gemma-2-9b-it-q0f16-MLC / ndarray-cache.json
CharlieFRuan's picture
Upload folder using huggingface_hub
7398d4e verified
{
"metadata": {
"ParamSize": 338,
"ParamBytes": 18483411968.0,
"BitsPerParam": 16.0
},
"records": [
{
"dataPath": "params_shard_0.bin",
"format": "raw-shard",
"nbytes": 1835008000,
"records": [
{
"name": "model.embed_tokens.weight",
"shape": [
256000,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 1835008000,
"byteOffset": 0
}
],
"md5sum": "168fc50d15fb31cb7c562a0b7e02e27c"
},
{
"dataPath": "params_shard_1.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.0.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "656d24868897c510c824a40edc4143bc"
},
{
"dataPath": "params_shard_2.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.0.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "ab3af607504f2df38a9670c632ba75fd"
},
{
"dataPath": "params_shard_3.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.0.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "888f29af02a973977c4f0314aa917dfc"
},
{
"dataPath": "params_shard_4.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.1.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "4a81647d9610dca1e9dceeab3260751a"
},
{
"dataPath": "params_shard_5.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.1.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "8d6997fe8b3f937bd50c2124e3a9e4dc"
},
{
"dataPath": "params_shard_6.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.1.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "ac014de0d57f359b2441a3707f76c96a"
},
{
"dataPath": "params_shard_7.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.1.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "d82605b2a7ac5805ebb98dcfbf068d16"
},
{
"dataPath": "params_shard_8.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.2.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "b338e605c06224736f30659d09175f8a"
},
{
"dataPath": "params_shard_9.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.2.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "9b1ad73a81a37a9c249ec322ecaee216"
},
{
"dataPath": "params_shard_10.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.2.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "d36feca5b13339134de56bdd1425e487"
},
{
"dataPath": "params_shard_11.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.2.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "87534676de6e7b250fcc908f504f3165"
},
{
"dataPath": "params_shard_12.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.3.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "e1b40a2ba14f307b38e5b5d5bc89d697"
},
{
"dataPath": "params_shard_13.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.3.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "2b64a1f1c9fcd8737b90b62fa7817d95"
},
{
"dataPath": "params_shard_14.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.3.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "0841f856a7dcc44502630565f1d4e21f"
},
{
"dataPath": "params_shard_15.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.3.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "f7432477f6a0a60f15d88a1d47db9fe1"
},
{
"dataPath": "params_shard_16.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.4.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "283e9c6e3495d1d4f5da7a73c711656c"
},
{
"dataPath": "params_shard_17.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.4.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "1767b59a82ec4c509a894b8fff46a502"
},
{
"dataPath": "params_shard_18.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.4.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "88686a65bf7264bd25976eb98009dfce"
},
{
"dataPath": "params_shard_19.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.4.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "9adf400169acb36beac61ae8bf4ee9cb"
},
{
"dataPath": "params_shard_20.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.5.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "bae08b922d4b11f4c412659196f859f3"
},
{
"dataPath": "params_shard_21.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.5.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "3643cdef66b12a04866cc58498372018"
},
{
"dataPath": "params_shard_22.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.5.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "6bff8d9e3baa6ae70ed5bd4da7819950"
},
{
"dataPath": "params_shard_23.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.5.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "5a45157ca5301e36d013d7e383165737"
},
{
"dataPath": "params_shard_24.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.6.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "8e7127f8aa1b298d0347ac361d5aeb19"
},
{
"dataPath": "params_shard_25.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.6.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "81124c78478b247130b6bb788f7f0eff"
},
{
"dataPath": "params_shard_26.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.6.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "576789d00b12b54f5047c1f063bdfe42"
},
{
"dataPath": "params_shard_27.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.6.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "1e7c323595db70f3f7efd6f37a953afc"
},
{
"dataPath": "params_shard_28.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.7.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "4369a6c02bd0418d106b2abbe8b8e6f9"
},
{
"dataPath": "params_shard_29.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.7.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "5540a26c3f5f81d9e86c5a6b08eb521c"
},
{
"dataPath": "params_shard_30.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.7.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "d5b8d87c678de2841605bdacbf4fc79e"
},
{
"dataPath": "params_shard_31.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.10.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "e7f4ee544292fc69bb31c684d97e9636"
},
{
"dataPath": "params_shard_32.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.10.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "f95ed7a74416558d551b408fd9cc4943"
},
{
"dataPath": "params_shard_33.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.10.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "282c8cea15adaa0e17cdd0133b5b0915"
},
{
"dataPath": "params_shard_34.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.10.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "07c4b69bbc22cb45b13851173190f75e"
},
{
"dataPath": "params_shard_35.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.11.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "59de26f53ca40db516567853beb22bb8"
