{ "metadata": { "ParamSize": 311, "ParamBytes": 965310464.0, "BitsPerParam": 5.002534272041053 }, "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": "d6a4315ea780a0261dec50ea468198b0" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 22330368, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 151936, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14585856, "byteOffset": 0 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 14585856 }, { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 14588928 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 21470208 } ], "md5sum": "580b10576d56095ddbd94be1e0f43e30" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.0.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.0.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.0.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "3cc3f4c7e8e49997b8cb27f30699ebae" }, { "dataPath": "params_shard_3.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": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.1.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.1.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.1.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "2451ebe8ce1bff157439471c78335a40" }, { "dataPath": "params_shard_4.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": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.10.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.10.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.10.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "0362066649144c99891b0a0c1facb27a" }, { "dataPath": "params_shard_5.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": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.11.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.11.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.11.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "61d2dcfef7af79c46d6a0cea237da964" }, { "dataPath": "params_shard_6.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": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.12.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.12.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.12.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "f0485cdc6ef55bfaef427f2120f3c654" }, { "dataPath": "params_shard_7.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": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.13.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.13.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.13.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "9214f99a826e48b1ebd46cee7a852969" }, { "dataPath": "params_shard_8.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": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.14.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.14.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.14.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "4e14cea30013119d7d1e65be1485cdf8" }, { "dataPath": "params_shard_9.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": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.15.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.15.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.15.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "f7fc89205466b13a922828610d1c759d" }, { "dataPath": "params_shard_10.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": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.16.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.16.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.16.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "dc39dbc8a35a318d00fe0966ddb5a7c0" }, { "dataPath": "params_shard_11.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": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.17.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.17.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.17.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "20aa94d203d42edfe19cf06e678e065a" }, { "dataPath": "params_shard_12.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": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.18.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.18.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.18.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "ecfb32de9e6b97b6b3937eafa28c436c" }, { "dataPath": "params_shard_13.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": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.19.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.19.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.19.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "09e4a46e9d6571adface517a2c7b042e" }, { "dataPath": "params_shard_14.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": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.2.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.2.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.2.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "88dfd427bff30f52477b8dedfdea088b" }, { "dataPath": "params_shard_15.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": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.20.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.20.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.20.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "90cc69a3039db10f567866b593993dc0" }, { "dataPath": "params_shard_16.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": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.21.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.21.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.21.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "04f575a3e25cc7346f50b42adbbcf1d8" }, { "dataPath": "params_shard_17.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": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.22.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.22.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.22.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "5d7f1c61c3108a44bcbc1850a10c1a9c" }, { "dataPath": "params_shard_18.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": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.23.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.23.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.23.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "78602eb03dd973ca191e420464440c0e" }, { "dataPath": "params_shard_19.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": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.24.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.24.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.24.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "434f6a792e7427d6eba459979b27cbd5" }, { "dataPath": "params_shard_20.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": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.25.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.25.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.25.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "0012b38d7ad3862dd23cd31c48a68861" }, { "dataPath": "params_shard_21.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": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.26.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.26.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.26.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "b996bd4686465ed87a3aae06ca683769" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 26331136, "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": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.27.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.27.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.27.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "eba118e548b4289306dae5128f4f01fb" }, { "dataPath": "params_shard_23.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": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.3.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.3.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.3.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "10936ca6bfdf0a0f59b914dd1bc1f494" }, { "dataPath": "params_shard_24.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": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.4.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.4.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.4.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "93408d5e53063834457e960ee6400082" }, { "dataPath": "params_shard_25.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": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.5.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.5.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.5.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "12d9061014531964797f5cca73113210" }, { "dataPath": "params_shard_26.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": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.6.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.6.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.6.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "869099e62e95609757a22cc75037d1cc" }, { "dataPath": "params_shard_27.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": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.7.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.7.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.7.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "4328f7dca23f4bf19de49445876299a8" }, { "dataPath": "params_shard_28.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": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.8.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.8.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.8.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "fdd5d4e66e68f8a1b7e0190d1035ef22" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 18589696, "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": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.9.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.9.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.9.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.norm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 } ], "md5sum": "af5a9ac27a6a7baeb59b151e8f21d32a" } ] }