{ "metadata": { "ParamSize": 311, "ParamBytes": 651700992.0, "BitsPerParam": 2.9337927755969315 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 94808064, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 151936, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 94808064, "byteOffset": 0 } ], "md5sum": "aa4184830ee11e6143b6c74424a418ae" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 29461248, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 151936, 13 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3950336, "byteOffset": 0 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 3950336 }, { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 900, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5529600, "byteOffset": 3953408 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 75, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 230400, "byteOffset": 9483008 }, { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 156, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 9713408 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 13, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 465920, "byteOffset": 20895488 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 21361408 }, { "name": "model.layers.0.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 21364480 }, { "name": "model.layers.0.self_attn.c_attn.q_weight", "shape": [ 156, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 21368576 }, { "name": "model.layers.0.self_attn.c_attn.q_scale", "shape": [ 13, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 53248, "byteOffset": 22646528 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 156, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 22699776 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 13, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 39936, "byteOffset": 23658240 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23698176 }, { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 900, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5529600, "byteOffset": 23701248 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 75, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 230400, "byteOffset": 29230848 } ], "md5sum": "1ab799819153433c013e927809e49ef2" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 32734208, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 156, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 0 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 13, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 465920, "byteOffset": 11182080 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 11648000 }, { "name": "model.layers.1.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 11651072 }, { "name": "model.layers.1.self_attn.c_attn.q_weight", "shape": [ 156, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 11655168 }, { "name": "model.layers.1.self_attn.c_attn.q_scale", "shape": [ 13, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 53248, "byteOffset": 12933120 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 156, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 12986368 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 13, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 39936, "byteOffset": 13944832 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 13984768 }, { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 900, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5529600, "byteOffset": 13987840 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 75, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 230400, "byteOffset": 19517440 }, { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 156, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 19747840 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 13, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 465920, "byteOffset": 30929920 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 31395840 }, { "name": "model.layers.10.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31398912 }, { "name": "model.layers.10.self_attn.c_attn.q_weight", "shape": [ 156, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 31403008 }, { "name": "model.layers.10.self_attn.c_attn.q_scale", "shape": [ 13, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 53248, "byteOffset": 32680960 } ], "md5sum": "7d00c8efad3c5ac104168e6b5a183882" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 26509312, "records": [ { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 156, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 0 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 13, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 39936, "byteOffset": 958464 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 998400 }, { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 900, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5529600, "byteOffset": 1001472 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 75, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 230400, "byteOffset": 6531072 }, { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 156, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 6761472 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 13, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 465920, "byteOffset": 17943552 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 18409472 }, { "name": "model.layers.11.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18412544 }, { "name": "model.layers.11.self_attn.c_attn.q_weight", "shape": [ 156, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 18416640 }, { "name": "model.layers.11.self_attn.c_attn.q_scale", "shape": [ 13, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 53248, "byteOffset": 19694592 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 156, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 19747840 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 13, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 39936, "byteOffset": 20706304 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 20746240 }, { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 900, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5529600, "byteOffset": 20749312 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 75, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 230400, "byteOffset": 26278912 } ], "md5sum": "a6cbec84eaeec9534a6462f6d5854738" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 32734208, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 156, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 0 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 13, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 465920, "byteOffset": 11182080 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 11648000 }, { "name": "model.layers.12.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 11651072 }, { "name": "model.layers.12.self_attn.c_attn.q_weight", "shape": [ 156, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 11655168 }, { "name": "model.layers.12.self_attn.c_attn.q_scale", "shape": [ 13, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 53248, "byteOffset": 12933120 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 156, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 12986368 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 13, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 39936, "byteOffset": 13944832 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 13984768 }, { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 900, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5529600, "byteOffset": 13987840 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 75, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 230400, "byteOffset": 19517440 }, { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 156, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 19747840 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 13, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 465920, "byteOffset": 30929920 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 31395840 }, { "name": "model.layers.13.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31398912 }, { "name": "model.layers.13.self_attn.c_attn.q_weight", "shape": [ 156, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 31403008 }, { "name": "model.layers.13.self_attn.c_attn.q_scale", "shape": [ 13, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 53248, "byteOffset": 32680960 } ], "md5sum": "2cb1ee9d3b45774badefcdeb2892ccac" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 26509312, "records": [ { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 156, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 0 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 13, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 39936, "byteOffset": 958464 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 998400 }, { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 900, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5529600, "byteOffset": 1001472 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 75, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 230400, "byteOffset": 6531072 }, { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 156, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 6761472 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 13, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 465920, "byteOffset": 17943552 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 18409472 }, { "name": "model.layers.14.