},
{
"dataPath": "params_shard_36.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.11.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "052c698f9964f4c59226c8c8545161a2"
},
{
"dataPath": "params_shard_37.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.11.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "7d2c68c8c8beed9072449712ec004f21"
},
{
"dataPath": "params_shard_38.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.11.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "e3a51416571a34cb35c417efa28c9a34"
},
{
"dataPath": "params_shard_39.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.12.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "0d7378eb6d54fa4f93f5e627ac6475e2"
},
{
"dataPath": "params_shard_40.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.12.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "65b48a39fa2a2c8db2d342891bbde43b"
},
{
"dataPath": "params_shard_41.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.12.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "d510c9eb3bd7164f008b4121dd714610"
},
{
"dataPath": "params_shard_42.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.12.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "3ca95c34721f4c2158cd0f4022442372"
},
{
"dataPath": "params_shard_43.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.13.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "c915695026218bfd773ee58e432eb1bb"
},
{
"dataPath": "params_shard_44.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.13.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "cdf08c322587b53f1b3b776780452d05"
},
{
"dataPath": "params_shard_45.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.13.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "500bb46901875f922ce0d6de3bf993d4"
},
{
"dataPath": "params_shard_46.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.13.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "b128832c2aafdf206010713b9f4c7cdf"
},
{
"dataPath": "params_shard_47.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.14.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "e6ed5ce3761c7b6e6eba86358a6b1e30"
},
{
"dataPath": "params_shard_48.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.14.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "043439705b9c47b4aa3ec90e6a456305"
},
{
"dataPath": "params_shard_49.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.14.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "cc7843a70fa8e8e3915adb61ac298ce3"
},
{
"dataPath": "params_shard_50.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.14.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "fc413a83e3bcc5018d22408c4b1142a4"
},
{
"dataPath": "params_shard_51.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.15.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "9900068b221226ec7a8b7a03bf62a0bb"
},
{
"dataPath": "params_shard_52.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.15.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "b6fef87b4c2d9c0259b239f60b452cfc"
},
{
"dataPath": "params_shard_53.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.15.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "cfb7bf987175b71ea82a0f8ad0e1380a"
},
{
"dataPath": "params_shard_54.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.15.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "fb5e9e7e6c8c97ad03fdb57fa1999b38"
},
{
"dataPath": "params_shard_55.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.16.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "c0fff83dfee25b05a8ce3712c4da144e"
},
{
"dataPath": "params_shard_56.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.16.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "f8fd58fa17d9add7520b88f525b7ce87"
},
{
"dataPath": "params_shard_57.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.16.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "ce07d4a3e59cc73990dab37107b3f49b"
},
{
"dataPath": "params_shard_58.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.16.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "1fbf7adb8c4468c8d75875bd144d123e"
},
{
"dataPath": "params_shard_59.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.17.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "0bedaa7cc084f6b441758d51fb60806f"
},
{
"dataPath": "params_shard_60.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.17.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "5c37d0a17cc4cba218611a4ddd2f8722"
},
{
"dataPath": "params_shard_61.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.17.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "ec3613057e0ecb49eec004b0d26770d4"
},
{
"dataPath": "params_shard_62.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.17.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "22c0838a0545fc7e93c3c1f1f4b53cbf"
},
{
"dataPath": "params_shard_63.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.18.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "90cdb69736aeca5410f979b7827374e0"
},
{
"dataPath": "params_shard_64.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.18.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "3b1617dd34a0e7dba718f3ad72dd11bc"
},
{
"dataPath": "params_shard_65.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.18.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "6f0ebe4b3e3a57dd6cd33857536f2219"
},
{
"dataPath": "params_shard_66.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.18.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "dd063106464c15ac2ae45ed6ac84ecc2"
},
{
"dataPath": "params_shard_67.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.19.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "55798cfba35f3997fe74789579d61d0d"
},
{
"dataPath": "params_shard_68.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.19.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "3ce0e52fe8a733db6837bc282599922d"
},
{
"dataPath": "params_shard_69.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.19.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "85adc23dec1944eaeb5eba3651341ab5"
},
{
"dataPath": "params_shard_70.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.19.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "1803adf4705a79f80f83e8c28e9633fd"
},
{
"dataPath": "params_shard_71.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.20.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "ef1ab2fc2aad78a8aac3fdbba7a4b15a"
},
{
"dataPath": "params_shard_72.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.20.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "99ea0af7c3e233c83fb8221ed103f782"
