{ "metadata": { "ParamSize": 405, "ParamBytes": 5859256320.0, "BitsPerParam": 3.6013014124597142 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "lm_head.q_weight", "shape": [ 32000, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "2dd96feac190bbdf24fc9e76db01f1f6" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "14aa10a4fe3ebe8c0fe20b0b34bf392e" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "f5e199c2ec166e730bcf74bfad97063e" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "08c8b4b28e2dcb18404a0ace982a460f" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.31.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "c3aa68d055be4f52ce9cded1ae69ea0f" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 26329088, "records": [ { "name": "lm_head.q_scale", "shape": [ 32000, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8192000 }, { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 8202240 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11745280 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11755520 }, { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11765760 }, { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15308800 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22386688 }, { "name": "model.layers.31.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22396928 } ], "md5sum": "57d6189aa63d40c1073107e9da5ce0f0" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.32.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "bdb75ea2056f67e6f786e2ba24f68cbf" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "329e7bc9ea042a38a1d6bf32a3508b62" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.32.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "01d39cfe27c25c8d073d423be103aba2" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.32.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.32.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.32.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.32.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.32.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "cf3465ff7f5b15b676c87b83d45318f1" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.33.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "9c0df03bc1bbd79073889d86bb9d0105" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "729b88f5e1383e9fd033004746c0f5ea" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.33.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "79dcc0bfef21018226d2f1a4ef23c4cc" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.32.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.32.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.33.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.33.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.33.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.33.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.33.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "73dbe391c8a09a6da952d61901665fdc" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.34.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "24140f7679958dffc55b3114357400c3" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "1000e1a61026f2d59fe9af36c4fef59e" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.34.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "f1dec996504a4ee44d3c2dc835618255" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.33.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.33.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.34.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.34.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.34.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.34.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.34.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "ebf4a498aa1bee4ae00fe1b789bf399d" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.35.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "646a9c1688077435c7678d8c94aacb77" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "297ee54fd00b69ac980bbe7985f746cb" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.35.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "1a77849f0c8db1f6a50a6f7b74ef65bf" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.34.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.34.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.35.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.35.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.35.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.35.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.35.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "d2803a059de583da98f10e9c48b6d41b" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.36.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "95638138e6b16a2cfdff970d9a1c0b38" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "212d90b085d3b4c2de6839c4c5f879d4" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.36.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "1e504160b92a8042911217b442146d29" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.35.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.35.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.36.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.36.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.36.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.36.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.36.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "6fa62e07fbd881576c5e592233cd997a" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.37.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "a9aa5e1aabc6a88cc5a9716ec11d94ad" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.37.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "1e7e804e969cec477f6b8cddbff53d9c" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.37.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "16a8f715efeaf89f1fd6b6a3a53ee34d" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.36.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.36.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.37.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.37.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.37.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.37.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.37.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "17e6de9f28bafead14f8d309f2758db7" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.38.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "51c48964c096b2a5142540f6239ac442" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "5e04dfe1536b9306d4c19265f53bc92c" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.38.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "7c1df999d70678a8fbcc57ad894f34df" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.37.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.37.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.38.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.38.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.38.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.38.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.38.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "a5a917683bc1f2a4f25a256caaeda0d8" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.39.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "b847e9efbdb3fd055e75c00b6062933d" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.39.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "ed273ad0c37b53a66def59dd5ffbb413" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.39.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "271db90ff16b6c0001c40300f0f3c27a" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.38.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.38.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.39.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.39.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.39.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.39.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.39.