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18412544 }, { "name": "model.layers.14.self_attn.c_attn.q_weight", "shape": [ 156, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 18416640 }, { "name": "model.layers.14.self_attn.c_attn.q_scale", "shape": [ 13, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 53248, "byteOffset": 19694592 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 156, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 19747840 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 13, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 39936, "byteOffset": 20706304 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 20746240 }, { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 900, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5529600, "byteOffset": 20749312 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 75, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 230400, "byteOffset": 26278912 } ], "md5sum": "5cd3d72135b6754e5d7bfb03d6a9aeb3" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 32734208, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 156, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 0 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 13, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 465920, "byteOffset": 11182080 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 11648000 }, { "name": "model.layers.15.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 11651072 }, { "name": "model.layers.15.self_attn.c_attn.q_weight", "shape": [ 156, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 11655168 }, { "name": "model.layers.15.self_attn.c_attn.q_scale", "shape": [ 13, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 53248, "byteOffset": 12933120 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 156, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 12986368 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 13, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 39936, "byteOffset": 13944832 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 13984768 }, { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 900, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5529600, "byteOffset": 13987840 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 75, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 230400, "byteOffset": 19517440 }, { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 156, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 19747840 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 13, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 465920, "byteOffset": 30929920 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 31395840 }, { "name": "model.layers.16.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31398912 }, { "name": "model.layers.16.self_attn.c_attn.q_weight", "shape": [ 156, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 31403008 }, { "name": "model.layers.16.self_attn.c_attn.q_scale", "shape": [ 13, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 53248, "byteOffset": 32680960 } ], "md5sum": "aef0eedf1ce08975507ffe00fd47f282" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 26509312, "records": [ { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 156, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 0 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 13, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 39936, "byteOffset": 958464 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 998400 }, { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 900, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5529600, "byteOffset": 1001472 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 75, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 230400, "byteOffset": 6531072 }, { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 156, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 6761472 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 13, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 465920, "byteOffset": 17943552 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 18409472 }, { "name": "model.layers.17.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18412544 }, { "name": "model.layers.17.self_attn.c_attn.q_weight", "shape": [ 156, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 18416640 }, { "name": "model.layers.17.self_attn.c_attn.q_scale", "shape": [ 13, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 53248, "byteOffset": 19694592 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 156, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 19747840 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 13, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 39936, "byteOffset": 20706304 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 20746240 }, { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 900, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5529600, "byteOffset": 20749312 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 75, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 230400, "byteOffset": 26278912 } ], "md5sum": "fa2732e9d60a6e384b821e3cd9ac4825" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 32734208, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 156, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 0 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 13, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 465920, "byteOffset": 11182080 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 11648000 }, { "name": "model.layers.18.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 11651072 }, { "name": "model.layers.18.self_attn.c_attn.q_weight", "shape": [ 156, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 11655168 }, { "name": "model.layers.18.self_attn.c_attn.q_scale", "shape": [ 13, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 53248, "byteOffset": 12933120 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 156, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 12986368 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 13, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 39936, "byteOffset": 13944832 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 13984768 }, { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 900, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5529600, "byteOffset": 13987840 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 75, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 230400, "byteOffset": 19517440 }, { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 156, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 19747840 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 13, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 465920, "byteOffset": 30929920 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 31395840 }, { "name": "model.layers.19.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31398912 }, { "name": "model.layers.19.self_attn.c_attn.q_weight", "shape": [ 156, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 31403008 }, { "name": "model.layers.19.self_attn.c_attn.q_scale", "shape": [ 13, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 53248, "byteOffset": 32680960 } ], "md5sum": "2dd5244021f7d8c5f82760381c1f6d8f" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 26509312, "records": [ { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 156, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 0 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 13, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 39936, "byteOffset": 958464 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 998400 }, { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 900, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5529600, "byteOffset": 1001472 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 75, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 230400, "byteOffset": 6531072 }, { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 156, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 6761472 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 13, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 465920, "byteOffset": 17943552 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 18409472 }, { "name": "model.layers.2.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18412544 }, { "name": "model.layers.2.self_attn.c_attn.q_weight", "shape": [ 156, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 18416640 }, { "name": "model.layers.2.self_attn.c_attn.q_scale", "shape": [ 13, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 53248, "byteOffset": 19694592 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 156, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 19747840 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 13, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 39936, "byteOffset": 20706304 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 20746240 }, { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 900, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5529600, "byteOffset": 20749312 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 75, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 230400, "byteOffset": 26278912 } ], "md5sum": "ba1b4e880a3b19e9e79fd08c38581c34" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 32734208, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 156, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 0 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 13, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 465920, "byteOffset": 11182080 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 11648000 }, { "name": "model.layers.20.