},
{
"dataPath": "params_shard_73.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.7.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "79decbc641b012c5def9ca20b39db699"
},
{
"dataPath": "params_shard_74.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.8.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "ad392380fc5c33e6430458722ea29a64"
},
{
"dataPath": "params_shard_75.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.8.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "6a6f57096dcf2bdade0dbcd8516b8332"
},
{
"dataPath": "params_shard_76.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.8.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "d254141291bd4f3afe26fb18ab81f283"
},
{
"dataPath": "params_shard_77.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.8.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "93698fdb857c95c485c382238ba35881"
},
{
"dataPath": "params_shard_78.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.9.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "a9c23f2997da4170030236c1eab17eed"
},
{
"dataPath": "params_shard_79.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.9.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "a4d333a678e58100602539a7fbb57d90"
},
{
"dataPath": "params_shard_80.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.9.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "5b127e7cae450c9614dcf51beb2701d0"
},
{
"dataPath": "params_shard_81.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.9.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "7e9e6e67725a14c2142bdb982d230c8d"
},
{
"dataPath": "params_shard_82.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.20.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "a2f91297589b720117864174ca6bd24f"
},
{
"dataPath": "params_shard_83.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.20.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "61fa07d48500c8496d197a18d5bcb9d1"
},
{
"dataPath": "params_shard_84.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.21.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "18126d4ac4650b144f441017f9ab5864"
},
{
"dataPath": "params_shard_85.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.21.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "3a718cf241ad3988257bf495b6351435"
},
{
"dataPath": "params_shard_86.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.21.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "3903d257be6a84edbc895482c66fefb5"
},
{
"dataPath": "params_shard_87.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.21.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "ff4a5ed2e42b857cf8ddaf4e1147ff82"
},
{
"dataPath": "params_shard_88.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.22.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "f825d2992325d19841546b04b4f01c8f"
},
{
"dataPath": "params_shard_89.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.22.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "7ceb45bf5e43950da420ba9c054457e1"
},
{
"dataPath": "params_shard_90.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.22.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "6f21f6567aa4af63cb5494e8e2986b1c"
},
{
"dataPath": "params_shard_91.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.22.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "ada6dec20a8effa10ec4c956bd75370f"
},
{
"dataPath": "params_shard_92.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.23.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "97447a6e7ee597a726532023e849d73d"
},
{
"dataPath": "params_shard_93.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.23.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "0ccf296314c21f0b7275a9b91044f34b"
},
{
"dataPath": "params_shard_94.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.23.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "34af5a7484eb19bd7cdd59f167772533"
},
{
"dataPath": "params_shard_95.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.23.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "1cde95266e745dca77d0cacda81fae78"
},
{
"dataPath": "params_shard_96.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.24.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "7369dd18f298c6e789315e6dffb4937a"
},
{
"dataPath": "params_shard_97.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.24.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "c561180cf4209a1956c97ce3a2d8031a"
},
{
"dataPath": "params_shard_98.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.24.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "a182037470043eac7d942f8fb0f3ee17"
},
{
"dataPath": "params_shard_99.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.24.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "69213d011d96919ac3898a31eb0874d3"
},
{
"dataPath": "params_shard_100.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.25.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "a9f00d67e02c166db371a08fd626db3e"
},
{
"dataPath": "params_shard_101.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.25.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "00ca088eef2390f9e9d0891260b5c842"
},
{
"dataPath": "params_shard_102.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.25.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "05869889d45ca24b22abb2f527b0ea2c"
},
{
"dataPath": "params_shard_103.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.25.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "4918b0473cc1a9409f725d3c62e97517"
},
{
"dataPath": "params_shard_104.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.26.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "ce3a423685e0d5dbc252920a6b2565e0"
},
{
"dataPath": "params_shard_105.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.26.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "7e2d62198ec804f44d91335e85e49bd2"
},
{
"dataPath": "params_shard_106.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.26.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "c14fef85f0b324a278826d117c9128d4"
},
{
"dataPath": "params_shard_107.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.26.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "40864e8c55f557c20e3acdf126585d7b"
},
{
"dataPath": "params_shard_108.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.27.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "cf9313c93c2a3a349e27179fb0028e20"
},
{
"dataPath": "params_shard_109.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.27.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "7a3ffa7161ca76d17436e1d2a48f2b1a"
},
{
