diff --git "a/ndarray-cache.json" "b/ndarray-cache.json" new file mode 100644--- /dev/null +++ "b/ndarray-cache.json" @@ -0,0 +1,5153 @@ +{ + "metadata": { + "ParamSize": 339, + "ParamBytes": 29540067328.0, + "BitsPerParam": 16.0 + }, + "records": [ + { + "dataPath": "params_shard_0.bin", + "format": "raw-shard", + "nbytes": 1557135360, + "records": [ + { + "name": "lm_head.weight", + "shape": [ + 152064, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1557135360, + "byteOffset": 0 + } + ], + "md5sum": "03ee1558dda4b10d21ed972d1a6be25a" + }, + { + "dataPath": "params_shard_1.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.42.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "d2bb00732b3fec0c9e8f19e546851050" + }, + { + "dataPath": "params_shard_2.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.42.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "fd20a9cce68e0943b03a935c6e7579ae" + }, + { + "dataPath": "params_shard_3.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.43.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "86e06584e83a7cee459e3e8b6184c2e7" + }, + { + "dataPath": "params_shard_4.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.43.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "0c8110f2ce4cccb8ad67b6bf5e171b8e" + }, + { + "dataPath": "params_shard_5.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.43.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "1226f7c733ed7598dbaadc81d1943f90" + }, + { + "dataPath": "params_shard_6.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.43.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "f4ead29fdf9efc6441a5dd3ec4912514" + }, + { + "dataPath": "params_shard_7.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.44.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "35ff5b25e56cf2d7f8855865bcba436c" + }, + { + "dataPath": "params_shard_8.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.44.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "ea5eedc0d27f2de4f3e545a945f3954b" + }, + { + "dataPath": "params_shard_9.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.44.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "5371e78b87bc113ea3e69e5b2df2f693" + }, + { + "dataPath": "params_shard_10.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.44.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "78be88e73a7858693e5ab675f51a0d81" + }, + { + "dataPath": "params_shard_11.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.45.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "410587c1ca0420de1828c87349b49399" + }, + { + "dataPath": "params_shard_12.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.45.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "8440141b1574e44535c1689aecddcdec" + }, + { + "dataPath": "params_shard_13.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.45.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "a80115572a8c0284218dce221359f949" + }, + { + "dataPath": "params_shard_14.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.45.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "9f08fe4f08802dfc5151dc8cf232a5db" + }, + { + "dataPath": "params_shard_15.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.46.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "9e8bef3b6475c474071a70049da2066b" + }, + { + "dataPath": "params_shard_16.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.46.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "902dd941794c68b77a42447eadbd2876" + }, + { + "dataPath": "params_shard_17.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.46.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "2b58c75094cd32d4c8bd5797689bb0e8" + }, + { + "dataPath": "params_shard_18.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.46.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "d4e9152127dca95dd67a6548ffbfba01" + }, + { + "dataPath": "params_shard_19.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.47.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "01e0bccc7c1b67c0794f95ff6f53a1e5" + }, + { + "dataPath": "params_shard_20.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.47.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "ffaae5c0be489fb8b5440a2e31102870" + }, + { + "dataPath": "params_shard_21.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.47.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "3cfbc42e11f465ae6f9daa0920180968" + }, + { + "dataPath": "params_shard_22.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.47.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "cc0c63b366e3d3099267c9b8c0ec98f0" + }, + { + "dataPath": "params_shard_23.bin", + "format": "raw-shard", + "nbytes": 1557135360, + "records": [ + { + "name": "model.embed_tokens.weight", + "shape": [ + 152064, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1557135360, + "byteOffset": 0 + } + ], + "md5sum": "45201bbab2e964818ed81c4f182e5634" + }, + { + "dataPath": "params_shard_24.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.0.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "74d95a6339a5543c6946148fea37b0c0" + }, + { + "dataPath": "params_shard_25.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.0.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "118fef34cbd06f9cde7d452d62337a5c" + }, + { + "dataPath": "params_shard_26.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.0.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "a951b92907aa18564edb3ccc7766842e" + }, + { + "dataPath": "params_shard_27.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.0.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "948f82f27a9393a0ec3e803182316cef" + }, + { + "dataPath": "params_shard_28.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.1.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "abdfd35c58a03efaee004757eed178ae" + }, + { + "dataPath": "params_shard_29.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.1.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "d761b231472c5e47bf90e5e33fbea932" + }, + { + "dataPath": "params_shard_30.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.1.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "5519d1d73b5ab1c0e68f2d490f6eabc2" + }, + { + "dataPath": "params_shard_31.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.1.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "285b98bb6f959511d0888e5046c329f1" + }, + { + "dataPath": "params_shard_32.