{ "metadata": { "ParamSize": 590, "ParamBytes": 14126854144.0, "BitsPerParam": 16.0 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 262668288, "records": [ { "name": "language_model.lm_head.weight", "shape": [ 32064, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262668288, "byteOffset": 0 } ], "md5sum": "39400dcc46be2f77cbd3bdbb23df0e20" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "language_model.model.layers.22.mlp.down_proj.weight", "shape": [ 4096, 11008 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "bdbe8a8197a4d2c8eaf4681401c32693" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "language_model.model.layers.22.mlp.gate_up_proj.weight", "shape": [ 22016, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "70fe8d914b1e231c9663aa4c7f1ea0b4" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "language_model.model.layers.23.mlp.down_proj.weight", "shape": [ 4096, 11008 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "0f4cb94fd572946ca5963e63cbe489af" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "language_model.model.layers.23.mlp.gate_up_proj.weight", "shape": [ 22016, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "198e73156986a21b4d51119a0415ff1f" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "language_model.model.layers.23.self_attn.qkv_proj.weight", "shape": [ 12288, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "438ed41988e68c301c0a28c0683cf762" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "language_model.model.layers.23.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "9bf81a4d4f8400a2d3e8bbbcb6f2cc63" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "language_model.model.layers.24.mlp.down_proj.weight", "shape": [ 4096, 11008 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "cca01120e773c4dc74e519993506415e" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "language_model.model.layers.24.mlp.gate_up_proj.weight", "shape": [ 22016, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "22d5817e607dd14836bfd302029ceeea" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "language_model.model.layers.24.self_attn.qkv_proj.weight", "shape": [ 12288, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "ceaefefabfff59d0052a5e5f1b87591f" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "language_model.model.layers.24.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "5ccda3809da42430def8bd26ee3e8b57" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "language_model.model.layers.25.mlp.down_proj.weight", "shape": [ 4096, 11008 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "09eee680c12f75b45e77579a96698659" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "language_model.model.layers.25.mlp.gate_up_proj.weight", "shape": [ 22016, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "5e783660ee70fcd7abcf211f10f87fd3" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "language_model.model.layers.25.self_attn.qkv_proj.weight", "shape": [ 12288, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "7520fe93a84a9a3b9b127d806f661dd1" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "language_model.model.layers.25.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "42472065a4227f0ef4b930cc2663960c" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "language_model.model.layers.26.mlp.down_proj.weight", "shape": [ 4096, 11008 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "298c0690d3a15175fb8454d230fb0659" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "language_model.model.layers.26.mlp.gate_up_proj.weight", "shape": [ 22016, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "314b39d52d515a0d4bff2f343a23c623" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "language_model.model.layers.26.self_attn.qkv_proj.weight", "shape": [ 12288, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "aeec9eab2fdcdf820f2b1536aa8363d4" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "language_model.model.layers.26.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "3da8cc5454947804f979084da2c98bc6" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "language_model.model.layers.27.mlp.down_proj.weight", "shape": [ 4096, 11008 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "2bfb7df00aa499af63871073c6d7883f" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "language_model.model.layers.27.mlp.gate_up_proj.weight", "shape": [ 22016, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "f08fe8b10ea2c4f0d73822dd0e4f5d2c" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "language_model.model.layers.27.self_attn.qkv_proj.weight", "shape": [ 12288, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "ae3e95c4fe29622e1a711a437a402999" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "language_model.model.layers.27.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "d6d28504f2e975b66b88ddea5da453f0" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "language_model.model.layers.28.mlp.down_proj.weight", "shape": [ 4096, 11008 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "f422e68c8d2b201ced094e45007d6e49" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "language_model.model.layers.28.mlp.gate_up_proj.weight", "shape": [ 22016, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "64488e71b761d42a0b772d50f2927f64" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "language_model.model.layers.28.self_attn.qkv_proj.weight", "shape": [ 12288, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "a7b97bd8f0a4fbcf7224407e45bc09c3" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "language_model.model.layers.28.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "2fb308b2d573d2dc3f0be7f61aaaabbc" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "language_model.model.layers.29.mlp.down_proj.weight", "shape": [ 4096, 11008 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "cdfdabe2656f7fb1a63eaef7de2e230c" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "language_model.model.layers.29.mlp.gate_up_proj.weight", "shape": [ 22016, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "8b828becbd4df305c1a934c8f57616f6" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "language_model.model.layers.29.self_attn.qkv_proj.weight", "shape": [ 12288, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "99806377b7045f23ffc5ef7ef37c7edf" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "language_model.model.layers.29.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "4bc1b87483c2be5b484d7346dc6f4626" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "language_model.model.layers.30.mlp.down_proj.weight", "shape": [ 4096, 11008 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "a258feda128fa1a161bda3068abf5eff" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "language_model.model.layers.30.mlp.gate_up_proj.weight", "shape": [ 22016, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "0f6d360cf0a172aa529f9a374c407bc7" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "language_model.model.layers.30.self_attn.qkv_proj.weight", "shape": [ 12288, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "dbd1d493a565cd306c1e479a92a8f88e" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "language_model.model.layers.30.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "ab17789069a6ece842c0dff07feabeca" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "language_model.model.layers.31.mlp.down_proj.weight", "shape": [ 4096, 11008 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "9319da461e1c7c938df92ec896ec146a" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "language_model.model.layers.31.mlp.gate_up_proj.weight", "shape": [ 22016, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "7aafdfacb8fbd3ad30745caf8ff07993" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "language_model.model.layers.31.self_attn.qkv_proj.weight", "shape": [ 12288, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "f25fd0547b6d286cf3f20947d7e9dcc3" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "language_model.model.layers.31.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "e8b65f4397049a0a9466c7e2deeea7e6" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 262668288, "records": [ { "name": "language_model.model.embed_tokens.weight", "shape": [ 32064, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262668288, "byteOffset": 0 } ], "md5sum": "bd58751fa90fc368810b08c25892d7c7" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "language_model.model.layers.0.mlp.down_proj.weight", "shape": [ 4096, 11008 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "5984a117cf5247ab8c8efb5752d835a7" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "language_model.model.layers.0.mlp.gate_up_proj.weight", "shape": [ 22016, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "924f67c5642241784a614c71bb308e87" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "language_model.model.layers.0.self_attn.qkv_proj.weight", "shape": [ 12288, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "3f505db5851c248e0756b732b68505ce" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "language_model.model.layers.0.