"dataPath": "params_shard_110.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.27.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "4173fcf4d7c668dc84582efe888a66c6"
},
{
"dataPath": "params_shard_111.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.27.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "e6065c2c610a8a3a7e9542827fc348cf"
},
{
"dataPath": "params_shard_112.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.28.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "48ca3a219adb9533c5a721e6447dd269"
},
{
"dataPath": "params_shard_113.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.28.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "52e64483edffb61f4706fb74dfe27a7a"
},
{
"dataPath": "params_shard_114.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.28.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "3e161077eacb673d40c06a861a7b08eb"
},
{
"dataPath": "params_shard_115.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.28.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "ba21988c32b5a9d1c8c7349b8ea149f3"
},
{
"dataPath": "params_shard_116.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.29.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "8ee2c4baa1bb52c4a4688b3c67b600b7"
},
{
"dataPath": "params_shard_117.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.29.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "d9dce1d4e690c5a6346559af5f6566d8"
},
{
"dataPath": "params_shard_118.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.29.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "4c0c0d70b29c995ba476a076c5c5a47e"
},
{
"dataPath": "params_shard_119.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.29.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "56116edc0ba4f58d0a8297e071d17ea5"
},
{
"dataPath": "params_shard_120.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.30.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "a18cc26556ebd53d11887e7d972b6b55"
},
{
"dataPath": "params_shard_121.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.30.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "9f11d5edd077c28354bde4d9ec235905"
},
{
"dataPath": "params_shard_122.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.30.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "783b973ec46414512971d06221a1a4f4"
},
{
"dataPath": "params_shard_123.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.30.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "7d8d5c275f41aee540ac53468ef0a861"
},
{
"dataPath": "params_shard_124.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.31.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "58c2567f8218b579ac2b2e4ea38757c1"
},
{
"dataPath": "params_shard_125.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.31.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "dd13aae09e042e14877baee3026246d0"
},
{
"dataPath": "params_shard_126.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.31.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "3289d92ed37cbcaf084298558e499fa0"
},
{
"dataPath": "params_shard_127.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.31.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "04fb20d859f091672e21c066f0b5c5d6"
},
{
"dataPath": "params_shard_128.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.32.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "66589ed1ba1c203b9117640a11974539"
},
{
"dataPath": "params_shard_129.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.32.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "133c4b4d1970077b27e943cdbec768be"
},
{
"dataPath": "params_shard_130.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.32.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "13468fb093216e59eb03822a3e63f870"
},
{
"dataPath": "params_shard_131.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.32.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "496032862ec3fb6b036201d8dfde97f4"
},
{
"dataPath": "params_shard_132.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.33.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "865f032938b845ae80daf57c99471195"
},
{
"dataPath": "params_shard_133.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.33.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "ace8dc4e93d6d2f384f77d5ee6829d40"
},
{
"dataPath": "params_shard_134.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.33.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "90267d30aefaa959c7ba3803adc41f2c"
},
{
"dataPath": "params_shard_135.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.33.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "20504a68333023af33e63d95626832ee"
},
{
"dataPath": "params_shard_136.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.34.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "f53cb7992e9c6b655922b97f76217d7b"
},
{
"dataPath": "params_shard_137.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.34.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "8d70aad5ad39b78ad8e02e93d079f7c7"
},
{
"dataPath": "params_shard_138.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.34.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "9f7e4d631ffe8e9719908292850fa753"
},
{
"dataPath": "params_shard_139.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.34.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "1736dfc6f44c1526cf5269717e652ee9"
},
{
"dataPath": "params_shard_140.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.35.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "11a40fedb22e8039a4d4b80802e50799"
},
{
"dataPath": "params_shard_141.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.35.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "b82a2f372f71f0c8ba9566f9b649a122"
},
{
"dataPath": "params_shard_142.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.35.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "3f28bd08ebb5a569bcf250566125a127"
},
{
"dataPath": "params_shard_143.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.35.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "2b8e71e8cbfb9c028aa9c37bb5187996"
},
{
"dataPath": "params_shard_144.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.36.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "fb63bcebad83cddfdcc7ebb6b6ce001e"
},
{
"dataPath": "params_shard_145.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.36.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "998c3107a311c58cc3e4073baa67ba3e"
},
{
"dataPath": "params_shard_146.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.36.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "4254aef7628f56aa1db691602141a32b"
},
{