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.2.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "7e5d768de9b869f72866b32e4714fb2f" + }, + { + "dataPath": "params_shard_33.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.2.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "9adb656d10b90595e58cc6a240fadd44" + }, + { + "dataPath": "params_shard_34.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.2.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "9dc0fbeac814fdf0d1fc94debe7d6859" + }, + { + "dataPath": "params_shard_35.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.2.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "4d010d82d3104bef6d361d1b21be399a" + }, + { + "dataPath": "params_shard_36.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.3.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "b44065c1e3c4de007fc0c8c2b20629fc" + }, + { + "dataPath": "params_shard_37.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.3.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "bbc3b6bfc16857427f384885f4a25537" + }, + { + "dataPath": "params_shard_38.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.3.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "a14fdcdb2c98170ff1d2154ddd3b5cb1" + }, + { + "dataPath": "params_shard_39.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.3.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "a6505c06596d4746a75aa76f4d2269dd" + }, + { + "dataPath": "params_shard_40.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.4.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "5ad2619299d29d1de633e060ce04aa16" + }, + { + "dataPath": "params_shard_41.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.4.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "eb10ab7ac625fadae30ad15aa0b9222b" + }, + { + "dataPath": "params_shard_42.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.4.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "f8179d2b0a8b8ab51ec2409c2ca31f39" + }, + { + "dataPath": "params_shard_43.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.4.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "e22d24b3006eb8ea02a4aeb9830fa152" + }, + { + "dataPath": "params_shard_44.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.5.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "8a17c74d5fe3ca2026719b107da68282" + }, + { + "dataPath": "params_shard_45.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.5.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "1496f30a00e02ce3f0e0d1002d1b04a6" + }, + { + "dataPath": "params_shard_46.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.5.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "4be7b62c47c974194a1418c0138f86cb" + }, + { + "dataPath": "params_shard_47.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.5.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "7eda4e23d6b31b170d4b1e8c1c91e313" + }, + { + "dataPath": "params_shard_48.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.6.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "573f7451517fd983eab7e78c57e2f215" + }, + { + "dataPath": "params_shard_49.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.6.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "c4ce2d603896c60fa88d6b53999d37cf" + }, + { + "dataPath": "params_shard_50.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.10.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "4a406f235a726d212a128fe173ce1a47" + }, + { + "dataPath": "params_shard_51.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.10.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "04dbb7078b29fa2b6382ff5e01d2babd" + }, + { + "dataPath": "params_shard_52.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.10.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "0eeae8d170db0e45121339e2fd229441" + }, + { + "dataPath": "params_shard_53.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.10.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "2fadb99fd02c143dcd4c9fc01efa3922" + }, + { + "dataPath": "params_shard_54.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.11.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "d28378db324ffc067cb5cbd535b81f3f" + }, + { + "dataPath": "params_shard_55.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.11.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "f6fe94cee50d4789572bf65d7d71c7ff" + }, + { + "dataPath": "params_shard_56.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.11.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "b2f8e2c91df9a0af849a8f23169b1977" + }, + { + "dataPath": "params_shard_57.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.11.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "bf71dfc10e19cc9cecdeb7511d413e32" + }, + { + "dataPath": "params_shard_58.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.12.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "07833984b3c0488be4aa1544d47797f6" + }, + { + "dataPath": "params_shard_59.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.12.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "164e83c68a1091eecaf24845fcecdf37" + }, + { + "dataPath": "params_shard_60.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.12.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "e53f492c3b4d75b3142fd23f1630db4f" + }, + { + "dataPath": "params_shard_61.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.12.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "d7ced719a8ccfbfcc174521cafcb2d4b" + }, + { + "dataPath": "params_shard_62.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.13.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "e8b53b7ead75ee98c859cad23c258c88" + }, + { + "dataPath": "params_shard_63.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.13.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "0ea211f89e3ffd16e352b6a0f37a3d4a" + }, + { + "dataPath": "params_shard_64.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.13.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "bbeaf3fd51819f4454289b0a4788bdcd" + }, + { + "dataPath": "params_shard_65.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.13.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "d4967b81564cf14612d974748451af7c" + }, + { + "dataPath": "params_shard_66.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.14.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "55c28c2c59acf8b578cce5f30a42f6f8" + }, + { + "dataPath": "params_shard_67.