{ "metadata": { "ParamSize": 311, "ParamBytes": 796192768.0, "BitsPerParam": 4.126114610388425 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 116686848, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 151936, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 116686848, "byteOffset": 0 } ], "md5sum": "44f3d9392dbd3d3cce91aab02ccb9b5c" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 27787264, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 151936, 12 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3646464, "byteOffset": 0 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 3646464 }, { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 1120, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 3649536 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 70, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 215040, "byteOffset": 10530816 }, { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 192, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 10745856 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 12, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 430080, "byteOffset": 24508416 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 24938496 }, { "name": "model.layers.0.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 24941568 }, { "name": "model.layers.0.self_attn.c_attn.q_weight", "shape": [ 192, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 24945664 }, { "name": "model.layers.0.self_attn.c_attn.q_scale", "shape": [ 12, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 49152, "byteOffset": 26518528 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 192, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 26567680 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 12, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 36864, "byteOffset": 27747328 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 27784192 } ], "md5sum": "ba6dafc361bba4e19b94de8ae2461058" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 31234048, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 1120, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 0 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 70, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 215040, "byteOffset": 6881280 }, { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 192, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 7096320 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 12, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 430080, "byteOffset": 20858880 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 21288960 }, { "name": "model.layers.1.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 21292032 }, { "name": "model.layers.1.self_attn.c_attn.q_weight", "shape": [ 192, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 21296128 }, { "name": "model.layers.1.self_attn.c_attn.q_scale", "shape": [ 12, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 49152, "byteOffset": 22868992 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 192, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 22918144 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 12, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 36864, "byteOffset": 24097792 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 24134656 }, { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 1120, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 24137728 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 70, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 215040, "byteOffset": 31019008 } ], "md5sum": "507d98ea5787f700a437ca36e565e522" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 24137728, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 192, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 12, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 430080, "byteOffset": 13762560 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 14192640 }, { "name": "model.layers.10.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14195712 }, { "name": "model.layers.10.self_attn.c_attn.q_weight", "shape": [ 192, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 14199808 }, { "name": "model.layers.10.self_attn.c_attn.q_scale", "shape": [ 12, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 49152, "byteOffset": 15772672 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 192, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 15821824 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 12, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 36864, "byteOffset": 17001472 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 17038336 }, { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 1120, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 17041408 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 70, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 215040, "byteOffset": 23922688 } ], "md5sum": "93e115ae0065d555ab1fbb47ca993b35" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 24137728, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 192, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 12, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 430080, "byteOffset": 13762560 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 14192640 }, { "name": "model.layers.11.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14195712 }, { "name": "model.layers.11.self_attn.c_attn.q_weight", "shape": [ 192, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 14199808 }, { "name": "model.layers.11.self_attn.c_attn.q_scale", "shape": [ 12, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 49152, "byteOffset": 15772672 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 192, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 15821824 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 12, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 36864, "byteOffset": 17001472 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 17038336 }, { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 1120, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 17041408 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 70, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 215040, "byteOffset": 23922688 } ], "md5sum": "8edc574d5ba72e272703410c2538026c" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 24137728, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 192, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 12, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 430080, "byteOffset": 13762560 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 14192640 }, { "name": "model.layers.12.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14195712 }, { "name": "model.layers.12.self_attn.c_attn.q_weight", "shape": [ 192, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 14199808 }, { "name": "model.layers.12.self_attn.c_attn.q_scale", "shape": [ 12, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 49152, "byteOffset": 15772672 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 192, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 15821824 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 12, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 36864, "byteOffset": 17001472 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 17038336 }, { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 1120, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 17041408 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 70, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 215040, "byteOffset": 23922688 } ], "md5sum": "f94d17e18b173bad723af5910302011d" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 24137728, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 192, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 12, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 430080, "byteOffset": 13762560 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 14192640 }, { "name": "model.layers.13.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14195712 }, { "name": "model.layers.13.self_attn.c_attn.q_weight", "shape": [ 192, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 14199808 }, { "name": "model.layers.13.self_attn.c_attn.q_scale", "shape": [ 12, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 49152, "byteOffset": 15772672 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 192, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 15821824 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 12, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 36864, "byteOffset": 17001472 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 17038336 }, { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 1120, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 17041408 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 70, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 215040, "byteOffset": 23922688 } ], "md5sum": "723c1e51ba7ab19d1f7ae47445d1ab16" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 24137728, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 192, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 12, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 430080, "byteOffset": 13762560 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 14192640 }, { "name": "model.layers.14.