"dataPath": "params_shard_147.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.36.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "510fe1408f7428fe9f4e48a439c0657a"
},
{
"dataPath": "params_shard_148.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.37.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "6cf6b29487c36868d8f0013329dbb88c"
},
{
"dataPath": "params_shard_149.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.37.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "4a66560596e750ea4aad672a6cdcb19a"
},
{
"dataPath": "params_shard_150.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.37.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "f87da3a39a357986ebda85e58de13874"
},
{
"dataPath": "params_shard_151.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.37.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "e8268e857f61732efce76ba06052defa"
},
{
"dataPath": "params_shard_152.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.38.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "690f46f958f29f03aea04fa91c78acef"
},
{
"dataPath": "params_shard_153.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.38.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "f383013565431de65663c2f326694ba4"
},
{
"dataPath": "params_shard_154.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.38.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "9f7e52bbc01fa6b41cdc9168dc0fb4e6"
},
{
"dataPath": "params_shard_155.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.38.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "b30ec7172aeb908fd96aed2256266307"
},
{
"dataPath": "params_shard_156.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.39.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "be48bf252a3ba49f4abe4cb329e4d267"
},
{
"dataPath": "params_shard_157.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.39.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "edca94a308a12145951c1c47dfeb85b7"
},
{
"dataPath": "params_shard_158.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.39.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "35ede895bcee52d8cb940700a25e6411"
},
{
"dataPath": "params_shard_159.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.39.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "8fe5f72299eb0ae0bf6a259994eb942e"
},
{
"dataPath": "params_shard_160.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.40.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "30e3b926898b749c4b449cea79dacd1b"
},
{
"dataPath": "params_shard_161.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.40.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "904eb89418f24a172dcd605ae5a1e1c2"
},
{
"dataPath": "params_shard_162.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.40.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "ed84ca297f4dad191ba79a1327f7b56d"
},
{
"dataPath": "params_shard_163.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.40.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "0e56979db7a565d41ee3191b0d821b82"
},
{
"dataPath": "params_shard_164.bin",
"format": "raw-shard",
"nbytes": 102760448,
"records": [
{
"name": "model.layers.41.mlp.down_proj.weight",
"shape": [
3584,
14336
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 102760448,
"byteOffset": 0
}
],
"md5sum": "d597a158f1307bdda0a2f1985dd93a87"
},
{
"dataPath": "params_shard_165.bin",
"format": "raw-shard",
"nbytes": 205520896,
"records": [
{
"name": "model.layers.41.mlp.gate_up_proj.weight",
"shape": [
28672,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 205520896,
"byteOffset": 0
}
],
"md5sum": "d8988bd2dddbbbe7747efcdc31ef3434"
},
{
"dataPath": "params_shard_166.bin",
"format": "raw-shard",
"nbytes": 58720256,
"records": [
{
"name": "model.layers.41.self_attn.qkv_proj.weight",
"shape": [
8192,
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 58720256,
"byteOffset": 0
}
],
"md5sum": "1ea64ada5980978eb52a70c59d2d7a7a"
},
{
"dataPath": "params_shard_167.bin",
"format": "raw-shard",
"nbytes": 29360128,
"records": [
{
"name": "model.layers.41.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 0
}
],
"md5sum": "b920fdb64688b8af7383d96ed8267ba0"
},
{
"dataPath": "params_shard_168.bin",
"format": "raw-shard",
"nbytes": 30571520,
"records": [
{
"name": "model.layers.0.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 0
},
{
"name": "model.layers.0.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 7168
},
{
"name": "model.layers.0.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 14336
},
{
"name": "model.layers.0.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 21504
},
{
"name": "model.layers.0.self_attn.o_proj.weight",
"shape": [
3584,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 29360128,
"byteOffset": 28672
},
{
"name": "model.layers.1.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29388800
},
{
"name": "model.layers.1.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29395968
},
{
"name": "model.layers.1.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29403136
},
{
"name": "model.layers.1.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29410304
},
{
"name": "model.layers.2.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29417472
},
{
"name": "model.layers.2.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29424640
},
{
"name": "model.layers.2.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29431808
},
{
"name": "model.layers.2.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29438976
},
{
"name": "model.layers.3.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29446144
},
{
"name": "model.layers.3.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29453312
},
{
"name": "model.layers.3.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29460480
},
{
"name": "model.layers.3.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29467648
},
{
"name": "model.layers.4.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29474816
},
{
"name": "model.layers.4.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29481984
},
{
"name": "model.layers.4.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29489152
},
{
"name": "model.layers.4.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29496320
},
{
"name": "model.layers.5.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29503488
},
{
"name": "model.layers.5.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29510656
},
{
"name": "model.layers.5.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29517824
},
{
"name": "model.layers.5.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29524992
},
{
"name": "model.layers.6.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29532160
},
{
