{ "metadata": { "ParamSize": 225, "ParamBytes": 687841280.0, "BitsPerParam": 5.0022620095953885 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 32768000, "records": [ { "name": "lm_head.q_weight", "shape": [ 32000, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 32768000, "byteOffset": 0 } ], "md5sum": "48bd05d608a5b9aabeae1409992822de" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 32768000, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 32000, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 32768000, "byteOffset": 0 } ], "md5sum": "1d95f3fa141e122e3a53b4188116de99" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 32976896, "records": [ { "name": "lm_head.q_scale", "shape": [ 32000, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096000, "byteOffset": 0 }, { "name": "model.embed_tokens.q_scale", "shape": [ 32000, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096000, "byteOffset": 4096000 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 8192000 }, { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 8196096 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 13963264 }, { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 14684160 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 26218496 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 27660288 }, { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27664384 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 30285824 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 30613504 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 32710656 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 32972800 } ], "md5sum": "88038189fcd5f275100a16878c20af0c" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 31268864, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 0 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 5767168 }, { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 6488064 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1441792, "byteOffset": 18022400 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19468288 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 22089728 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22417408 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 24514560 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 24776704 }, { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 24780800 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 30547968 } ], "md5sum": "2c4f8dd17c82308775785630bc23aba8" }, { "dataPath": "params_shard_4.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.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "0c88c94644c542d322ac0fd2c6ab1110" }, { "dataPath": "params_shard_5.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.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "27d9603d57dbc540b3ca9a6b768804c3" }, { "dataPath": "params_shard_6.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.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "e9b24f41c420a4c080376bff566ea1cd" }, { "dataPath": "params_shard_7.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.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "3094c487a92e3d3471e14deaaa28bf94" }, { "dataPath": "params_shard_8.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.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "6cc4bc66e0cadadf2519f84cf1a611cc" }, { "dataPath": "params_shard_9.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.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "31625dc2bcbca8c9c3142945f2a02d5e" }, { "dataPath": "params_shard_10.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.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "63cb05c81cc576442a9bfe941c41c055" }, { "dataPath": "params_shard_11.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.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "8e60220ace56fcc551256f8faa4356e5" }, { "dataPath": "params_shard_12.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.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.18.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "73e627d55fc9e9861d0e6cdc51faecf9" }, { "dataPath": "params_shard_13.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.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.19.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "ea202a7b92109b0db3a53bc44b0cdb73" }, { "dataPath": "params_shard_14.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.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "2c40dd21db70c939738245eede3b6e9e" }, { "dataPath": "params_shard_15.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.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.20.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "d6214637046a1a2e764877e04b266509" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 24780800, "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.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.21.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "18f8ed7991838dc014e08b002d3409bc" }, { "dataPath": "params_shard_17.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.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "f8d84c93c9a12d4190a2abfb09b31b38" }, { "dataPath": "params_shard_18.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.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "93165d4d1a617bd8a938792532e882b1" }, { "dataPath": "params_shard_19.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.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "f31747b3d2176bdc5741f3ad421cab44" }, { "dataPath": "params_shard_20.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.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "b029a8b0e8acfccea962f17192ec0737" }, { "dataPath": "params_shard_21.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.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "a5a6db7dca1275fb87d705ef71186149" }, { "dataPath": "params_shard_22.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.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "bfloat16", "format": "raw", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "64989de65907d89175ea26e6be5e3290" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 18292736, "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.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.norm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 18288640 } ], "md5sum": "9bb01cc092994dd52209533e0ca5c058" } ] }