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 11651072 }, { "name": "model.layers.20.self_attn.c_attn.q_weight", "shape": [ 156, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 11655168 }, { "name": "model.layers.20.self_attn.c_attn.q_scale", "shape": [ 13, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 53248, "byteOffset": 12933120 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 156, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 12986368 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 13, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 39936, "byteOffset": 13944832 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 13984768 }, { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 900, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5529600, "byteOffset": 13987840 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 75, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 230400, "byteOffset": 19517440 }, { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 156, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 19747840 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 13, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 465920, "byteOffset": 30929920 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 31395840 }, { "name": "model.layers.21.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31398912 }, { "name": "model.layers.21.self_attn.c_attn.q_weight", "shape": [ 156, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 31403008 }, { "name": "model.layers.21.self_attn.c_attn.q_scale", "shape": [ 13, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 53248, "byteOffset": 32680960 } ], "md5sum": "5e7b379a5810cf63e209297939dfcba5" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 26509312, "records": [ { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 156, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 0 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 13, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 39936, "byteOffset": 958464 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 998400 }, { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 900, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5529600, "byteOffset": 1001472 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 75, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 230400, "byteOffset": 6531072 }, { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 156, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 6761472 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 13, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 465920, "byteOffset": 17943552 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 18409472 }, { "name": "model.layers.22.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18412544 }, { "name": "model.layers.22.self_attn.c_attn.q_weight", "shape": [ 156, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 18416640 }, { "name": "model.layers.22.self_attn.c_attn.q_scale", "shape": [ 13, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 53248, "byteOffset": 19694592 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 156, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 19747840 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 13, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 39936, "byteOffset": 20706304 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 20746240 }, { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 900, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5529600, "byteOffset": 20749312 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 75, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 230400, "byteOffset": 26278912 } ], "md5sum": "dd55a417950d3efc7347c8f8b8f03b13" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 32734208, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 156, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 0 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 13, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 465920, "byteOffset": 11182080 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 11648000 }, { "name": "model.layers.23.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 11651072 }, { "name": "model.layers.23.self_attn.c_attn.q_weight", "shape": [ 156, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 11655168 }, { "name": "model.layers.23.self_attn.c_attn.q_scale", "shape": [ 13, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 53248, "byteOffset": 12933120 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 156, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 12986368 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 13, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 39936, "byteOffset": 13944832 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 13984768 }, { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 900, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5529600, "byteOffset": 13987840 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 75, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 230400, "byteOffset": 19517440 }, { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 156, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 19747840 }, { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 13, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 465920, "byteOffset": 30929920 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 31395840 }, { "name": "model.layers.24.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31398912 }, { "name": "model.layers.24.self_attn.c_attn.q_weight", "shape": [ 156, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 31403008 }, { "name": "model.layers.24.self_attn.c_attn.q_scale", "shape": [ 13, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 53248, "byteOffset": 32680960 } ], "md5sum": "d388ebff2bac3b9c723915945cb742f7" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 26509312, "records": [ { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 156, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 0 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 13, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 39936, "byteOffset": 958464 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 998400 }, { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 900, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5529600, "byteOffset": 1001472 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 75, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 230400, "byteOffset": 6531072 }, { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 156, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 6761472 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 13, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 465920, "byteOffset": 17943552 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 18409472 }, { "name": "model.layers.25.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18412544 }, { "name": "model.layers.25.self_attn.c_attn.q_weight", "shape": [ 156, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 18416640 }, { "name": "model.layers.25.self_attn.c_attn.q_scale", "shape": [ 13, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 53248, "byteOffset": 19694592 }, { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 156, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 19747840 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 13, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 39936, "byteOffset": 20706304 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 20746240 }, { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 900, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5529600, "byteOffset": 20749312 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 75, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 230400, "byteOffset": 26278912 } ], "md5sum": "09b410c7838ac40a4bf30988fa939a5a" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 32734208, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 156, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 0 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 13, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 465920, "byteOffset": 11182080 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 11648000 }, { "name": "model.layers.26.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 11651072 }, { "name": "model.layers.26.self_attn.c_attn.q_weight", "shape": [ 156, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 11655168 }, { "name": "model.layers.26.self_attn.c_attn.q_scale", "shape": [ 13, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 53248, "byteOffset": 12933120 }, { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 156, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 12986368 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 13, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 39936, "byteOffset": 13944832 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 13984768 }, { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 900, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5529600, "byteOffset": 13987840 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 75, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 230400, "byteOffset": 19517440 }, { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 156, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 19747840 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 13, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 465920, "byteOffset": 30929920 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 31395840 }, { "name": "model.layers.27.