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.14.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "bfa2cf50528643d8bcf108d1f8171597" + }, + { + "dataPath": "params_shard_68.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.14.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "83fc908e0ef19221077f0be21d64b868" + }, + { + "dataPath": "params_shard_69.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.14.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "3c96dacf68fd56f612a8e8351d07fcd6" + }, + { + "dataPath": "params_shard_70.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.15.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "f4750e36bb78422bda9960dc84251938" + }, + { + "dataPath": "params_shard_71.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.15.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "ead2fa6d2768e19aa4b466e9b353d4c2" + }, + { + "dataPath": "params_shard_72.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.6.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "df7bebc0e58dd2036838539435487c6c" + }, + { + "dataPath": "params_shard_73.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.6.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "47ab9069d40983ca08cb2ced5e490a0f" + }, + { + "dataPath": "params_shard_74.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.7.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "ea1500f6f7b07cbc8c87e2e45e91313c" + }, + { + "dataPath": "params_shard_75.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.7.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "828f21d380d4ce59ee2eca2a8699b891" + }, + { + "dataPath": "params_shard_76.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.7.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "a6ac9fcb1a17276d2fd8ee10dfa50941" + }, + { + "dataPath": "params_shard_77.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.7.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "06f94991adc3719888f126f915d939f4" + }, + { + "dataPath": "params_shard_78.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.8.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "9085c0dd3f995a7b6433b6e8275b696e" + }, + { + "dataPath": "params_shard_79.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.8.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "fc83729445b433e7148f916be8a754be" + }, + { + "dataPath": "params_shard_80.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.8.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "44084fbb306695901cbd8a45044289bb" + }, + { + "dataPath": "params_shard_81.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.8.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "37a3016f0d5793a26d20575ac9510d66" + }, + { + "dataPath": "params_shard_82.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.9.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "1287548edb803dbdbca0f85c2c52efc5" + }, + { + "dataPath": "params_shard_83.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.9.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "4b0779610bc1a7a279d888b663dd124f" + }, + { + "dataPath": "params_shard_84.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.9.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "184c6a9d906c96ab36446d361f53a200" + }, + { + "dataPath": "params_shard_85.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.9.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "acee1066855d2cb513c5d5bb739aff36" + }, + { + "dataPath": "params_shard_86.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.15.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "424af53d7c8cdca6aadf3d414c1404bb" + }, + { + "dataPath": "params_shard_87.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.15.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "9390c3cecea5730e27b138ceeffde18e" + }, + { + "dataPath": "params_shard_88.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.16.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "d585169187806efea1ca340edf0955da" + }, + { + "dataPath": "params_shard_89.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.16.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "13dfc412ca0c0f862f262212192746cc" + }, + { + "dataPath": "params_shard_90.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.16.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "5cd727e30906d4f9a7d781a909a072e0" + }, + { + "dataPath": "params_shard_91.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.16.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "adf3a3568a0d85aae320684588f01973" + }, + { + "dataPath": "params_shard_92.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.17.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "3516f156f945203fde2ba2ffdbe5aa99" + }, + { + "dataPath": "params_shard_93.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.17.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "ac9fc3e61c2318f1f9fdf7a01c5395cb" + }, + { + "dataPath": "params_shard_94.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.17.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "4fad53a47907dcfbe4f85e82b028930d" + }, + { + "dataPath": "params_shard_95.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.17.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "96dd34d2913b075854296e0f9b5eae2b" + }, + { + "dataPath": "params_shard_96.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.18.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "fac0321cc64675d8d8cb03991d95934b" + }, + { + "dataPath": "params_shard_97.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.18.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "f4bde3da86224e8a7731da3162162a0b" + }, + { + "dataPath": "params_shard_98.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.18.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "9b46feee6565aa3978d5f57cd1d4cd20" + }, + { + "dataPath": "params_shard_99.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.18.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "9954fc6611e689527f710e3f90bda3e9" + }, + { + "dataPath": "params_shard_100.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.19.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "c74a587f9bc11b9bab1692989e040a61" + }, + { + "dataPath": "params_shard_101.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.19.