "model.language_model.layers.61.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 0.00023652003146706901, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -0.00035312902182341177, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 123, | |
| "layers": [ | |
| "model.language_model.layers.61.mlp.gate_proj", | |
| "model.language_model.layers.61.mlp.up_proj", | |
| "model.language_model.layers.61.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.00031162113882601816, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.0005344925448298454, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 124, | |
| "layers": [ | |
| "model.language_model.layers.62.self_attn.q_proj", | |
| "model.language_model.layers.62.self_attn.k_proj", | |
| "model.language_model.layers.62.self_attn.v_proj", | |
| "model.language_model.layers.62.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.0011726192198693863, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": -0.0011081209406256787, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 125, | |
| "layers": [ | |
| "model.language_model.layers.62.mlp.gate_proj", | |
| "model.language_model.layers.62.mlp.up_proj", | |
| "model.language_model.layers.62.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.0033292342443019263, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.003356328653171675, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 126, | |
| "layers": [ | |
| "model.language_model.layers.63.self_attn.q_proj", | |
| "model.language_model.layers.63.self_attn.k_proj", | |
| "model.language_model.layers.63.self_attn.v_proj", | |
| "model.language_model.layers.63.self_attn.o_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": 0.00011754971928892854, | |
| "dbits": 94371840 | |
| }, | |
| { | |
| "dkld": 0.00028725313022731624, | |
| "dbits": 188743680 | |
| } | |
| ] | |
| }, | |
| { | |
| "idx": 127, | |
| "layers": [ | |
| "model.language_model.layers.63.mlp.gate_proj", | |
| "model.language_model.layers.63.mlp.up_proj", | |
| "model.language_model.layers.63.mlp.down_proj" | |
| ], | |
| "candidates": [ | |
| { | |
| "dkld": -0.0020378781482577324, | |
| "dbits": 393216000 | |
| }, | |
| { | |
| "dkld": -0.002213719766587019, | |
| "dbits": 786432000 | |
| } | |
| ] | |
| } | |
| ], | |
| "base_kld": 0.19816926405765117, | |
| "arch_string": "Qwen3VLForConditionalGeneration" | |
| } |