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "b4b48f4a67631da13e7d9913ccbf8e57" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 32000, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "ffe14ce7238d1c15d0e0316e88c612d5" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "2fc2b2d45163d4a096fbf56ef6800082" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "e3ad64723b47d845fbf28ea2dc378c3c" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "f43f6fe7e1a2f864c66b9ac9953b28fa" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 30640128, "records": [ { "name": "model.layers.39.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.39.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.norm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.embed_tokens.q_scale", "shape": [ 32000, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 11806720 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 19998720 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 20008960 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 23552000 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30629888 } ], "md5sum": "f2f1150add2a02e5cbb59a466895c22c" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "5f4b2ee5532a60b08cdcb3689b9500c5" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "0ddd84005b5e67d6c8d2654bfd4061dc" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "62627ec0f96765fe84a178d6e7973a60" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 30302208, "records": [ { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 3932160 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 14417920 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 15728640 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 15738880 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 19281920 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 26359808 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 26370048 } ], "md5sum": "ddd2f368147b3afc476f2940ff15d02f" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "298faabcf41a744bed0eb34282a6b00b" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "2bd732342fd12ce3e22e44f0ec5bce0a" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "196f87dbcc211eeb794f33352ad38eb2" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "a79033faaba487cd64baedfa8af7eab9" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "1fffb50ebf139b413e13da4403d527ca" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "adbef0763ff628c4fd2260816a1a53b4" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "a5deca96abba3fff9ad2669782f46e57" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "fde4b177d87512a3b90fc2e9129028cf" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "dbc0d85c5b0a9628c9c40ff7e38dbdcf" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "89e2928fa40f3df5e62714b722b84823" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "deea085030856eb09b0241d43bc06292" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "bf694efeafbbf2430ae3e01a149182a8" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "6fad5426614492103f18b6a4cff2e220" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "75a8932a7ea2298224f73fac66c6178a" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "eb4d6b11f99663f774d5e5d3b8e9ba8e" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "0d95c52b78f7cab0e3f5c2131d4a501c" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "aed6abb6da31c7e680a9d7ef54de1336" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "57e2c3e997787901a8477c419aeebe7a" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "a807b1cfeb84581c9fa7d2130965d4d3" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "19cf6d21b18a7bf05581bb7059c65f6c" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "46329f2b0a84f8b2cb7cad419024942b" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "453e25bc0dc36c3f8b9d2c83a49e5771" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "0d15cee52b56c7bd9d4219a7df3e2175" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "e78b77442cbaa7e4f7ff94de785adff1" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 30302208, "records": [ { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 11796480 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 15728640 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 15738880 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 19281920 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 26359808 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 26370048 } ], "md5sum": "eb3ea292b4ace639acae93ae6908b6e2" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "1fae8dbed0cfdfc99992d04d087167d2" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "baa25fd0502f82e5d06dc157778d61cb" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "afec589ff4a45d7e2799f0f15599f70c" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "634597d62fc5bf00455c8c9f79fcaddd" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "31a0daeea10296512bf3a85e9ad1c77f" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "4d41c7af1d5c7bbbd11431d0ac4f51a5" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "5539674ad90a6990fff63e4461d0d71c" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "1a2892d18612d4dcda845d2ebfe5ef63" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "80938b10735c7c70a593d048825bc859" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "4260c46a3835cc034b2bd39a62864674" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "a59bce34939c9e33f5b9e90dd2edf58e" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "aedbdf9527e7281aa3d1f50918fe18b3" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "9aaecff93bdf671b5072d6e54bfa687e" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "2ef71b3f208bba737c414d997428c39c" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "ee4c8c1b6f391789de9801a64194c7a9" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "14e44217d0933ef98b307abf0d61c02e" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "de5ee1c98eb4392b284a27358372f27b" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "a180bbc52530ce2fe792260c63b9584a" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "2c1b0584c18dba963ff798980128a662" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "7661faffc73bc47ad4b77c2d9a029a45" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "6271d8f5101b449457a1d214183c7ef3" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "d059201d3774b50767e0acd28e97dae7" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "0639329558fc87f7e82c51695e275223" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "f6a18b009cc68a66699f33b5e8ab624f" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "ddbcf6a03618122243733ecff9d728a9" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "757d47b0761270a5e53b23f212cf24ea" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "c16004a5df2432bf537bb92db6ed5721" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "46461cbd69a80a79f871930a229ab852" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "4d89a006f67b89fbed7be6bfbd2fb537" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "02655bf829776502b6b182960c416a91" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 32923648, "records": [ { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 22437888 } ], "md5sum": "763cc4c2988aca420e4f6b5240179190" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "e10ebb58f890e2c6a5624a63d7a6f926" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 33208320, "records": [ { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 0 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 1310720 }, { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 1320960 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 29665280 } ], "md5sum": "3d0fe53301f32057784db230676ef0a2" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "426255d6b3cc3c1a3331b08e2eec8b21" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "f106a48fb445cc2a5af19caf7e7a50b6" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "577092ab80005ce532c945f2fa141639" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "65a429d49182bf1f5d873045496a244a" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 33458176, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 0 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 7077888 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 7088128 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 11020288 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 21506048 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22816768 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 22827008 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 26370048 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 33447936 } ], "md5sum": "e7da0b6b08e88ae84a5009f7ac60fa9c" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "e091d0d2cd8793cb2b22d18f59fb1d82" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "f7afd4072719344c88d176cf732a142b" }, { "dataPath": "params_shard_112.