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "f6fd8b7a7360cb00c74c9a8e1f9680e3" + }, + { + "dataPath": "params_shard_102.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.19.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "81a431e7881712c934bc29b57cfa0e86" + }, + { + "dataPath": "params_shard_103.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.19.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "0f395dfcc633e99cdcbffd1a0280d5d3" + }, + { + "dataPath": "params_shard_104.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.20.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "a82becf3008fd74ec9bdf97da7ee11dc" + }, + { + "dataPath": "params_shard_105.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.20.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "423c86548fd0acdf8dbd824e0aecc3a0" + }, + { + "dataPath": "params_shard_106.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.20.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "7aa5d12139205af9eee4e1d48e9e3337" + }, + { + "dataPath": "params_shard_107.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.20.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "5f5156c78f55c400edc6612f09a2740b" + }, + { + "dataPath": "params_shard_108.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.21.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "10665a55c5ab6cb03c6c159acc3b9ff4" + }, + { + "dataPath": "params_shard_109.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.21.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "5b83babecbf0defa6b677504094fbc3f" + }, + { + "dataPath": "params_shard_110.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.21.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "23232db355b8e02866450a8a6e450308" + }, + { + "dataPath": "params_shard_111.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.21.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "edb8980b3be6bffaf489ce6d8b4fbb79" + }, + { + "dataPath": "params_shard_112.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.22.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "247f1dd7d8f398c85e0cb0b66f2fba85" + }, + { + "dataPath": "params_shard_113.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.22.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "2c338b94a39917a56a6256974a9ec35b" + }, + { + "dataPath": "params_shard_114.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.22.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "9b4b26e4d0dae6a28c213ccd2456818b" + }, + { + "dataPath": "params_shard_115.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.22.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "ea7b1c9b1a1da3f8fc539b302d0637f8" + }, + { + "dataPath": "params_shard_116.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.23.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "bcc11b18b6eecae7cb4793d717705344" + }, + { + "dataPath": "params_shard_117.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.23.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "d5acdc0810dec03a3309d36783d8e42a" + }, + { + "dataPath": "params_shard_118.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.23.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "da49524f4b2e44ecf4a631a88fe4abdc" + }, + { + "dataPath": "params_shard_119.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.23.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "1daccbc0fcb5dcc121f960cda1fc0c31" + }, + { + "dataPath": "params_shard_120.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.24.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "f3e1b50efd741d595e44c698913a7f6c" + }, + { + "dataPath": "params_shard_121.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.24.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "a4666b47d43633401622194668c62d34" + }, + { + "dataPath": "params_shard_122.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.24.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "6f398d5250cb7e1b760bb1c06ca18f72" + }, + { + "dataPath": "params_shard_123.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.24.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "3f2b7e9baed16058381b3dec61ae3655" + }, + { + "dataPath": "params_shard_124.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.25.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "edadf50244e46393a37b1a58062b29c0" + }, + { + "dataPath": "params_shard_125.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.25.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "2a4335886d90c46106d96aee8448fafc" + }, + { + "dataPath": "params_shard_126.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.25.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "e1220f9fa2737711ec3e2ba565b31b82" + }, + { + "dataPath": "params_shard_127.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.25.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "13904bf85dad4fc274af95aa98ddede0" + }, + { + "dataPath": "params_shard_128.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.26.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "cbbd953bbdeb354edd47d9a0cca47356" + }, + { + "dataPath": "params_shard_129.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.26.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "a538e8f5feba91bcb51c0f6018d02b4c" + }, + { + "dataPath": "params_shard_130.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.26.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "4d95b8eeb71873c7ac325434c41728e4" + }, + { + "dataPath": "params_shard_131.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.26.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "b53656e214e6b8b82d70406c8b995368" + }, + { + "dataPath": "params_shard_132.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.27.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "ec0c082869d892f74f767fe11d2d9709" + }, + { + "dataPath": "params_shard_133.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.27.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "7614b0a26b4a4fd4af60d2c68d9583b4" + }, + { + "dataPath": "params_shard_134.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.27.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "bc1e1f497e24ccdf93999a79475f1c13" + }, + { + "dataPath": "params_shard_135.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.27.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "351c50e6b96cd16b4420017a106b21e9" + }, + { + "dataPath": "params_shard_136.