{ "metadata": { "ParamSize": 311, "ParamBytes": 1670769664.0, "BitsPerParam": 7.5213817841322435 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 466747392, "records": [ { "name": "model.embed_tokens.weight", "shape": [ 151936, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 466747392, "byteOffset": 0 } ], "md5sum": "fecf67195ad7c035b39a5b4b1c77facc" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 29431808, "records": [ { "name": "model.layers.0.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 196608, "byteOffset": 1572864 }, { "name": "model.layers.0.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 1769472 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 1773568 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 147456, "byteOffset": 2953216 }, { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 3100672 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1720320, "byteOffset": 16863232 }, { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18583552 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 860160, "byteOffset": 25464832 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 26324992 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 26328064 }, { "name": "model.layers.1.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 26331136 }, { "name": "model.layers.1.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 196608, "byteOffset": 27904000 }, { "name": "model.layers.1.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 28100608 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 28104704 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 147456, "byteOffset": 29284352 } ], "md5sum": "41e8a76411959d7b2196c22931aba9a5" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 15482880 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 860160, "byteOffset": 22364160 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23224320 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23227392 }, { "name": "model.layers.2.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23230464 }, { "name": "model.layers.2.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 196608, "byteOffset": 24803328 }, { "name": "model.layers.2.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 24999936 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 25004032 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 147456, "byteOffset": 26183680 } ], "md5sum": "7e2bd90d01fe85760f54324dec4e7098" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 15482880 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 860160, "byteOffset": 22364160 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23224320 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23227392 }, { "name": "model.layers.3.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23230464 }, { "name": "model.layers.3.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 196608, "byteOffset": 24803328 }, { "name": "model.layers.3.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 24999936 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 25004032 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 147456, "byteOffset": 26183680 } ], "md5sum": "e858217415e3836b27cd58a97939845a" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 15482880 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 860160, "byteOffset": 22364160 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23224320 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23227392 }, { "name": "model.layers.4.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23230464 }, { "name": "model.layers.4.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 196608, "byteOffset": 24803328 }, { "name": "model.layers.4.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 24999936 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 25004032 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 147456, "byteOffset": 26183680 } ], "md5sum": "cd6cbc8cfdfeafc81f63726fcc392c3d" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 15482880 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 860160, "byteOffset": 22364160 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23224320 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23227392 }, { "name": "model.layers.5.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23230464 }, { "name": "model.layers.5.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 196608, "byteOffset": 24803328 }, { "name": "model.layers.5.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 24999936 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 25004032 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 147456, "byteOffset": 26183680 } ], "md5sum": "999da6ee917622997753e525ed1a89c0" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 15482880 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 860160, "byteOffset": 22364160 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23224320 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23227392 }, { "name": "model.layers.6.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23230464 }, { "name": "model.layers.6.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 196608, "byteOffset": 24803328 }, { "name": "model.layers.6.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 24999936 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 25004032 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 147456, "byteOffset": 26183680 } ], "md5sum": "eff1a12e8aeb905c5cc647ebaaff900b" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 15482880 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 860160, "byteOffset": 22364160 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23224320 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23227392 }, { "name": "model.layers.7.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23230464 }, { "name": "model.layers.7.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 196608, "byteOffset": 24803328 }, { "name": "model.layers.7.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 24999936 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 25004032 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 147456, "byteOffset": 26183680 } ], "md5sum": "9a14099341c2baf7c0558abddeea08ba" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 15482880 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 860160, "byteOffset": 22364160 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23224320 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23227392 }, { "name": "model.layers.8.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23230464 }, { "name": "model.layers.8.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 196608, "byteOffset": 24803328 }, { "name": "model.layers.8.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 24999936 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 25004032 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 147456, "byteOffset": 26183680 } ], "md5sum": "0dd0829243954dabef2817538bbaf9a5" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 15482880 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 860160, "byteOffset": 22364160 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23224320 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23227392 }, { "name": "model.layers.9.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23230464 }, { "name": "model.layers.9.