"name": "model.layers.6.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29539328
},
{
"name": "model.layers.6.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29546496
},
{
"name": "model.layers.6.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29553664
},
{
"name": "model.layers.10.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29560832
},
{
"name": "model.layers.10.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29568000
},
{
"name": "model.layers.10.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29575168
},
{
"name": "model.layers.10.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29582336
},
{
"name": "model.layers.11.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29589504
},
{
"name": "model.layers.11.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29596672
},
{
"name": "model.layers.11.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29603840
},
{
"name": "model.layers.11.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29611008
},
{
"name": "model.layers.12.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29618176
},
{
"name": "model.layers.12.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29625344
},
{
"name": "model.layers.12.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29632512
},
{
"name": "model.layers.12.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29639680
},
{
"name": "model.layers.13.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29646848
},
{
"name": "model.layers.13.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29654016
},
{
"name": "model.layers.13.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29661184
},
{
"name": "model.layers.13.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29668352
},
{
"name": "model.layers.14.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29675520
},
{
"name": "model.layers.14.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29682688
},
{
"name": "model.layers.14.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29689856
},
{
"name": "model.layers.14.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29697024
},
{
"name": "model.layers.15.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29704192
},
{
"name": "model.layers.15.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29711360
},
{
"name": "model.layers.15.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29718528
},
{
"name": "model.layers.15.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29725696
},
{
"name": "model.layers.16.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29732864
},
{
"name": "model.layers.16.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29740032
},
{
"name": "model.layers.16.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29747200
},
{
"name": "model.layers.16.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29754368
},
{
"name": "model.layers.17.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29761536
},
{
"name": "model.layers.17.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29768704
},
{
"name": "model.layers.17.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29775872
},
{
"name": "model.layers.17.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29783040
},
{
"name": "model.layers.18.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29790208
},
{
"name": "model.layers.18.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29797376
},
{
"name": "model.layers.18.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29804544
},
{
"name": "model.layers.18.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29811712
},
{
"name": "model.layers.19.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29818880
},
{
"name": "model.layers.19.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29826048
},
{
"name": "model.layers.19.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29833216
},
{
"name": "model.layers.19.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29840384
},
{
"name": "model.layers.7.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29847552
},
{
"name": "model.layers.7.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29854720
},
{
"name": "model.layers.7.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29861888
},
{
"name": "model.layers.7.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29869056
},
{
"name": "model.layers.8.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29876224
},
{
"name": "model.layers.8.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29883392
},
{
"name": "model.layers.8.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29890560
},
{
"name": "model.layers.8.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29897728
},
{
"name": "model.layers.9.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29904896
},
{
"name": "model.layers.9.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29912064
},
{
"name": "model.layers.9.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29919232
},
{
"name": "model.layers.9.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29926400
},
{
"name": "model.layers.20.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29933568
},
{
"name": "model.layers.20.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29940736
},
{
"name": "model.layers.20.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29947904
},
{
"name": "model.layers.20.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29955072
},
{
"name": "model.layers.21.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29962240
},
{
"name": "model.layers.21.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29969408
},
{
"name": "model.layers.21.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29976576
},
{
"name": "model.layers.21.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29983744
},
{
"name": "model.layers.22.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29990912
},
{
"name": "model.layers.22.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 29998080
},
{
"name": "model.layers.22.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30005248
},
{
"name": "model.layers.22.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30012416
},
{
"name": "model.layers.23.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30019584
},
{
"name": "model.layers.23.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30026752
},
{
"name": "model.layers.23.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30033920
},
{
"name": "model.layers.23.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30041088
},
{
"name": "model.layers.24.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30048256
},
{
"name": "model.layers.24.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30055424
},
{
