{ "metadata": { "ParamSize": 225, "ParamBytes": 618916608.0, "BitsPerParam": 4.500963437769367 }, "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": "0de507cb080a53c33b5a126bb17c61cc" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 31826304, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 32003, 64 ], "dtype": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 28148096 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28868992 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 31498624 } ], "md5sum": "90ae815d41be3acc088cdb349fb5d5d5" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 21102592 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 21823488 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 26877952 } ], "md5sum": "9b81d5d065ff7b48050509af5f4aa54b" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "8cbe73c19589e36719d4360134339be3" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "6b1ea62b1186d0c4531403664c2912a0" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "e6c026425df30f6b05ebb01c04e203d5" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "77a049a0ee44a399754a4ebc6aae0f8b" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "b3c6189f75b9cec5695688cfa73430bf" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "001cda9551c653b441c2e268940bb0ab" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "95835c49d5c079d807fb4e16621df1b9" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "82ff0ae7858f5d42caf4c648e46cfcef" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "bec762f6806da53a5389b0f9dd08b5d2" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "9750d3b12b538a85dc1ccf02dda5627d" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "eaaf438c99ccb5cf709e14dd0f40fede" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "abd71f92cf81b8f5389ef446096afa0c" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "30bc69f1e579f9ced49dfc26c4d2728d" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "921ba5bf602be1a6b84073eb21601d94" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "e4edc4ca163d8dc8117d73572b1f388e" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "fb6207b18ec554b58a333da532560738" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "b6e0e891b172794025b4290aa581fadb" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "a909f06208d20de0d403b8b760a2249f" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 24518656 } ], "md5sum": "bebec58c4a24bca4f79e25ac51e105b1" }, { "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": "c885b6dd537a7e207efb4c16eaaf6e09" }, { "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": "float16", "format": "f32-to-bf16", "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": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 18743296 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 19468288 }, { "name": "model.norm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 19472384 }, { "name": "lm_head.q_scale", "shape": [ 32003, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096384, "byteOffset": 19476480 } ], "md5sum": "41453a71e8f2de930c0a3c00c930f4f8" } ] }