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 196608, "byteOffset": 24803328 }, { "name": "model.layers.9.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 24999936 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 25004032 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 147456, "byteOffset": 26183680 } ], "md5sum": "555847fe05ccec397dbb1f60d095f1dc" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 15482880 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 860160, "byteOffset": 22364160 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23224320 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23227392 }, { "name": "model.layers.10.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23230464 }, { "name": "model.layers.10.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 196608, "byteOffset": 24803328 }, { "name": "model.layers.10.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 24999936 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 25004032 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 147456, "byteOffset": 26183680 } ], "md5sum": "17693da31b8da9235cac164ad210adba" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 15482880 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 860160, "byteOffset": 22364160 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23224320 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23227392 }, { "name": "model.layers.11.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23230464 }, { "name": "model.layers.11.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 196608, "byteOffset": 24803328 }, { "name": "model.layers.11.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 24999936 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 25004032 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 147456, "byteOffset": 26183680 } ], "md5sum": "5e5762c181adacff5787437bbeed8be4" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 15482880 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 860160, "byteOffset": 22364160 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23224320 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23227392 }, { "name": "model.layers.12.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23230464 }, { "name": "model.layers.12.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 196608, "byteOffset": 24803328 }, { "name": "model.layers.12.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 24999936 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 25004032 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 147456, "byteOffset": 26183680 } ], "md5sum": "b10becb16302c0b4bb71e217e9e29ce3" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 15482880 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 860160, "byteOffset": 22364160 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23224320 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23227392 }, { "name": "model.layers.13.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23230464 }, { "name": "model.layers.13.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 196608, "byteOffset": 24803328 }, { "name": "model.layers.13.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 24999936 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 25004032 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 147456, "byteOffset": 26183680 } ], "md5sum": "7a707eb54de20dc6eff3a062c43b3b98" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 15482880 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 860160, "byteOffset": 22364160 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23224320 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23227392 }, { "name": "model.layers.14.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23230464 }, { "name": "model.layers.14.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 196608, "byteOffset": 24803328 }, { "name": "model.layers.14.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 24999936 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 25004032 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 147456, "byteOffset": 26183680 } ], "md5sum": "da841282f75386f7f7aab1aca8ca791c" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 15482880 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 860160, "byteOffset": 22364160 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23224320 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23227392 }, { "name": "model.layers.15.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23230464 }, { "name": "model.layers.15.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 196608, "byteOffset": 24803328 }, { "name": "model.layers.15.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 24999936 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 25004032 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 147456, "byteOffset": 26183680 } ], "md5sum": "331bc3e0c825f8b5aa2b4bfb4e080b81" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 15482880 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 860160, "byteOffset": 22364160 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23224320 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23227392 }, { "name": "model.layers.16.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23230464 }, { "name": "model.layers.16.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 196608, "byteOffset": 24803328 }, { "name": "model.layers.16.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 24999936 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 25004032 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 147456, "byteOffset": 26183680 } ], "md5sum": "dfa1104ff532e4f1685cbd34ba8bb987" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 15482880 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 860160, "byteOffset": 22364160 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23224320 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23227392 }, { "name": "model.layers.17.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23230464 }, { "name": "model.layers.17.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 196608, "byteOffset": 24803328 }, { "name": "model.layers.17.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 24999936 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 25004032 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 147456, "byteOffset": 26183680 } ], "md5sum": "d85d924e2d55642861b47c1a9e2a76a8" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 15482880 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 860160, "byteOffset": 22364160 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23224320 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23227392 }, { "name": "model.layers.18.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23230464 }, { "name": "model.layers.18.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 196608, "byteOffset": 24803328 }, { "name": "model.layers.18.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 24999936 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 25004032 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 147456, "byteOffset": 26183680 } ], "md5sum": "ef9f81b687f953d110c8f75f6d43a875" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 15482880 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 860160, "byteOffset": 22364160 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23224320 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23227392 }, { "name": "model.layers.19.