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.28.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "9c3af396ee5754ad518860b7a9675bde" + }, + { + "dataPath": "params_shard_137.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.28.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "8faa246eecd44e55ce8e60f7bf47cda7" + }, + { + "dataPath": "params_shard_138.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.28.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "6f0e0c81fe25b0b255dd0c26b3b9037f" + }, + { + "dataPath": "params_shard_139.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.28.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "816852916926c48549c5c3447d25ff71" + }, + { + "dataPath": "params_shard_140.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.29.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "6376133768b0480d791c7d75037461c3" + }, + { + "dataPath": "params_shard_141.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.29.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "7e89d10dd75e4c93bd242a32ecba7fd0" + }, + { + "dataPath": "params_shard_142.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.29.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "3c44d932956d1ae47f1e0b519dfe7dce" + }, + { + "dataPath": "params_shard_143.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.29.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "217ecaa1acc4852d24cc0c7481a4d435" + }, + { + "dataPath": "params_shard_144.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.30.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "a7cefdbfac9e7a2524fb1ac3e91f5e94" + }, + { + "dataPath": "params_shard_145.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.30.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "e0c497be8471488830c46308e255d442" + }, + { + "dataPath": "params_shard_146.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.30.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "ce895c3cce1f77a9817945319a2ef828" + }, + { + "dataPath": "params_shard_147.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.30.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "af49c9fe68411595d7fced261e7c8a25" + }, + { + "dataPath": "params_shard_148.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.31.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "80d2ae482b9f493bc446476529a0f559" + }, + { + "dataPath": "params_shard_149.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.31.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "1e10d847bb82e08af6e01fad3ce54ede" + }, + { + "dataPath": "params_shard_150.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.31.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "7195e36fd86b559c91c43df01b063ae3" + }, + { + "dataPath": "params_shard_151.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.31.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "dcfbb385915cf2c00c68f8ecf86b312c" + }, + { + "dataPath": "params_shard_152.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.32.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "00e6f89fbf4f2ed4f3513fa80a789a50" + }, + { + "dataPath": "params_shard_153.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.32.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "19704b5b8fccb487c8ccdcd9900b3e26" + }, + { + "dataPath": "params_shard_154.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.32.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "28ae557dbcb7064502837084de8e083d" + }, + { + "dataPath": "params_shard_155.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.32.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "76d28672bde449169283d85f74428691" + }, + { + "dataPath": "params_shard_156.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.33.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "8dfee996c7779f3b0ad4f94899658ec7" + }, + { + "dataPath": "params_shard_157.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.33.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "cbaad508e9a0fd2595face8775739e09" + }, + { + "dataPath": "params_shard_158.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.33.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "ececffcdc006506317e8cd17a4262813" + }, + { + "dataPath": "params_shard_159.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.33.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "80b7ab0be10dd612605a1154efa1c706" + }, + { + "dataPath": "params_shard_160.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.34.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "b8c8eed37fc54a420a1933ce8270be53" + }, + { + "dataPath": "params_shard_161.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.34.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "d28c08de7c7ca66349dcb79e4f064973" + }, + { + "dataPath": "params_shard_162.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.34.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "fb3915968a4fb58632423d777381ce0c" + }, + { + "dataPath": "params_shard_163.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.34.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "9e2242fd7cf527a0d64626d9e4825085" + }, + { + "dataPath": "params_shard_164.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.35.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "d2193f6f324d122d68d851ef68dfe2ac" + }, + { + "dataPath": "params_shard_165.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.35.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "47e7b05bbb7a62212ea0099ebdf915c5" + }, + { + "dataPath": "params_shard_166.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.35.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "4f644dff58c4a84839e128e7c454e785" + }, + { + "dataPath": "params_shard_167.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.35.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "65f96d88322d98fcb7f889f185811ecf" + }, + { + "dataPath": "params_shard_168.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.36.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "4c1b35f2b09e8a0e407a894a968a2ec6" + }, + { + "dataPath": "params_shard_169.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.36.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "e19a3d031c9285069019425f3532f776" + }, + { + "dataPath": "params_shard_170.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.36.