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31398912 }, { "name": "model.layers.27.self_attn.c_attn.q_weight", "shape": [ 156, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 31403008 }, { "name": "model.layers.27.self_attn.c_attn.q_scale", "shape": [ 13, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 53248, "byteOffset": 32680960 } ], "md5sum": "e7a463ec7e325b855553890b5f565e71" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 26509312, "records": [ { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 156, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 0 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 13, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 39936, "byteOffset": 958464 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 998400 }, { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 900, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5529600, "byteOffset": 1001472 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 75, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 230400, "byteOffset": 6531072 }, { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 156, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 6761472 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 13, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 465920, "byteOffset": 17943552 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 18409472 }, { "name": "model.layers.3.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18412544 }, { "name": "model.layers.3.self_attn.c_attn.q_weight", "shape": [ 156, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 18416640 }, { "name": "model.layers.3.self_attn.c_attn.q_scale", "shape": [ 13, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 53248, "byteOffset": 19694592 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 156, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 19747840 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 13, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 39936, "byteOffset": 20706304 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 20746240 }, { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 900, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5529600, "byteOffset": 20749312 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 75, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 230400, "byteOffset": 26278912 } ], "md5sum": "5c8a7166f4e25b4a1bdd1b90c3782c6e" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 32734208, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 156, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 0 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 13, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 465920, "byteOffset": 11182080 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 11648000 }, { "name": "model.layers.4.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 11651072 }, { "name": "model.layers.4.self_attn.c_attn.q_weight", "shape": [ 156, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 11655168 }, { "name": "model.layers.4.self_attn.c_attn.q_scale", "shape": [ 13, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 53248, "byteOffset": 12933120 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 156, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 12986368 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 13, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 39936, "byteOffset": 13944832 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 13984768 }, { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 900, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5529600, "byteOffset": 13987840 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 75, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 230400, "byteOffset": 19517440 }, { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 156, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 19747840 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 13, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 465920, "byteOffset": 30929920 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 31395840 }, { "name": "model.layers.5.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31398912 }, { "name": "model.layers.5.self_attn.c_attn.q_weight", "shape": [ 156, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 31403008 }, { "name": "model.layers.5.self_attn.c_attn.q_scale", "shape": [ 13, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 53248, "byteOffset": 32680960 } ], "md5sum": "55960906c6de6b4af44db3da1a7a9f7f" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 26509312, "records": [ { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 156, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 0 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 13, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 39936, "byteOffset": 958464 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 998400 }, { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 900, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5529600, "byteOffset": 1001472 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 75, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 230400, "byteOffset": 6531072 }, { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 156, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 6761472 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 13, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 465920, "byteOffset": 17943552 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 18409472 }, { "name": "model.layers.6.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18412544 }, { "name": "model.layers.6.self_attn.c_attn.q_weight", "shape": [ 156, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 18416640 }, { "name": "model.layers.6.self_attn.c_attn.q_scale", "shape": [ 13, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 53248, "byteOffset": 19694592 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 156, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 19747840 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 13, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 39936, "byteOffset": 20706304 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 20746240 }, { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 900, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5529600, "byteOffset": 20749312 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 75, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 230400, "byteOffset": 26278912 } ], "md5sum": "cbaa2e5eddd893011c4f864d30192e19" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 32734208, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 156, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 0 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 13, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 465920, "byteOffset": 11182080 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 11648000 }, { "name": "model.layers.7.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 11651072 }, { "name": "model.layers.7.self_attn.c_attn.q_weight", "shape": [ 156, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 11655168 }, { "name": "model.layers.7.self_attn.c_attn.q_scale", "shape": [ 13, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 53248, "byteOffset": 12933120 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 156, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 12986368 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 13, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 39936, "byteOffset": 13944832 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 13984768 }, { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 900, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5529600, "byteOffset": 13987840 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 75, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 230400, "byteOffset": 19517440 }, { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 156, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 19747840 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 13, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 465920, "byteOffset": 30929920 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 31395840 }, { "name": "model.layers.8.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 31398912 }, { "name": "model.layers.8.self_attn.c_attn.q_weight", "shape": [ 156, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 31403008 }, { "name": "model.layers.8.self_attn.c_attn.q_scale", "shape": [ 13, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 53248, "byteOffset": 32680960 } ], "md5sum": "d50cd884cfa4e7a5faf450739fbfce50" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 20749312, "records": [ { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 156, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 0 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 13, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 39936, "byteOffset": 958464 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 998400 }, { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 900, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5529600, "byteOffset": 1001472 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 75, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 230400, "byteOffset": 6531072 }, { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 156, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 6761472 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 13, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 465920, "byteOffset": 17943552 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 18409472 }, { "name": "model.layers.9.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18412544 }, { "name": "model.layers.9.self_attn.c_attn.q_weight", "shape": [ 156, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 18416640 }, { "name": "model.layers.9.self_attn.c_attn.q_scale", "shape": [ 13, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 53248, "byteOffset": 19694592 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 156, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 19747840 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 13, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 39936, "byteOffset": 20706304 }, { "name": "model.norm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 20746240 } ], "md5sum": "406b08682765bbd901d278508f933ca5" } ] }