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "945dc55633ad33427b27e661fc164cf0" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "language_model.model.layers.1.mlp.down_proj.weight", "shape": [ 4096, 11008 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "2a746ce7ad3399237ef7525dedb13c37" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "language_model.model.layers.1.mlp.gate_up_proj.weight", "shape": [ 22016, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "1254d789af599843b5544c96f24b3897" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "language_model.model.layers.1.self_attn.qkv_proj.weight", "shape": [ 12288, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "b7134b05e1b20ae5c4772a22318b68c0" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "language_model.model.layers.1.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "b26b3c3db565b6129060eddc2e55e194" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "language_model.model.layers.10.self_attn.qkv_proj.weight", "shape": [ 12288, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "a416427d81e4a55d2c03ac8db84ea12d" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "language_model.model.layers.2.mlp.down_proj.weight", "shape": [ 4096, 11008 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "d3d71029dbfdd41000af967ff1303de4" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "language_model.model.layers.2.mlp.gate_up_proj.weight", "shape": [ 22016, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "96585495c0712d10a7cae939d07a2125" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "language_model.model.layers.2.self_attn.qkv_proj.weight", "shape": [ 12288, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "fdde7ad40423ad0554efa6dd6ff411a8" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "language_model.model.layers.2.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "189fe345d893659c8ddf26f890adf035" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "language_model.model.layers.3.mlp.down_proj.weight", "shape": [ 4096, 11008 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "2f318464eef7e68318a29c73920d8f2f" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "language_model.model.layers.3.mlp.gate_up_proj.weight", "shape": [ 22016, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "a2800ef38c95c775e36eb83705729a5d" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "language_model.model.layers.3.self_attn.qkv_proj.weight", "shape": [ 12288, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "eea0e96014fc70a987950ebb4fab65ce" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "language_model.model.layers.3.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "bdbcd435ffcd9a2b0c739bccd3c6ce7e" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "language_model.model.layers.4.mlp.down_proj.weight", "shape": [ 4096, 11008 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "d664a0b8c06e15c992f364ed970dbd42" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "language_model.model.layers.4.mlp.gate_up_proj.weight", "shape": [ 22016, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "2a826e99789084c8c23d8a577adafec9" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "language_model.model.layers.4.self_attn.qkv_proj.weight", "shape": [ 12288, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "30890a582f0c76d5c1fe010f744804c3" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "language_model.model.layers.4.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "0141e03bbef1960981ab477d3e7073f1" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "language_model.model.layers.5.mlp.down_proj.weight", "shape": [ 4096, 11008 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "66dff6aff1b1b2cc3b5f6b6ea21d8100" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "language_model.model.layers.5.mlp.gate_up_proj.weight", "shape": [ 22016, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "6c531e3ef56f94266927fbdd3724d236" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "language_model.model.layers.5.self_attn.qkv_proj.weight", "shape": [ 12288, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "4d21077e72355d83930795db630b007b" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "language_model.model.layers.5.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "f3fe776c5274d3fd6f976e8903e16fd2" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "language_model.model.layers.6.mlp.down_proj.weight", "shape": [ 4096, 11008 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "149360f5339d0496a1c9828e14efc5ef" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "language_model.model.layers.6.mlp.gate_up_proj.weight", "shape": [ 22016, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "35b6e2b53fe6167feec30a8e1632076c" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "language_model.model.layers.6.self_attn.qkv_proj.weight", "shape": [ 12288, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "7adb1070ed4528d0f7a72fc651e1bbef" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "language_model.model.layers.6.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "164040fb0478417dbc527abd88e55588" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "language_model.model.layers.7.mlp.down_proj.weight", "shape": [ 4096, 11008 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "f6dc7420c629862abaaa8e8ed5b6bf77" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "language_model.model.layers.7.mlp.gate_up_proj.weight", "shape": [ 22016, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "26cdd5b2a62d86f713866b60987fbc29" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "language_model.model.layers.7.self_attn.qkv_proj.weight", "shape": [ 12288, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "4410b92e1050c4b4885859d5ebc22f6c" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "language_model.model.layers.7.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "d179c1287a7027360cda0592e824a0d9" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "language_model.model.layers.8.mlp.down_proj.weight", "shape": [ 4096, 11008 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "9674dd1468664b96cb23d6eedc12083e" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "language_model.model.layers.8.mlp.gate_up_proj.weight", "shape": [ 22016, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "81e305f64c33ea732e3db371d7d2c198" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "language_model.model.layers.8.self_attn.qkv_proj.weight", "shape": [ 12288, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "a4ef8e08432523bae4cac7fd80273333" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "language_model.model.layers.8.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "0a955c803f84afec485564a674b6c32f" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "language_model.model.layers.9.mlp.down_proj.weight", "shape": [ 4096, 11008 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "346caf73b2fe993e346d4e960e5500f9" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "language_model.model.layers.9.mlp.gate_up_proj.weight", "shape": [ 22016, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "48f1ed15c141f1edc834079d573f9a1a" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "language_model.model.layers.9.self_attn.qkv_proj.weight", "shape": [ 12288, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "fa6d6077aa20cdfd278f052fe30fe371" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "language_model.model.layers.9.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "d089111971ee2d3f784ab86ec7b8fc8b" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "multi_modal_projector.linear_2.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "8a47170acedb67e9ec7a46cff23cff57" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 32124928, "records": [ { "name": "language_model.model.layers.22.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 0 }, { "name": "language_model.model.layers.22.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 8192 }, { "name": "language_model.model.layers.23.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 16384 }, { "name": "language_model.model.layers.23.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24576 }, { "name": "language_model.model.layers.24.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 32768 }, { "name": "language_model.model.layers.24.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 40960 }, { "name": "language_model.model.layers.25.