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "bbfc20500de7a91f90d250e119947ade" + }, + { + "dataPath": "params_shard_171.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.36.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "a759c2ee089ce746371d9d9a659661d2" + }, + { + "dataPath": "params_shard_172.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.37.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "35795fc75c7599b05b07ca1a4dd8cb57" + }, + { + "dataPath": "params_shard_173.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.37.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "1847cd53555081379c5b8f690bf2c7f4" + }, + { + "dataPath": "params_shard_174.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.37.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "dec5174100f8cf57f4744119df1c172d" + }, + { + "dataPath": "params_shard_175.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.37.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "fd406c5c067d610657304a86db5dea5d" + }, + { + "dataPath": "params_shard_176.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.38.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "6317e453f32bf646e747ec05f09a823d" + }, + { + "dataPath": "params_shard_177.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.38.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "f333b955233d9e32442014bcc2a23b76" + }, + { + "dataPath": "params_shard_178.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.38.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "288a2651f3c15dc1e5eb5920a649340f" + }, + { + "dataPath": "params_shard_179.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.38.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "e52ae06d6c1bb726a6454dca824cf264" + }, + { + "dataPath": "params_shard_180.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.39.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "ed98c6973a731fda76c61ca5a2119d34" + }, + { + "dataPath": "params_shard_181.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.39.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "b2029a5478c872e4cfe216cd80703d04" + }, + { + "dataPath": "params_shard_182.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.39.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "cb785b9bb520d814516e55f41a582ce7" + }, + { + "dataPath": "params_shard_183.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.39.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "e86933e46e3accbde05b3ce96ec11bc9" + }, + { + "dataPath": "params_shard_184.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.40.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "d26842c5a69ec1986e6d52f1110f75a0" + }, + { + "dataPath": "params_shard_185.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.40.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "56b944da9af02b801f91ac9ed86dde8e" + }, + { + "dataPath": "params_shard_186.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.40.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "4ce26679b752e00db0acf94254df469e" + }, + { + "dataPath": "params_shard_187.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.40.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "47723efd95ef0e068c7c9e387c93350d" + }, + { + "dataPath": "params_shard_188.bin", + "format": "raw-shard", + "nbytes": 141557760, + "records": [ + { + "name": "model.layers.41.mlp.down_proj.weight", + "shape": [ + 5120, + 13824 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 141557760, + "byteOffset": 0 + } + ], + "md5sum": "5f240e0a728501d53aa0a7554cc334aa" + }, + { + "dataPath": "params_shard_189.bin", + "format": "raw-shard", + "nbytes": 283115520, + "records": [ + { + "name": "model.layers.41.mlp.gate_up_proj.weight", + "shape": [ + 27648, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 283115520, + "byteOffset": 0 + } + ], + "md5sum": "bbe958811c7f97095cda0f2663361bf9" + }, + { + "dataPath": "params_shard_190.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.41.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "a20b1f14bd04c2e9b6b2ded665b04e34" + }, + { + "dataPath": "params_shard_191.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.41.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "0dc45554a44c8e50b9b5f42599ac9b11" + }, + { + "dataPath": "params_shard_192.bin", + "format": "raw-shard", + "nbytes": 73400320, + "records": [ + { + "name": "model.layers.42.self_attn.c_attn.weight", + "shape": [ + 7168, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 73400320, + "byteOffset": 0 + } + ], + "md5sum": "91666d4aa1f393b3a86fb206ed6fc995" + }, + { + "dataPath": "params_shard_193.bin", + "format": "raw-shard", + "nbytes": 52428800, + "records": [ + { + "name": "model.layers.42.self_attn.o_proj.weight", + "shape": [ + 5120, + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 52428800, + "byteOffset": 0 + } + ], + "md5sum": "8312314b47fce65cbceca9eb30e37592" + }, + { + "dataPath": "params_shard_194.bin", + "format": "raw-shard", + "nbytes": 1681408, + "records": [ + { + "name": "model.layers.42.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 0 + }, + { + "name": "model.layers.42.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 10240 + }, + { + "name": "model.layers.43.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 20480 + }, + { + "name": "model.layers.43.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 30720 + }, + { + "name": "model.layers.43.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 40960 + }, + { + "name": "model.layers.44.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 55296 + }, + { + "name": "model.layers.44.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 65536 + }, + { + "name": "model.layers.44.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 75776 + }, + { + "name": "model.layers.45.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 90112 + }, + { + "name": "model.layers.45.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 100352 + }, + { + "name": "model.layers.45.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 110592 + }, + { + "name": "model.layers.46.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 124928 + }, + { + "name": "model.layers.46.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 135168 + }, + { + "name": "model.layers.46.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 145408 + }, + { + "name": "model.layers.47.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 159744 + }, + { + "name": "model.layers.47.