{ "metadata": { "ParamSize": 225, "ParamBytes": 687848960.0, "BitsPerParam": 5.002261984328079 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 32771072, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 32003, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 32771072, "byteOffset": 0 } ], "md5sum": "5d04d3daaea233773d55c738ca893695" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 31826304, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 32003, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096384, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 4096384 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 6717824 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7045504 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 9142656 }, { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 9404800 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 20939136 }, { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 22380928 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 28148096 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 28868992 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 28873088 }, { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 28877184 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 31498624 } ], "md5sum": "680c11ff1744d5bfa3cab96425d32284" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 27140096, "records": [ { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 2097152 }, { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 2359296 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 13893632 }, { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 15335424 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 21102592 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 21823488 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 21827584 }, { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 21831680 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 24453120 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 24780800 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 26877952 } ], "md5sum": "8c28be42014a0308dacc2f2ecdf10aa3" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 12976128 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19468288 }, { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19472384 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 22093824 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22421504 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "a2fe11ae5b5c809f09adfcb9f58422be" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 12976128 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19468288 }, { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19472384 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 22093824 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22421504 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "4cddfca8f748085f6fc7deeabda1ce27" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 12976128 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19468288 }, { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19472384 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 22093824 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22421504 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "e120e89f444fd0c436baf3068f479762" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 12976128 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19468288 }, { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19472384 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 22093824 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22421504 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "5a8837813b094d491b5a14205460886e" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 12976128 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19468288 }, { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19472384 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 22093824 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22421504 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "4de03c54f7105a9e8fb0da0f275f40a3" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 12976128 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19468288 }, { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19472384 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 22093824 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22421504 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "ab488c2050fdfe91cd78eb473120e649" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 12976128 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19468288 }, { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19472384 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 22093824 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22421504 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "ff443a9a0d0db2a220f332b8c6f4fa6a" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 12976128 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19468288 }, { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19472384 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 22093824 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22421504 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "b3e98ffeb6a1180a5ec8ab7fa89b15f1" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 12976128 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19468288 }, { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19472384 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 22093824 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22421504 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "466137e0af99496138348a221df36f30" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 12976128 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19468288 }, { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19472384 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 22093824 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22421504 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "8097c1ddc6ac569ae089e4e1735709d1" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 12976128 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19468288 }, { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19472384 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 22093824 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22421504 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "cb4d8ac3523d4a78c40f6e05e6a75a3f" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 12976128 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19468288 }, { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19472384 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 22093824 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22421504 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "97fec4eb81b0c8ba326d6bd7c2d0d01e" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 12976128 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19468288 }, { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19472384 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 22093824 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22421504 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "5942e747ef08c2f1f6aee113d2fdb843" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 12976128 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19468288 }, { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19472384 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 22093824 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22421504 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "fa1b0776d20499dcf35ca524e65addcd" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 12976128 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19468288 }, { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19472384 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 22093824 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22421504 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "4eec190a3558aad16647bedadf63ad68" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 12976128 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19468288 }, { "name": "model.layers.18.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19472384 }, { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 22093824 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22421504 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "d34c9a3f1d0cb3900907226eca95af8d" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 12976128 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19468288 }, { "name": "model.layers.19.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19472384 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 22093824 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22421504 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "829dd454ac1242bc973177bc2248a1f8" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 12976128 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19468288 }, { "name": "model.layers.20.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19472384 }, { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 22093824 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22421504 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "4b6e5593f9e640846c38651fd89f279c" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 12976128 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19468288 }, { "name": "model.layers.21.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19472384 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 22093824 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22421504 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "a74f48bc17bc757ea9d4c75002229241" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 32771072, "records": [ { "name": "lm_head.q_weight", "shape": [ 32003, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 32771072, "byteOffset": 0 } ], "md5sum": "9a1c53a4e8ad27cf8d5fb1fcc5c333c2" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 23572864, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 12976128 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19468288 }, { "name": "model.norm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19472384 }, { "name": "lm_head.q_scale", "shape": [ 32003, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096384, "byteOffset": 19476480 } ], "md5sum": "cc2bb39dd7372753ef316485aa555550" } ] }