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 49152 }, { "name": "language_model.model.layers.25.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 57344 }, { "name": "language_model.model.layers.26.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 65536 }, { "name": "language_model.model.layers.26.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 73728 }, { "name": "language_model.model.layers.27.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 81920 }, { "name": "language_model.model.layers.27.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 90112 }, { "name": "language_model.model.layers.28.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 98304 }, { "name": "language_model.model.layers.28.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 106496 }, { "name": "language_model.model.layers.29.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 114688 }, { "name": "language_model.model.layers.29.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 122880 }, { "name": "language_model.model.layers.30.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 131072 }, { "name": "language_model.model.layers.30.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 139264 }, { "name": "language_model.model.layers.31.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 147456 }, { "name": "language_model.model.layers.31.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 155648 }, { "name": "language_model.model.norm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 163840 }, { "name": "language_model.model.layers.0.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 172032 }, { "name": "language_model.model.layers.0.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 180224 }, { "name": "language_model.model.layers.1.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 188416 }, { "name": "language_model.model.layers.1.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 196608 }, { "name": "language_model.model.layers.2.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 204800 }, { "name": "language_model.model.layers.2.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 212992 }, { "name": "language_model.model.layers.3.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 221184 }, { "name": "language_model.model.layers.3.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 229376 }, { "name": "language_model.model.layers.4.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 237568 }, { "name": "language_model.model.layers.4.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 245760 }, { "name": "language_model.model.layers.5.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 253952 }, { "name": "language_model.model.layers.5.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 262144 }, { "name": "language_model.model.layers.6.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 270336 }, { "name": "language_model.model.layers.6.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 278528 }, { "name": "language_model.model.layers.7.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 286720 }, { "name": "language_model.model.layers.7.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 294912 }, { "name": "language_model.model.layers.8.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 303104 }, { "name": "language_model.model.layers.8.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 311296 }, { "name": "language_model.model.layers.9.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 319488 }, { "name": "language_model.model.layers.9.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 327680 }, { "name": "multi_modal_projector.linear_1.bias", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 335872 }, { "name": "multi_modal_projector.linear_1.weight", "shape": [ 4096, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 344064 }, { "name": "multi_modal_projector.linear_2.bias", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 8732672 }, { "name": "vision_tower.vision_model.embeddings.class_embedding", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 8740864 }, { "name": "vision_tower.vision_model.embeddings.patch_embedding.weight", "shape": [ 1024, 3, 14, 14 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1204224, "byteOffset": 8742912 }, { "name": "vision_tower.vision_model.embeddings.position_embedding.weight", "shape": [ 577, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1181696, "byteOffset": 9947136 }, { "name": "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 11128832 }, { "name": "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 11130880 }, { "name": "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 11132928 }, { "name": "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 11134976 }, { "name": "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 11137024 }, { "name": "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight", "shape": [ 4096, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11145216 }, { "name": "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 19533824 }, { "name": "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight", "shape": [ 1024, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 19535872 }, { "name": "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 27924480 }, { "name": "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 27926528 }, { "name": "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 30023680 }, { "name": "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 30025728 }, { "name": "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 32122880 } ], "md5sum": "8ad03846d2568bf856c678e9448501a0" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 29405184, "records": [ { "name": "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 0 }, { "name": "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 2097152 }, { "name": "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 2099200 }, { "name": "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 4196352 }, { "name": "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 4198400 }, { "name": "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 4200448 }, { "name": "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 4202496 }, { "name": "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 4204544 }, { "name": "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight", "shape": [ 4096, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 4212736 }, { "name": "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 12601344 }, { "name": "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight", "shape": [ 1024, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 12603392 }, { "name": "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 20992000 }, { "name": "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20994048 }, { "name": "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 23091200 }, { "name": "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23093248 }, { "name": "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25190400 }, { "name": "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 25192448 }, { "name": "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 27289600 }, { "name": "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 27291648 }, { "name": "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 29388800 }, { "name": "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 29390848 }, { "name": "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 29392896 }, { "name": "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 29394944 }, { "name": "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29396992 } ], "md5sum": "45a78a0d70be9defb9128bcf67c31496" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 25192448, "records": [ { "name": "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight", "shape": [ 4096, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 8388608 }, { "name": "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight", "shape": [ 1024, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8390656 }, { "name": "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 16779264 }, { "name": "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 16781312 }, { "name": "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 18878464 }, { "name": "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18880512 }, { "name": "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 20977664 }, { "name": "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20979712 }, { "name": "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 23076864 }, { "name": "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23078912 }, { "name": "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25176064 }, { "name": "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25178112 }, { "name": "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25180160 }, { "name": "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25182208 }, { "name": "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25184256 } ], "md5sum": "45b93ee7acd2cf78617830f4db37d1da" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 25192448, "records": [ { "name": "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight", "shape": [ 4096, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 8388608 }, { "name": "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight", "shape": [ 1024, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8390656 }, { "name": "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 16779264 }, { "name": "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 16781312 }, { "name": "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 18878464 }, { "name": "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18880512 }, { "name": "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 20977664 }, { "name": "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20979712 }, { "name": "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 23076864 }, { "name": "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23078912 }, { "name": "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25176064 }, { "name": "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25178112 }, { "name": "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25180160 }, { "name": "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25182208 }, { "name": "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25184256 } ], "md5sum": "848d05f288b225a6ad57f1fcc06d0db4" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 25192448, "records": [ { "name": "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight", "shape": [ 4096, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 8388608 }, { "name": "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight", "shape": [ 1024, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8390656 }, { "name": "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 16779264 }, { "name": "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 16781312 }, { "name": "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 18878464 }, { "name": "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18880512 }, { "name": "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 20977664 }, { "name": "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20979712 }, { "name": "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 23076864 }, { "name": "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23078912 }, { "name": "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25176064 }, { "name": "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25178112 }, { "name": "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25180160 }, { "name": "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25182208 }, { "name": "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25184256 } ], "md5sum": "7a5a1eb82716308e5fef638df3988b8c" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 25192448, "records": [ { "name": "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight", "shape": [ 4096, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 8388608 }, { "name": "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight", "shape": [ 1024, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8390656 }, { "name": "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 16779264 }, { "name": "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 16781312 }, { "name": "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 18878464 }, { "name": "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18880512 }, { "name": "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 20977664 }, { "name": "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20979712 }, { "name": "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 23076864 }, { "name": "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23078912 }, { "name": "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25176064 }, { "name": "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25178112 }, { "name": "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25180160 }, { "name": "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25182208 }, { "name": "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25184256 } ], "md5sum": "2eb33b4c1dfc835c8ecc272808fe3607" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 25192448, "records": [ { "name": "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight", "shape": [ 4096, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 8388608 }, { "name": "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight", "shape": [ 1024, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8390656 }, { "name": "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 16779264 }, { "name": "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 16781312 }, { "name": "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 18878464 }, { "name": "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18880512 }, { "name": "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 20977664 }, { "name": "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20979712 }, { "name": "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 23076864 }, { "name": "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23078912 }, { "name": "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25176064 }, { "name": "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25178112 }, { "name": "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25180160 }, { "name": "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25182208 }, { "name": "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25184256 } ], "md5sum": "546b40ff6aa48daee4502c000f26c90c" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 25192448, "records": [ { "name": "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight", "shape": [ 4096, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 8388608 }, { "name": "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight", "shape": [ 1024, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8390656 }, { "name": "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 16779264 }, { "name": "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 16781312 }, { "name": "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 18878464 }, { "name": "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18880512 }, { "name": "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 20977664 }, { "name": "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20979712 }, { "name": "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 23076864 }, { "name": "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23078912 }, { "name": "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25176064 }, { "name": "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25178112 }, { "name": "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25180160 }, { "name": "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25182208 }, { "name": "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25184256 } ], "md5sum": "ef0296089e022d2853187b686e422c03" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 25192448, "records": [ { "name": "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight", "shape": [ 4096, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 8388608 }, { "name": "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight", "shape": [ 1024, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8390656 }, { "name": "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 16779264 }, { "name": "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 16781312 }, { "name": "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 18878464 }, { "name": "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18880512 }, { "name": "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 20977664 }, { "name": "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20979712 }, { "name": "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 23076864 }, { "name": "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23078912 }, { "name": "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25176064 }, { "name": "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25178112 }, { "name": "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25180160 }, { "name": "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25182208 }, { "name": "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25184256 } ], "md5sum": "f4b6e3686c289d2b2506e69f7a5467dd" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 25192448, "records": [ { "name": "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight", "shape": [ 4096, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 8388608 }, { "name": "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight", "shape": [ 1024, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8390656 }, { "name": "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 16779264 }, { "name": "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 16781312 }, { "name": "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 18878464 }, { "name": "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18880512 }, { "name": "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 20977664 }, { "name": "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20979712 }, { "name": "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 23076864 }, { "name": "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23078912 }, { "name": "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25176064 }, { "name": "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25178112 }, { "name": "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25180160 }, { "name": "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25182208 }, { "name": "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25184256 } ], "md5sum": "959205e1554d059d6dedd6fab6e01f35" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 25192448, "records": [ { "name": "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight", "shape": [ 4096, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 8388608 }, { "name": "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight", "shape": [ 1024, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8390656 }, { "name": "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 16779264 }, { "name": "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 16781312 }, { "name": "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 18878464 }, { "name": "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18880512 }, { "name": "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 20977664 }, { "name": "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20979712 }, { "name": "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 23076864 }, { "name": "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23078912 }, { "name": "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25176064 }, { "name": "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25178112 }, { "name": "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25180160 }, { "name": "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25182208 }, { "name": "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25184256 } ], "md5sum": "3057856c4131b7e707feb9717f4fd21d" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 25192448, "records": [ { "name": "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight", "shape": [ 4096, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 8388608 }, { "name": "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight", "shape": [ 1024, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8390656 }, { "name": "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 16779264 }, { "name": "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 16781312 }, { "name": "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 18878464 }, { "name": "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18880512 }, { "name": "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 20977664 }, { "name": "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20979712 }, { "name": "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 23076864 }, { "name": "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23078912 }, { "name": "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25176064 }, { "name": "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25178112 }, { "name": "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25180160 }, { "name": "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25182208 }, { "name": "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25184256 } ], "md5sum": "602612832e4e57eb7530ceb325587e88" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 25192448, "records": [ { "name": "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight", "shape": [ 4096, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 8388608 }, { "name": "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight", "shape": [ 1024, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8390656 }, { "name": "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 16779264 }, { "name": "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 16781312 }, { "name": "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 18878464 }, { "name": "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18880512 }, { "name": "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 20977664 }, { "name": "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20979712 }, { "name": "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 23076864 }, { "name": "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23078912 }, { "name": "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25176064 }, { "name": "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25178112 }, { "name": "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25180160 }, { "name": "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25182208 }, { "name": "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25184256 } ], "md5sum": "c1859d3e0af7ccd5213125f72084c36c" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 25192448, "records": [ { "name": "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight", "shape": [ 4096, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 8388608 }, { "name": "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight", "shape": [ 1024, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8390656 }, { "name": "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 16779264 }, { "name": "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 16781312 }, { "name": "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 18878464 }, { "name": "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18880512 }, { "name": "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 20977664 }, { "name": "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20979712 }, { "name": "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 23076864 }, { "name": "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23078912 }, { "name": "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25176064 }, { "name": "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25178112 }, { "name": "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25180160 }, { "name": "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25182208 }, { "name": "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25184256 } ], "md5sum": "7a8bb0d64140900e86c011755f22e75a" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 25192448, "records": [ { "name": "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight", "shape": [ 4096, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 8388608 }, { "name": "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight", "shape": [ 1024, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8390656 }, { "name": "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 16779264 }, { "name": "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 16781312 }, { "name": "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 18878464 }, { "name": "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18880512 }, { "name": "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 20977664 }, { "name": "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20979712 }, { "name": "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 23076864 }, { "name": "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23078912 }, { "name": "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25176064 }, { "name": "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25178112 }, { "name": "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25180160 }, { "name": "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25182208 }, { "name": "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25184256 } ], "md5sum": "e0f7ad5cf55a90deec2d29f616b30de0" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 25192448, "records": [ { "name": "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight", "shape": [ 4096, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 8388608 }, { "name": "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight", "shape": [ 1024, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8390656 }, { "name": "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 16779264 }, { "name": "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 16781312 }, { "name": "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 18878464 }, { "name": "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18880512 }, { "name": "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 20977664 }, { "name": "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20979712 }, { "name": "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 23076864 }, { "name": "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23078912 }, { "name": "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25176064 }, { "name": "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25178112 }, { "name": "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25180160 }, { "name": "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25182208 }, { "name": "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25184256 } ], "md5sum": "50dd60e033a06bd332ca5bd848448168" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 25192448, "records": [ { "name": "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight", "shape": [ 4096, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 8388608 }, { "name": "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight", "shape": [ 1024, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8390656 }, { "name": "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 16779264 }, { "name": "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 16781312 }, { "name": "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 18878464 }, { "name": "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18880512 }, { "name": "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 20977664 }, { "name": "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20979712 }, { "name": "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 23076864 }, { "name": "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23078912 }, { "name": "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25176064 }, { "name": "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25178112 }, { "name": "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25180160 }, { "name": "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25182208 }, { "name": "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25184256 } ], "md5sum": "a674ecc2692d2941d5ac0b513e95c772" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 25192448, "records": [ { "name": "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight", "shape": [ 4096, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 8388608 }, { "name": "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight", "shape": [ 1024, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8390656 }, { "name": "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 16779264 }, { "name": "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 16781312 }, { "name": "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 18878464 }, { "name": "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18880512 }, { "name": "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 20977664 }, { "name": "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20979712 }, { "name": "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 23076864 }, { "name": "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23078912 }, { "name": "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25176064 }, { "name": "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25178112 }, { "name": "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25180160 }, { "name": "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25182208 }, { "name": "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25184256 } ], "md5sum": "9c8db32c14eadb6a4a4e2db51649f312" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 25192448, "records": [ { "name": "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight", "shape": [ 4096, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 8388608 }, { "name": "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight", "shape": [ 1024, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8390656 }, { "name": "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 16779264 }, { "name": "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 16781312 }, { "name": "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 18878464 }, { "name": "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18880512 }, { "name": "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 20977664 }, { "name": "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20979712 }, { "name": "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 23076864 }, { "name": "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23078912 }, { "name": "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25176064 }, { "name": "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25178112 }, { "name": "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25180160 }, { "name": "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25182208 }, { "name": "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25184256 } ], "md5sum": "569c1572f8377a19b175c2342e0c3acb" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 25192448, "records": [ { "name": "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight", "shape": [ 4096, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 8388608 }, { "name": "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight", "shape": [ 1024, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8390656 }, { "name": "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 16779264 }, { "name": "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 16781312 }, { "name": "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 18878464 }, { "name": "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18880512 }, { "name": "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 20977664 }, { "name": "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20979712 }, { "name": "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 23076864 }, { "name": "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23078912 }, { "name": "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25176064 }, { "name": "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25178112 }, { "name": "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25180160 }, { "name": "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25182208 }, { "name": "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25184256 } ], "md5sum": "553bbf52f779eadc2ceb3f992ba4fc1f" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 25192448, "records": [ { "name": "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight", "shape": [ 4096, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 8388608 }, { "name": "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight", "shape": [ 1024, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8390656 }, { "name": "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 16779264 }, { "name": "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 16781312 }, { "name": "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 18878464 }, { "name": "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18880512 }, { "name": "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 20977664 }, { "name": "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20979712 }, { "name": "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 23076864 }, { "name": "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23078912 }, { "name": "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25176064 }, { "name": "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25178112 }, { "name": "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25180160 }, { "name": "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25182208 }, { "name": "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25184256 } ], "md5sum": "a8c4e5eab493ab816bebc94a091035f9" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 25192448, "records": [ { "name": "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight", "shape": [ 4096, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 8388608 }, { "name": "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight", "shape": [ 1024, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8390656 }, { "name": "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 16779264 }, { "name": "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 16781312 }, { "name": "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 18878464 }, { "name": "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18880512 }, { "name": "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 20977664 }, { "name": "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20979712 }, { "name": "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 23076864 }, { "name": "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23078912 }, { "name": "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25176064 }, { "name": "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25178112 }, { "name": "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25180160 }, { "name": "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25182208 }, { "name": "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25184256 } ], "md5sum": "70535f60bfef99fcc95e2bc84bcea1bc" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 25192448, "records": [ { "name": "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight", "shape": [ 4096, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 8388608 }, { "name": "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight", "shape": [ 1024, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8390656 }, { "name": "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 16779264 }, { "name": "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 16781312 }, { "name": "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 18878464 }, { "name": "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18880512 }, { "name": "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 20977664 }, { "name": "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20979712 }, { "name": "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 23076864 }, { "name": "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23078912 }, { "name": "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25176064 }, { "name": "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25178112 }, { "name": "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25180160 }, { "name": "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25182208 }, { "name": "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25184256 } ], "md5sum": "70bbe5474dba6bc26d836c750586eb4a" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "language_model.model.layers.10.mlp.down_proj.weight", "shape": [ 4096, 11008 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "6f42271bb55931053ab064b4951fc510" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "language_model.model.layers.10.mlp.gate_up_proj.weight", "shape": [ 22016, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "267ac07763ab00b4eff0a7f6c02c192d" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "language_model.model.layers.10.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "a19dfacf43c9a0217fc54684ecb672e1" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "language_model.model.layers.11.mlp.down_proj.weight", "shape": [ 4096, 11008 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "a3053c6101fd96e1ff34f918c4f88abb" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "language_model.model.layers.11.mlp.gate_up_proj.weight", "shape": [ 22016, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "535bd27592903a3f676e7af547ccbf6d" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "language_model.model.layers.11.self_attn.qkv_proj.weight", "shape": [ 12288, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "bc607dc4becc48b31e22a7c0af453841" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "language_model.model.layers.11.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c90016f0587cbbac37326fc925e7d284" }, { "dataPath": "params_shard_112.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "language_model.model.layers.12.mlp.down_proj.weight", "shape": [ 4096, 11008 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "b3a8af2a56021dd4c193c0d08b40cc73" }, { "dataPath": "params_shard_113.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "language_model.model.layers.12.mlp.gate_up_proj.weight", "shape": [ 22016, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "5c5be72a189f96c3bbb6460a7cabe932" }, { "dataPath": "params_shard_114.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "language_model.model.layers.12.self_attn.qkv_proj.weight", "shape": [ 12288, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "bdbcd0af3872ac677b46873c235eaa42" }, { "dataPath": "params_shard_115.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "language_model.model.layers.12.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "9503cf3697d396319a32d3d9b24a605d" }, { "dataPath": "params_shard_116.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "language_model.model.layers.13.mlp.down_proj.weight", "shape": [ 4096, 11008 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "d96dc2bc2ea847c3d1da66472f72a396" }, { "dataPath": "params_shard_117.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "language_model.model.layers.13.mlp.gate_up_proj.weight", "shape": [ 22016, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "b9f1067d4907cd69c3e9a801c7c718f1" }, { "dataPath": "params_shard_118.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "language_model.model.layers.13.self_attn.qkv_proj.weight", "shape": [ 12288, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "787d7c592d6639ebdffa01bd996fb2c4" }, { "dataPath": "params_shard_119.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "language_model.model.layers.13.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "761bbb1d91815ed5b34284cfdbab7bf8" }, { "dataPath": "params_shard_120.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "language_model.model.layers.14.mlp.down_proj.weight", "shape": [ 4096, 11008 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "405bb0186f5e0e1e300f9629472bc5df" }, { "dataPath": "params_shard_121.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "language_model.model.layers.14.mlp.gate_up_proj.weight", "shape": [ 22016, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "1618a4c0de1853034bfb03f658c48381" }, { "dataPath": "params_shard_122.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "language_model.model.layers.14.self_attn.qkv_proj.weight", "shape": [ 12288, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "7fade5a898d2e7edfd440d6648750f3f" }, { "dataPath": "params_shard_123.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "language_model.model.layers.14.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "64d9c22f58105698174e48a09dd4f778" }, { "dataPath": "params_shard_124.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "language_model.model.layers.15.mlp.down_proj.weight", "shape": [ 4096, 11008 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "806e8b3d66590ffa7546cd5efdfb42e4" }, { "dataPath": "params_shard_125.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "language_model.model.layers.15.mlp.gate_up_proj.weight", "shape": [ 22016, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "8ad1df861673a0b19edb96bedfa86f49" }, { "dataPath": "params_shard_126.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "language_model.model.layers.15.self_attn.qkv_proj.weight", "shape": [ 12288, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "4103f1dc4003814423ccbc5f9be89ed3" }, { "dataPath": "params_shard_127.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "language_model.model.layers.15.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "3759fce7ae5bd1f9403490c6529dfe1f" }, { "dataPath": "params_shard_128.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "language_model.model.layers.16.mlp.down_proj.weight", "shape": [ 4096, 11008 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "d18a208e1874058fa602a5700dde96b5" }, { "dataPath": "params_shard_129.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "language_model.model.layers.16.mlp.gate_up_proj.weight", "shape": [ 22016, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "c5b734898c94de9f26732d61f99a754d" }, { "dataPath": "params_shard_130.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "language_model.model.layers.16.self_attn.qkv_proj.weight", "shape": [ 12288, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "15c94672e0a770d798318ed61b6cc247" }, { "dataPath": "params_shard_131.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "language_model.model.layers.16.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "de463ae618403c927a3fd5ac7ee84e77" }, { "dataPath": "params_shard_132.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "language_model.model.layers.17.mlp.down_proj.weight", "shape": [ 4096, 11008 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "b65c474a2340f772f3e2b006a76f6f8a" }, { "dataPath": "params_shard_133.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "language_model.model.layers.17.mlp.gate_up_proj.weight", "shape": [ 22016, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "d922e438a06ebc4e52e3d55aeb05d9a3" }, { "dataPath": "params_shard_134.