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 169984 + }, + { + "name": "model.layers.47.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 180224 + }, + { + "name": "model.norm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 194560 + }, + { + "name": "model.layers.0.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 204800 + }, + { + "name": "model.layers.0.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 215040 + }, + { + "name": "model.layers.0.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 225280 + }, + { + "name": "model.layers.1.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 239616 + }, + { + "name": "model.layers.1.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 249856 + }, + { + "name": "model.layers.1.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 260096 + }, + { + "name": "model.layers.2.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 274432 + }, + { + "name": "model.layers.2.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 284672 + }, + { + "name": "model.layers.2.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 294912 + }, + { + "name": "model.layers.3.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 309248 + }, + { + "name": "model.layers.3.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 319488 + }, + { + "name": "model.layers.3.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 329728 + }, + { + "name": "model.layers.4.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 344064 + }, + { + "name": "model.layers.4.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 354304 + }, + { + "name": "model.layers.4.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 364544 + }, + { + "name": "model.layers.5.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 378880 + }, + { + "name": "model.layers.5.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 389120 + }, + { + "name": "model.layers.5.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 399360 + }, + { + "name": "model.layers.6.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 413696 + }, + { + "name": "model.layers.10.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 428032 + }, + { + "name": "model.layers.10.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 438272 + }, + { + "name": "model.layers.10.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 448512 + }, + { + "name": "model.layers.11.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 462848 + }, + { + "name": "model.layers.11.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 473088 + }, + { + "name": "model.layers.11.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 483328 + }, + { + "name": "model.layers.12.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 497664 + }, + { + "name": "model.layers.12.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 507904 + }, + { + "name": "model.layers.12.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 518144 + }, + { + "name": "model.layers.13.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 532480 + }, + { + "name": "model.layers.13.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 542720 + }, + { + "name": "model.layers.13.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 552960 + }, + { + "name": "model.layers.14.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 567296 + }, + { + "name": "model.layers.14.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 577536 + }, + { + "name": "model.layers.14.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 587776 + }, + { + "name": "model.layers.15.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 602112 + }, + { + "name": "model.layers.6.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 616448 + }, + { + "name": "model.layers.6.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 626688 + }, + { + "name": "model.layers.7.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 636928 + }, + { + "name": "model.layers.7.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 647168 + }, + { + "name": "model.layers.7.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 657408 + }, + { + "name": "model.layers.8.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 671744 + }, + { + "name": "model.layers.8.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 681984 + }, + { + "name": "model.layers.8.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 692224 + }, + { + "name": "model.layers.9.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 706560 + }, + { + "name": "model.layers.9.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 716800 + }, + { + "name": "model.layers.9.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 727040 + }, + { + "name": "model.layers.15.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 741376 + }, + { + "name": "model.layers.15.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 751616 + }, + { + "name": "model.layers.16.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 761856 + }, + { + "name": "model.layers.16.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 772096 + }, + { + "name": "model.layers.16.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 782336 + }, + { + "name": "model.layers.17.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 796672 + }, + { + "name": "model.layers.17.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 806912 + }, + { + "name": "model.layers.17.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 817152 + }, + { + "name": "model.layers.18.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 831488 + }, + { + "name": "model.layers.18.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 841728 + }, + { + "name": "model.layers.18.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 851968 + }, + { + "name": "model.layers.19.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 866304 + }, + { + "name": "model.layers.19.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 876544 + }, + { + "name": "model.layers.19.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 886784 + }, + { + "name": "model.layers.20.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 901120 + }, + { + "name": "model.layers.20.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 911360 + }, + { + "name": "model.layers.20.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 921600 + }, + { + "name": "model.layers.21.