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14195712 }, { "name": "model.layers.14.self_attn.c_attn.q_weight", "shape": [ 192, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 14199808 }, { "name": "model.layers.14.self_attn.c_attn.q_scale", "shape": [ 12, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 49152, "byteOffset": 15772672 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 192, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 15821824 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 12, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 36864, "byteOffset": 17001472 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 17038336 }, { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 1120, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 17041408 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 70, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 215040, "byteOffset": 23922688 } ], "md5sum": "3342d757bca24db7e204687ccd3342d2" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 24137728, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 192, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 12, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 430080, "byteOffset": 13762560 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 14192640 }, { "name": "model.layers.15.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14195712 }, { "name": "model.layers.15.self_attn.c_attn.q_weight", "shape": [ 192, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 14199808 }, { "name": "model.layers.15.self_attn.c_attn.q_scale", "shape": [ 12, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 49152, "byteOffset": 15772672 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 192, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 15821824 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 12, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 36864, "byteOffset": 17001472 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 17038336 }, { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 1120, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 17041408 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 70, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 215040, "byteOffset": 23922688 } ], "md5sum": "44334c3f508bb61a9d34a94606dd7495" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 24137728, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 192, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 12, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 430080, "byteOffset": 13762560 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 14192640 }, { "name": "model.layers.16.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14195712 }, { "name": "model.layers.16.self_attn.c_attn.q_weight", "shape": [ 192, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 14199808 }, { "name": "model.layers.16.self_attn.c_attn.q_scale", "shape": [ 12, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 49152, "byteOffset": 15772672 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 192, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 15821824 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 12, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 36864, "byteOffset": 17001472 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 17038336 }, { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 1120, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 17041408 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 70, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 215040, "byteOffset": 23922688 } ], "md5sum": "a069017f37af20c416b4ea8feb15860d" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 24137728, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 192, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 12, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 430080, "byteOffset": 13762560 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 14192640 }, { "name": "model.layers.17.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14195712 }, { "name": "model.layers.17.self_attn.c_attn.q_weight", "shape": [ 192, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 14199808 }, { "name": "model.layers.17.self_attn.c_attn.q_scale", "shape": [ 12, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 49152, "byteOffset": 15772672 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 192, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 15821824 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 12, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 36864, "byteOffset": 17001472 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 17038336 }, { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 1120, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 17041408 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 70, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 215040, "byteOffset": 23922688 } ], "md5sum": "4995ee5f253979a878065a8d5f150547" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 24137728, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 192, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 12, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 430080, "byteOffset": 13762560 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 14192640 }, { "name": "model.layers.18.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14195712 }, { "name": "model.layers.18.self_attn.c_attn.q_weight", "shape": [ 192, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 14199808 }, { "name": "model.layers.18.self_attn.c_attn.q_scale", "shape": [ 12, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 49152, "byteOffset": 15772672 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 192, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 15821824 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 12, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 36864, "byteOffset": 17001472 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 17038336 }, { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 1120, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 17041408 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 70, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 215040, "byteOffset": 23922688 } ], "md5sum": "46625bc385bf12b8a5f5f4e339e0438d" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 24137728, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 192, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 12, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 430080, "byteOffset": 13762560 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 14192640 }, { "name": "model.layers.19.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14195712 }, { "name": "model.layers.19.self_attn.c_attn.q_weight", "shape": [ 192, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 14199808 }, { "name": "model.layers.19.self_attn.c_attn.q_scale", "shape": [ 12, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 49152, "byteOffset": 15772672 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 192, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 15821824 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 12, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 36864, "byteOffset": 17001472 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 17038336 }, { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 1120, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 17041408 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 70, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 215040, "byteOffset": 23922688 } ], "md5sum": "8b99c8a87664a6b9726b2e1d67134253" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 24137728, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 192, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 12, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 430080, "byteOffset": 13762560 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 14192640 }, { "name": "model.layers.2.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14195712 }, { "name": "model.layers.2.self_attn.c_attn.q_weight", "shape": [ 192, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 14199808 }, { "name": "model.layers.2.self_attn.c_attn.q_scale", "shape": [ 12, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 49152, "byteOffset": 15772672 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 192, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 15821824 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 12, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 36864, "byteOffset": 17001472 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 17038336 }, { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 1120, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 17041408 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 70, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 215040, "byteOffset": 23922688 } ], "md5sum": "2aa2b4b2b8b82ab502c27cffcb1dd9e0" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 24137728, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 192, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 12, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 430080, "byteOffset": 13762560 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 14192640 }, { "name": "model.layers.20.