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "language_model.model.layers.17.self_attn.qkv_proj.weight", "shape": [ 12288, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "15190a861664a18772871b7435e9f3ee" }, { "dataPath": "params_shard_135.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "language_model.model.layers.17.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "5e466285966efff82202e3b13350d73a" }, { "dataPath": "params_shard_136.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "language_model.model.layers.18.mlp.down_proj.weight", "shape": [ 4096, 11008 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "19a671347b1c8cb810d2f8d3edea683e" }, { "dataPath": "params_shard_137.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "language_model.model.layers.18.mlp.gate_up_proj.weight", "shape": [ 22016, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "67730cef3cda6c2941217a3151a7fb96" }, { "dataPath": "params_shard_138.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "language_model.model.layers.18.self_attn.qkv_proj.weight", "shape": [ 12288, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "e26ba3dd7eb04ccea23a262735797b54" }, { "dataPath": "params_shard_139.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "language_model.model.layers.18.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "7b33b57d9439d5c81624c5b3dcc4b25c" }, { "dataPath": "params_shard_140.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "language_model.model.layers.19.mlp.down_proj.weight", "shape": [ 4096, 11008 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "4d3ce43c200acd8d5688dc3d70e86890" }, { "dataPath": "params_shard_141.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "language_model.model.layers.19.mlp.gate_up_proj.weight", "shape": [ 22016, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "20d52b878164a91a04c40496857b7046" }, { "dataPath": "params_shard_142.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "language_model.model.layers.19.self_attn.qkv_proj.weight", "shape": [ 12288, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "dc4efe0c92f5e28f3f1bfbc92d0c2298" }, { "dataPath": "params_shard_143.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "language_model.model.layers.19.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "a6f3a78863d4e5488734a42e2c58fc0f" }, { "dataPath": "params_shard_144.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "language_model.model.layers.20.mlp.down_proj.weight", "shape": [ 4096, 11008 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "5a98fbb2a03e2cc68dcb66f345f5cb6e" }, { "dataPath": "params_shard_145.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "language_model.model.layers.20.mlp.gate_up_proj.weight", "shape": [ 22016, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "d0ed5d20fa56e2c53ee32ddb5a64f022" }, { "dataPath": "params_shard_146.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "language_model.model.layers.20.self_attn.qkv_proj.weight", "shape": [ 12288, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "777630e0c7f090a9ecd2adfbdcbf4159" }, { "dataPath": "params_shard_147.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "language_model.model.layers.20.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "1350f6d6a6db9555b607e37b0dc0f3d0" }, { "dataPath": "params_shard_148.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "language_model.model.layers.21.mlp.down_proj.weight", "shape": [ 4096, 11008 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "a67fa41a12fb49e4e70b0735249fefb5" }, { "dataPath": "params_shard_149.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "language_model.model.layers.21.mlp.gate_up_proj.weight", "shape": [ 22016, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "9e0b9ee675e8a0843d2bd08a5a37200e" }, { "dataPath": "params_shard_150.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "language_model.model.layers.21.self_attn.qkv_proj.weight", "shape": [ 12288, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "4fc47e011f42f5a344a05a63d4e2e41c" }, { "dataPath": "params_shard_151.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "language_model.model.layers.21.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "17866d0ad00dbaaaa715ed1463563223" }, { "dataPath": "params_shard_152.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "language_model.model.layers.22.self_attn.qkv_proj.weight", "shape": [ 12288, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "efe86fc45fe13324cc7bc8b0cb285283" }, { "dataPath": "params_shard_153.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "language_model.model.layers.22.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "2f929477c8e1ee3bab49db0300468d4b" }, { "dataPath": "params_shard_154.bin", "format": "raw-shard", "nbytes": 25380864, "records": [ { "name": "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight", "shape": [ 4096, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 8388608 }, { "name": "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight", "shape": [ 1024, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 8390656 }, { "name": "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 16779264 }, { "name": "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 16781312 }, { "name": "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 18878464 }, { "name": "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 18880512 }, { "name": "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 20977664 }, { "name": "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20979712 }, { "name": "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 23076864 }, { "name": "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight", "shape": [ 1024, 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 23078912 }, { "name": "vision_tower.vision_model.post_layernorm.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25176064 }, { "name": "vision_tower.vision_model.post_layernorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25178112 }, { "name": "vision_tower.vision_model.pre_layrnorm.bias", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25180160 }, { "name": "vision_tower.vision_model.pre_layrnorm.weight", "shape": [ 1024 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2048, "byteOffset": 25182208 }, { "name": "language_model.model.layers.10.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25184256 }, { "name": "language_model.model.layers.10.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25192448 }, { "name": "language_model.model.layers.11.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25200640 }, { "name": "language_model.model.layers.11.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25208832 }, { "name": "language_model.model.layers.12.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25217024 }, { "name": "language_model.model.layers.12.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25225216 }, { "name": "language_model.model.layers.13.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25233408 }, { "name": "language_model.model.layers.13.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25241600 }, { "name": "language_model.model.layers.14.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25249792 }, { "name": "language_model.model.layers.14.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25257984 }, { "name": "language_model.model.layers.15.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25266176 }, { "name": "language_model.model.layers.15.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25274368 }, { "name": "language_model.model.layers.16.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25282560 }, { "name": "language_model.model.layers.16.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25290752 }, { "name": "language_model.model.layers.17.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25298944 }, { "name": "language_model.model.layers.17.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25307136 }, { "name": "language_model.model.layers.18.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25315328 }, { "name": "language_model.model.layers.18.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25323520 }, { "name": "language_model.model.layers.19.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25331712 }, { "name": "language_model.model.layers.19.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25339904 }, { "name": "language_model.model.layers.20.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25348096 }, { "name": "language_model.model.layers.20.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25356288 }, { "name": "language_model.model.layers.21.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25364480 }, { "name": "language_model.model.layers.21.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 25372672 } ], "md5sum": "f7211ef1aa3c07d624dc09073ea2d871" } ] }