"name": "model.layers.24.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30062592
},
{
"name": "model.layers.24.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30069760
},
{
"name": "model.layers.25.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30076928
},
{
"name": "model.layers.25.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30084096
},
{
"name": "model.layers.25.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30091264
},
{
"name": "model.layers.25.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30098432
},
{
"name": "model.layers.26.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30105600
},
{
"name": "model.layers.26.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30112768
},
{
"name": "model.layers.26.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30119936
},
{
"name": "model.layers.26.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30127104
},
{
"name": "model.layers.27.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30134272
},
{
"name": "model.layers.27.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30141440
},
{
"name": "model.layers.27.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30148608
},
{
"name": "model.layers.27.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30155776
},
{
"name": "model.layers.28.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30162944
},
{
"name": "model.layers.28.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30170112
},
{
"name": "model.layers.28.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30177280
},
{
"name": "model.layers.28.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30184448
},
{
"name": "model.layers.29.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30191616
},
{
"name": "model.layers.29.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30198784
},
{
"name": "model.layers.29.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30205952
},
{
"name": "model.layers.29.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30213120
},
{
"name": "model.layers.30.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30220288
},
{
"name": "model.layers.30.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30227456
},
{
"name": "model.layers.30.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30234624
},
{
"name": "model.layers.30.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30241792
},
{
"name": "model.layers.31.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30248960
},
{
"name": "model.layers.31.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30256128
},
{
"name": "model.layers.31.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30263296
},
{
"name": "model.layers.31.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30270464
},
{
"name": "model.layers.32.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30277632
},
{
"name": "model.layers.32.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30284800
},
{
"name": "model.layers.32.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30291968
},
{
"name": "model.layers.32.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30299136
},
{
"name": "model.layers.33.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30306304
},
{
"name": "model.layers.33.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30313472
},
{
"name": "model.layers.33.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30320640
},
{
"name": "model.layers.33.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30327808
},
{
"name": "model.layers.34.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30334976
},
{
"name": "model.layers.34.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30342144
},
{
"name": "model.layers.34.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30349312
},
{
"name": "model.layers.34.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30356480
},
{
"name": "model.layers.35.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30363648
},
{
"name": "model.layers.35.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30370816
},
{
"name": "model.layers.35.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30377984
},
{
"name": "model.layers.35.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30385152
},
{
"name": "model.layers.36.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30392320
},
{
"name": "model.layers.36.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30399488
},
{
"name": "model.layers.36.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30406656
},
{
"name": "model.layers.36.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30413824
},
{
"name": "model.layers.37.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30420992
},
{
"name": "model.layers.37.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30428160
},
{
"name": "model.layers.37.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30435328
},
{
"name": "model.layers.37.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30442496
},
{
"name": "model.layers.38.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30449664
},
{
"name": "model.layers.38.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30456832
},
{
"name": "model.layers.38.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30464000
},
{
"name": "model.layers.38.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30471168
},
{
"name": "model.layers.39.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30478336
},
{
"name": "model.layers.39.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30485504
},
{
"name": "model.layers.39.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30492672
},
{
"name": "model.layers.39.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30499840
},
{
"name": "model.layers.40.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30507008
},
{
"name": "model.layers.40.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30514176
},
{
"name": "model.layers.40.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30521344
},
{
"name": "model.layers.40.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30528512
},
{
"name": "model.layers.41.input_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30535680
},
{
"name": "model.layers.41.post_attention_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30542848
},
{
"name": "model.layers.41.post_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30550016
},
{
"name": "model.layers.41.pre_feedforward_layernorm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30557184
},
{
"name": "model.norm.weight",
"shape": [
3584
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 7168,
"byteOffset": 30564352
}
],
"md5sum": "3f1c421ad2a85e17049eeb94b0adb027"
}
]
}