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14195712 }, { "name": "model.layers.20.self_attn.c_attn.q_weight", "shape": [ 192, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 14199808 }, { "name": "model.layers.20.self_attn.c_attn.q_scale", "shape": [ 12, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 49152, "byteOffset": 15772672 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 192, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 15821824 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 12, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 36864, "byteOffset": 17001472 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 17038336 }, { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 1120, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 17041408 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 70, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 215040, "byteOffset": 23922688 } ], "md5sum": "11e9fe2e2d18bfe529c910c8869cffe4" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 24137728, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 192, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 12, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 430080, "byteOffset": 13762560 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 14192640 }, { "name": "model.layers.21.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14195712 }, { "name": "model.layers.21.self_attn.c_attn.q_weight", "shape": [ 192, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 14199808 }, { "name": "model.layers.21.self_attn.c_attn.q_scale", "shape": [ 12, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 49152, "byteOffset": 15772672 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 192, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 15821824 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 12, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 36864, "byteOffset": 17001472 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 17038336 }, { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 1120, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 17041408 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 70, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 215040, "byteOffset": 23922688 } ], "md5sum": "9cc4be5ad9fa6f0dd2a2ae9933bae99b" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 24137728, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 192, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 12, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 430080, "byteOffset": 13762560 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 14192640 }, { "name": "model.layers.22.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14195712 }, { "name": "model.layers.22.self_attn.c_attn.q_weight", "shape": [ 192, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 14199808 }, { "name": "model.layers.22.self_attn.c_attn.q_scale", "shape": [ 12, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 49152, "byteOffset": 15772672 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 192, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 15821824 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 12, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 36864, "byteOffset": 17001472 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 17038336 }, { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 1120, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 17041408 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 70, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 215040, "byteOffset": 23922688 } ], "md5sum": "990f899233475e0124110f0da09551c1" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 24137728, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 192, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 12, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 430080, "byteOffset": 13762560 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 14192640 }, { "name": "model.layers.23.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14195712 }, { "name": "model.layers.23.self_attn.c_attn.q_weight", "shape": [ 192, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 14199808 }, { "name": "model.layers.23.self_attn.c_attn.q_scale", "shape": [ 12, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 49152, "byteOffset": 15772672 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 192, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 15821824 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 12, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 36864, "byteOffset": 17001472 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 17038336 }, { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 1120, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 17041408 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 70, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 215040, "byteOffset": 23922688 } ], "md5sum": "e63dca766cf5a8264d764afd75ede3ff" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 24137728, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 192, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 12, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 430080, "byteOffset": 13762560 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 14192640 }, { "name": "model.layers.24.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14195712 }, { "name": "model.layers.24.self_attn.c_attn.q_weight", "shape": [ 192, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 14199808 }, { "name": "model.layers.24.self_attn.c_attn.q_scale", "shape": [ 12, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 49152, "byteOffset": 15772672 }, { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 192, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 15821824 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 12, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 36864, "byteOffset": 17001472 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 17038336 }, { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 1120, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 17041408 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 70, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 215040, "byteOffset": 23922688 } ], "md5sum": "503ca0482483bdebe0efe375bcc8b89b" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 24137728, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 192, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 12, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 430080, "byteOffset": 13762560 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 14192640 }, { "name": "model.layers.25.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14195712 }, { "name": "model.layers.25.self_attn.c_attn.q_weight", "shape": [ 192, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 14199808 }, { "name": "model.layers.25.self_attn.c_attn.q_scale", "shape": [ 12, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 49152, "byteOffset": 15772672 }, { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 192, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 15821824 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 12, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 36864, "byteOffset": 17001472 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 17038336 }, { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 1120, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 17041408 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 70, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 215040, "byteOffset": 23922688 } ], "md5sum": "e2989bf596cf94ca8ca126dcb310a73d" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 24137728, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 192, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 12, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 430080, "byteOffset": 13762560 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 14192640 }, { "name": "model.layers.26.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14195712 }, { "name": "model.layers.26.self_attn.c_attn.q_weight", "shape": [ 192, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 14199808 }, { "name": "model.layers.26.self_attn.c_attn.q_scale", "shape": [ 12, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 49152, "byteOffset": 15772672 }, { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 192, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 15821824 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 12, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 36864, "byteOffset": 17001472 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 17038336 }, { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 1120, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 17041408 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 70, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 215040, "byteOffset": 23922688 } ], "md5sum": "77d10dd766fc8f8444259186faa498f2" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 24137728, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 192, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 12, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 430080, "byteOffset": 13762560 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 14192640 }, { "name": "model.layers.27.