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23230464 }, { "name": "model.layers.19.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 196608, "byteOffset": 24803328 }, { "name": "model.layers.19.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 24999936 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 25004032 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 147456, "byteOffset": 26183680 } ], "md5sum": "205e26022d208d6a4ad212a40937aa6d" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 15482880 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 860160, "byteOffset": 22364160 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23224320 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23227392 }, { "name": "model.layers.20.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23230464 }, { "name": "model.layers.20.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 196608, "byteOffset": 24803328 }, { "name": "model.layers.20.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 24999936 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 25004032 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 147456, "byteOffset": 26183680 } ], "md5sum": "3182b714b1ea400a7742de220f4b0bc5" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 15482880 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 860160, "byteOffset": 22364160 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23224320 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23227392 }, { "name": "model.layers.21.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23230464 }, { "name": "model.layers.21.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 196608, "byteOffset": 24803328 }, { "name": "model.layers.21.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 24999936 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 25004032 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 147456, "byteOffset": 26183680 } ], "md5sum": "26b7aa6e035a1378ccc3c25f723f8975" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 15482880 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 860160, "byteOffset": 22364160 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23224320 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23227392 }, { "name": "model.layers.22.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23230464 }, { "name": "model.layers.22.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 196608, "byteOffset": 24803328 }, { "name": "model.layers.22.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 24999936 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 25004032 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 147456, "byteOffset": 26183680 } ], "md5sum": "dfc9e7f40ad8d60124e82d692166cae6" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 15482880 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 860160, "byteOffset": 22364160 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23224320 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23227392 }, { "name": "model.layers.23.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23230464 }, { "name": "model.layers.23.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 196608, "byteOffset": 24803328 }, { "name": "model.layers.23.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 24999936 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 25004032 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 147456, "byteOffset": 26183680 } ], "md5sum": "1a75614351eaac1b6d4d664de1568b54" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 15482880 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 860160, "byteOffset": 22364160 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23224320 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23227392 }, { "name": "model.layers.24.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23230464 }, { "name": "model.layers.24.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 196608, "byteOffset": 24803328 }, { "name": "model.layers.24.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 24999936 }, { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 25004032 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 147456, "byteOffset": 26183680 } ], "md5sum": "1d46dd660d57f58e3151c319034bb2bb" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 15482880 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 860160, "byteOffset": 22364160 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23224320 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23227392 }, { "name": "model.layers.25.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23230464 }, { "name": "model.layers.25.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 196608, "byteOffset": 24803328 }, { "name": "model.layers.25.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 24999936 }, { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 25004032 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 147456, "byteOffset": 26183680 } ], "md5sum": "ced90aa6def99599e08ef90fdddf873c" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 15482880 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 860160, "byteOffset": 22364160 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23224320 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23227392 }, { "name": "model.layers.26.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23230464 }, { "name": "model.layers.26.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 196608, "byteOffset": 24803328 }, { "name": "model.layers.26.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 24999936 }, { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 25004032 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 147456, "byteOffset": 26183680 } ], "md5sum": "4e40b602803bb56cb7c81edecf69e22b" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 15482880 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 860160, "byteOffset": 22364160 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23224320 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23227392 }, { "name": "model.layers.27.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 23230464 }, { "name": "model.layers.27.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 196608, "byteOffset": 24803328 }, { "name": "model.layers.27.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 24999936 }, { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 25004032 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 147456, "byteOffset": 26183680 } ], "md5sum": "2ce6300c8b1c7f885c9d0a7a9900679c" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 466747392, "records": [ { "name": "lm_head.weight", "shape": [ 151936, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 466747392, "byteOffset": 0 } ], "md5sum": "fecf67195ad7c035b39a5b4b1c77facc" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 23233536, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 15482880 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 860160, "byteOffset": 22364160 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23224320 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23227392 }, { "name": "model.norm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 23230464 } ], "md5sum": "bcb99fa5878a5a3c4566d919ce99e098" } ] }