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.18.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "1c895822ab0cae5f055948fc5f57b8ac" }, { "dataPath": "params_shard_113.bin", "format": "raw-shard", "nbytes": 30302208, "records": [ { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 0 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 3932160 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 14417920 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 15728640 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 15738880 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 19281920 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 26359808 }, { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 26370048 } ], "md5sum": "eed2617585be7dbf434d456784f30018" }, { "dataPath": "params_shard_114.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "b47bf054505428f641f685dae0c4a85a" }, { "dataPath": "params_shard_115.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "47b4a03432ab4d1a2eafda37a5527b7e" }, { "dataPath": "params_shard_116.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.19.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "2f572accd07dd84967e9dfebe78c1381" }, { "dataPath": "params_shard_117.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "200b2e0f8f48bf5c63d46dbfe677fa61" }, { "dataPath": "params_shard_118.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "df068975a52045f8ad293de28051e2cb" }, { "dataPath": "params_shard_119.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "4ab6c5895b665da080f570f7b0670e4f" }, { "dataPath": "params_shard_120.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.20.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "c8c7a3d287119d093256b459faf308b7" }, { "dataPath": "params_shard_121.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "e4d340d441f26cf6d601c7d41a90b6d7" }, { "dataPath": "params_shard_122.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "abfd8d7c0b57901fce5ecd32b8264f4b" }, { "dataPath": "params_shard_123.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "7a2b4cbb5b22b41bc4675d30d0500e00" }, { "dataPath": "params_shard_124.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.21.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "3fadddd677a71f1ebcb918d6a9884b84" }, { "dataPath": "params_shard_125.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "bb6048787366bdeb3047953e9ae39174" }, { "dataPath": "params_shard_126.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "a1ef53faa3245297a9ef94e275c18bfc" }, { "dataPath": "params_shard_127.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "4513b42f8952498c3ceff0e7d62c1507" }, { "dataPath": "params_shard_128.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.22.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "4724cea0ca9dfbe9bf043ade5fe671f1" }, { "dataPath": "params_shard_129.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.22.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "73b75caa8764da5c834808fdef074451" }, { "dataPath": "params_shard_130.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "273828c6aa17d9b0cd2ecf5ca50dbddf" }, { "dataPath": "params_shard_131.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "ed320df2694dd5f931221306ac3db304" }, { "dataPath": "params_shard_132.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.23.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "113a1f5ba6adc10d5e79bca7d83ffa59" }, { "dataPath": "params_shard_133.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.23.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "39ff30bce6622e92a61f6c964d5ebd5d" }, { "dataPath": "params_shard_134.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "03318151106fe608cd7f364efc960770" }, { "dataPath": "params_shard_135.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "ff6afc03b6a0d7bc1edcbf2f858e8f58" }, { "dataPath": "params_shard_136.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.24.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "b2b63eaa58026cd0b6c945eefc3f2a8a" }, { "dataPath": "params_shard_137.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.24.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "35773305dbfcf9489da2ebcaf40db332" }, { "dataPath": "params_shard_138.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "bd44d46477a7b9d52d64bd3f3bfe771d" }, { "dataPath": "params_shard_139.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "25b4418b7f2894a0820db48aca272642" }, { "dataPath": "params_shard_140.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.25.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "c6d2bc66bac652aab5ce02e1d5566ce0" }, { "dataPath": "params_shard_141.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.25.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "3a6bb52653ea0a2492c6f69950fd0821" }, { "dataPath": "params_shard_142.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "eb484aeeeace917941d487572cd5dab1" }, { "dataPath": "params_shard_143.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "7408756aa9a2ea684454f87d46f87c92" }, { "dataPath": "params_shard_144.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.26.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "788c3eb782252b0e46aee95365b1e911" }, { "dataPath": "params_shard_145.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.26.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "8fd2f21180a95f7d9366c7daf7116d3f" }, { "dataPath": "params_shard_146.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "b6387815cf93d478953acc9382e84966" }, { "dataPath": "params_shard_147.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "55e795ebf94d02a6973ae2fe47c4400b" }, { "dataPath": "params_shard_148.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.27.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "de9d69983c86ccfe54534f7195bcb61f" }, { "dataPath": "params_shard_149.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.27.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "8ef50ac3aefa2a8a184a28dd1e2a8c75" }, { "dataPath": "params_shard_150.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "232582e12a05f77422e92a91a94ed8c9" }, { "dataPath": "params_shard_151.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "4d55a4447f197d81bd39914702c75669" }, { "dataPath": "params_shard_152.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.28.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "45a731e27a15fbb80801b5c91ffb6e58" }, { "dataPath": "params_shard_153.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.28.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "8bf77563568efd0c0bade7253fb87374" }, { "dataPath": "params_shard_154.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "166a944e0d658171c9660aeacd6fcc2c" }, { "dataPath": "params_shard_155.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "f37f1be58d751f97bfc0929479e3ea3f" }, { "dataPath": "params_shard_156.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.29.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "ae7e17f90e45866d28ef8e85026ffa15" }, { "dataPath": "params_shard_157.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.29.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "4423fc33bb946c341e312f1d3ee5281b" }, { "dataPath": "params_shard_158.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "b3940e5282648f4fcbdd457f67e89fea" }, { "dataPath": "params_shard_159.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.30.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "dfeed23e8a98c386fea7a7a854a9591b" }, { "dataPath": "params_shard_160.bin", "format": "raw-shard", "nbytes": 33292288, "records": [ { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 11796480 }, { "name": "model.layers.30.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 18874368 }, { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 22806528 } ], "md5sum": "9fdf7b545efa6f152374462dbbe86fdd" }, { "dataPath": "params_shard_161.bin", "format": "raw-shard", "nbytes": 1310720, "records": [ { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 0 } ], "md5sum": "c056d17232a56cea56dd6be8c5f05894" } ] }