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 935936 + }, + { + "name": "model.layers.21.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 946176 + }, + { + "name": "model.layers.21.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 956416 + }, + { + "name": "model.layers.22.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 970752 + }, + { + "name": "model.layers.22.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 980992 + }, + { + "name": "model.layers.22.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 991232 + }, + { + "name": "model.layers.23.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1005568 + }, + { + "name": "model.layers.23.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1015808 + }, + { + "name": "model.layers.23.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 1026048 + }, + { + "name": "model.layers.24.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 1040384 + }, + { + "name": "model.layers.24.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1054720 + }, + { + "name": "model.layers.24.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1064960 + }, + { + "name": "model.layers.25.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1075200 + }, + { + "name": "model.layers.25.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1085440 + }, + { + "name": "model.layers.25.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 1095680 + }, + { + "name": "model.layers.26.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1110016 + }, + { + "name": "model.layers.26.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1120256 + }, + { + "name": "model.layers.26.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 1130496 + }, + { + "name": "model.layers.27.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1144832 + }, + { + "name": "model.layers.27.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1155072 + }, + { + "name": "model.layers.27.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 1165312 + }, + { + "name": "model.layers.28.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1179648 + }, + { + "name": "model.layers.28.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1189888 + }, + { + "name": "model.layers.28.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 1200128 + }, + { + "name": "model.layers.29.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1214464 + }, + { + "name": "model.layers.29.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1224704 + }, + { + "name": "model.layers.29.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 1234944 + }, + { + "name": "model.layers.30.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1249280 + }, + { + "name": "model.layers.30.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1259520 + }, + { + "name": "model.layers.30.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 1269760 + }, + { + "name": "model.layers.31.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1284096 + }, + { + "name": "model.layers.31.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1294336 + }, + { + "name": "model.layers.31.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 1304576 + }, + { + "name": "model.layers.32.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1318912 + }, + { + "name": "model.layers.32.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1329152 + }, + { + "name": "model.layers.32.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 1339392 + }, + { + "name": "model.layers.33.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 1353728 + }, + { + "name": "model.layers.33.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1368064 + }, + { + "name": "model.layers.33.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1378304 + }, + { + "name": "model.layers.34.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1388544 + }, + { + "name": "model.layers.34.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1398784 + }, + { + "name": "model.layers.34.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 1409024 + }, + { + "name": "model.layers.35.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1423360 + }, + { + "name": "model.layers.35.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1433600 + }, + { + "name": "model.layers.35.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 1443840 + }, + { + "name": "model.layers.36.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1458176 + }, + { + "name": "model.layers.36.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1468416 + }, + { + "name": "model.layers.36.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 1478656 + }, + { + "name": "model.layers.37.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1492992 + }, + { + "name": "model.layers.37.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1503232 + }, + { + "name": "model.layers.37.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 1513472 + }, + { + "name": "model.layers.38.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1527808 + }, + { + "name": "model.layers.38.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1538048 + }, + { + "name": "model.layers.38.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 1548288 + }, + { + "name": "model.layers.39.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1562624 + }, + { + "name": "model.layers.39.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1572864 + }, + { + "name": "model.layers.39.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 1583104 + }, + { + "name": "model.layers.40.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1597440 + }, + { + "name": "model.layers.40.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1607680 + }, + { + "name": "model.layers.40.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 1617920 + }, + { + "name": "model.layers.41.input_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1632256 + }, + { + "name": "model.layers.41.post_attention_layernorm.weight", + "shape": [ + 5120 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 10240, + "byteOffset": 1642496 + }, + { + "name": "model.layers.41.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 1652736 + }, + { + "name": "model.layers.42.self_attn.c_attn.bias", + "shape": [ + 7168 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14336, + "byteOffset": 1667072 + } + ], + "md5sum": "9626c51b07b45f58c41c28d1fa1f8a57" + } + ] +} \ No newline at end of file