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14195712 }, { "name": "model.layers.27.self_attn.c_attn.q_weight", "shape": [ 192, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 14199808 }, { "name": "model.layers.27.self_attn.c_attn.q_scale", "shape": [ 12, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 49152, "byteOffset": 15772672 }, { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 192, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 15821824 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 12, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 36864, "byteOffset": 17001472 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 17038336 }, { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 1120, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 17041408 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 70, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 215040, "byteOffset": 23922688 } ], "md5sum": "8c6acead431353232ee867f916aa591b" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 24137728, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 192, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 12, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 430080, "byteOffset": 13762560 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 14192640 }, { "name": "model.layers.3.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14195712 }, { "name": "model.layers.3.self_attn.c_attn.q_weight", "shape": [ 192, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 14199808 }, { "name": "model.layers.3.self_attn.c_attn.q_scale", "shape": [ 12, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 49152, "byteOffset": 15772672 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 192, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 15821824 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 12, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 36864, "byteOffset": 17001472 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 17038336 }, { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 1120, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 17041408 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 70, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 215040, "byteOffset": 23922688 } ], "md5sum": "e0254463ec65cb83a363412c66e3fe7d" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 24137728, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 192, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 12, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 430080, "byteOffset": 13762560 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 14192640 }, { "name": "model.layers.4.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14195712 }, { "name": "model.layers.4.self_attn.c_attn.q_weight", "shape": [ 192, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 14199808 }, { "name": "model.layers.4.self_attn.c_attn.q_scale", "shape": [ 12, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 49152, "byteOffset": 15772672 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 192, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 15821824 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 12, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 36864, "byteOffset": 17001472 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 17038336 }, { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 1120, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 17041408 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 70, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 215040, "byteOffset": 23922688 } ], "md5sum": "681b0a42115bc5ab66d10b975e8c38aa" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 24137728, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 192, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 12, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 430080, "byteOffset": 13762560 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 14192640 }, { "name": "model.layers.5.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14195712 }, { "name": "model.layers.5.self_attn.c_attn.q_weight", "shape": [ 192, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 14199808 }, { "name": "model.layers.5.self_attn.c_attn.q_scale", "shape": [ 12, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 49152, "byteOffset": 15772672 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 192, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 15821824 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 12, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 36864, "byteOffset": 17001472 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 17038336 }, { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 1120, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 17041408 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 70, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 215040, "byteOffset": 23922688 } ], "md5sum": "971a680ec968796a6f67a15d775857dc" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 24137728, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 192, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 12, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 430080, "byteOffset": 13762560 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 14192640 }, { "name": "model.layers.6.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14195712 }, { "name": "model.layers.6.self_attn.c_attn.q_weight", "shape": [ 192, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 14199808 }, { "name": "model.layers.6.self_attn.c_attn.q_scale", "shape": [ 12, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 49152, "byteOffset": 15772672 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 192, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 15821824 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 12, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 36864, "byteOffset": 17001472 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 17038336 }, { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 1120, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 17041408 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 70, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 215040, "byteOffset": 23922688 } ], "md5sum": "d827b3227a3e1d13d52f8b36682d0712" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 24137728, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 192, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 12, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 430080, "byteOffset": 13762560 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 14192640 }, { "name": "model.layers.7.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14195712 }, { "name": "model.layers.7.self_attn.c_attn.q_weight", "shape": [ 192, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 14199808 }, { "name": "model.layers.7.self_attn.c_attn.q_scale", "shape": [ 12, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 49152, "byteOffset": 15772672 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 192, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 15821824 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 12, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 36864, "byteOffset": 17001472 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 17038336 }, { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 1120, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 17041408 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 70, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 215040, "byteOffset": 23922688 } ], "md5sum": "5b719d031ccb575e896151be0b9b287e" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 24137728, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 192, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 12, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 430080, "byteOffset": 13762560 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 14192640 }, { "name": "model.layers.8.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14195712 }, { "name": "model.layers.8.self_attn.c_attn.q_weight", "shape": [ 192, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 14199808 }, { "name": "model.layers.8.self_attn.c_attn.q_scale", "shape": [ 12, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 49152, "byteOffset": 15772672 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 192, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 15821824 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 12, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 36864, "byteOffset": 17001472 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 17038336 }, { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 1120, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 17041408 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 70, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 215040, "byteOffset": 23922688 } ], "md5sum": "846cafacfa76b1b64361c80c08141691" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 17041408, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 192, 17920 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 12, 17920 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 430080, "byteOffset": 13762560 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 14192640 }, { "name": "model.layers.9.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 14195712 }, { "name": "model.layers.9.self_attn.c_attn.q_weight", "shape": [ 192, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 14199808 }, { "name": "model.layers.9.self_attn.c_attn.q_scale", "shape": [ 12, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 49152, "byteOffset": 15772672 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 192, 1536 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 15821824 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 12, 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 36864, "byteOffset": 17001472 }, { "name": "model.norm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 17038336 } ], "md5sum": "ddbf0748316b94c2b78d6d9ab2608b28" } ] }