{ "metadata": { "ParamSize": 325, "ParamBytes": 3274754296.0, "BitsPerParam": 2.608942222483959 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 52739296, "records": [ { "name": "lm_head.q_weight", "shape": [ 32002, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 52739296, "byteOffset": 0 } ], "md5sum": "ae7dfdd348a4b36ab9a7df486bf7387b" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "a0602b96bb8a6562f9930a50aec93732" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 52739296, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 32002, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 52739296, "byteOffset": 0 } ], "md5sum": "f56a62a7410de868e527c6d2c04cfe39" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "472455859067ac28edc1ff8fe0802508" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "925653c172fcb2371275dfece50b7e45" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 27979576, "records": [ { "name": "lm_head.q_scale", "shape": [ 32002, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6592412, "byteOffset": 0 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 6592412 }, { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 6600604 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 12507036 }, { "name": "model.norm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 12515228 }, { "name": "model.embed_tokens.q_scale", "shape": [ 32002, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6592412, "byteOffset": 12523420 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 19115832 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 19124024 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 22064952 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 27971384 } ], "md5sum": "0d581193bccc1ede6591c51baecb56a9" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "fb468b90208ad6b23dbd4d9d1c20a0d8" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "1e009715ac869c6a8746701d1e94a6a0" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 10125312 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 11390976 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 18141184 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 18984960 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 18993152 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 21934080 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 27840512 } ], "md5sum": "84845ff602bc4af3b657c111a474a4a5" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 30375936, "records": [ { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 0 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 10125312 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 11390976 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 18141184 }, { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 18984960 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 29110272 } ], "md5sum": "7c1be4eb164878e4ceab8fcbdfae83fc" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 31129600, "records": [ { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 0 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 6750208 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 7593984 }, { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 7602176 } ], "md5sum": "8e20e26b59a7782f463a2cdc2c02e589" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "a45901a7be365fc4cf3d3c53faf816b7" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "5c8f960ff735006c48d43f00d969717e" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "530f7bf9c83189d51ee02963474aa3a9" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 30789632, "records": [ { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 0 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 2940928 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 8847360 }, { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 8855552 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 18980864 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 20246528 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 26996736 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 27840512 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 27848704 } ], "md5sum": "0ed3d95f1e88fff15474afe64252e94a" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "9edfe681a6e44328a42d72652f83a310" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "a9bbca56b4f0f16c9b0a53d98f15a11f" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "308286211827d0ff22c64235e0a4445d" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "6b36943f298177548212a714cf9c8a31" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "ae45b75c3572ca7f21104ea8025dee69" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "370366f48083a262653b24379345d442" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "5f1010bca169706bfa42f53fa381841e" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "874274b85fdfa81262682c1329ac5639" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "baaba1af05056d34028d2ea3f0c880be" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "1b7a6e5b3c5252e8c9b4cc956ec2a804" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "761873aa7467278e9445f0dc6a384f24" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "9768d99a19a62c5a0c58f41a9dc08de5" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "96779520032d3f7a0514976ec377bf82" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "5d2d59627e6824958f5fb27fa0f6249a" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "1dfd4d070029615012396b32eb64e29e" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "e66c21cf3a2edcdeca395106842f1f24" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "81bdc739beb5f92eedbc9cee82eccda3" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "82c6e9882c962856ee4a7dbaa996ee4e" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "b3972992784f3760a2b858d8d1892600" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "a974baace75cddf36444b8d1d14805c2" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "b65bd042e91a62806c192f42d0db8c2c" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "84dc9eedc9c6d52464730e18d4ee5ebc" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 32391168, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5914624 }, { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 5922816 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 29450240 } ], "md5sum": "bd4a608cafffb9afa10cc48ef29c4cea" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "306b34f030facbe29e81c761386adf8a" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "1bd97d3117c397dbabf40bd90f8f8ed3" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "3d82e5ee2efda2933337db174b63acdb" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "0e20603731b01f9b9ba7a752811b52d7" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "35cc16f536b4c5fed220ecc89509a4d2" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "8c67f66ad38c041799416645b8026265" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "b2c5450aa8c0bbec2e671b568a088a25" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "113dfa0efc33f47b4ef1537665c7463d" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "744bfd08a02b4ca62fa7080739059bb0" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "f7c0d0f00e612d34a5140b134c5ab496" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "dc5f52c8a9428d8d78404e8942195ecb" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "07c38882ca0716577523410ca2422ff3" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "4ffd0cdf96cced348dc5731220a7cb6b" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "053c5c9098820504e13704aad8006de5" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "2735c0a1d8fc937534ffd480ca325107" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "ede2e8e6818200d525ab1b70d9b0a82f" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "41ace129dc6b5332f9403b0fba75eda8" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "8e5b02732c2d05f9f89e81e0fd5b22a6" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "614dd0c3d9e35ab9960939d35309d8d6" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "8caabc1d4d95a5834b879109791634dc" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "d9d4b37db88a8dd9f5645c4924ce478a" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "9e1379b8f3c2a9e38b721479fdd3c502" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "ae21fda6cac53ca67536601cc6b31b10" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.18.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "3b50fe174ca839681ef3f6cbb4d19791" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "4e06d6c09683392658229c5e78269e04" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "5a25ff934ddc6cff695a515cb1cc4f3e" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.19.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "040b56a5ad83e2db1f0feb26ee646749" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 24899584, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.20.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 } ], "md5sum": "65a8fb6537b63872c9589bfe1d78299f" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "7fe79b5e95563515d269959b761622f4" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "e74174d52522fc6b9b1a1ccf3972e30e" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "a51e63063d6f8a82530a0c6e529af8de" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "84f9680d60f245d45586a091c6859c84" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 30797824, "records": [ { "name": "model.layers.21.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 0 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 10125312 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 11390976 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 11399168 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 14340096 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 20246528 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 20254720 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 27004928 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 27848704 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 27856896 } ], "md5sum": "10a016bab9ff2822f71ff90d9328ed89" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "12b72aee693ed80b240fc4c9caed4772" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "eb428cda63407ef9e345263e6e486598" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.22.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.22.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "5dd9feea813c5d0dd535445dcd1f7cdd" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "1d7c49cd51ff1cade9f1e5c0d1e0599b" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "6a7d5c5fa1b7f8edc86ffbf50c6b879e" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.23.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.23.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "c94ee0948e342cd96fadedef016ea36e" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "d912be682d924d97a18f1fc958f019c4" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "d935a64b0c6b41d93be985180ef7caa7" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.24.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.24.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "7d300317707c854a2eb088549bd6b6c0" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "0188773279a91a6a59a6f75c7224ec74" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "7b4b5f08ccb35441a9de969fcdb8724f" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.25.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.25.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "4d2f5a2f2ef08e6efdf8dbb55a228f37" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "c2184f100bba9b389eead2256e83e9bf" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "65ef78a23a451f95566c845debd74fa3" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.26.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.26.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "ca4820f4351becfe9f7ab81eef197d05" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "e5857a9c9ffd41669097af93d60b0e12" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "805b38d78bf4d82d0a4a86426c0f0574" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.27.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.27.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "c0233859a61d58b3158b51b58f770d0c" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "965cbd2b00b456284aa0abbd5ea0a1f0" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "b1a8fc87a99c8f68474eb5619087910b" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.28.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.28.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "223d02d4074aeb1006a0e2daf1d64752" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "e82d61f19cdd41d10e8aa01eeadd044a" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "8309abb8be6fc6eac6d69ad57ea8ea73" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.29.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.29.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "1ba0ddedc93d7ac440ec53a100a652a0" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "cbfcb44ed601bfb128f705ab039d05bc" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 27840512, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.30.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.30.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24899584 } ], "md5sum": "02f4c2d8371b51278b30306b53e3ffff" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 18984960, "records": [ { "name": "model.layers.31.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 0 }, { "name": "model.layers.31.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 10125312 }, { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 11390976 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 18141184 } ], "md5sum": "9a428c7d7bddd0ef8233ab57f5441924" } ] }