svdllama-2b-q0f16 / ndarray-cache.json
Samiul's picture
Upload 93 files
1c5ed93 verified
{
"metadata": {
"ParamSize": 515,
"ParamBytes": 3113836544.0,
"BitsPerParam": 15.999978953322415
},
"records": [
{
"dataPath": "params_shard_0.bin",
"format": "raw-shard",
"nbytes": 262144000,
"records": [
{
"name": "lm_head.weight",
"shape": [
32000,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144000,
"byteOffset": 0
}
],
"md5sum": "d6b7f632d45a6671e86edd191d6060ea"
},
{
"dataPath": "params_shard_1.bin",
"format": "raw-shard",
"nbytes": 262144000,
"records": [
{
"name": "model.embed_tokens.weight",
"shape": [
32000,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 262144000,
"byteOffset": 0
}
],
"md5sum": "f1f601338a702fe42b2da79aa982284a"
},
{
"dataPath": "params_shard_2.bin",
"format": "raw-shard",
"nbytes": 31185920,
"records": [
{
"name": "model.layers.0.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 0
},
{
"name": "model.layers.0.mlp.down_u_proj.weight",
"shape": [
4096,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 8192
},
{
"name": "model.layers.0.mlp.down_v_proj.weight",
"shape": [
597,
11008
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 4898816
},
{
"name": "model.layers.0.mlp.gate_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 18042368
}
],
"md5sum": "a2c309341b6f92f7a66f87d95d5ee4cc"
},
{
"dataPath": "params_shard_3.bin",
"format": "raw-shard",
"nbytes": 32984576,
"records": [
{
"name": "model.layers.0.mlp.gate_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 0
},
{
"name": "model.layers.0.mlp.up_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 4890624
},
{
"name": "model.layers.0.mlp.up_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 18034176
},
{
"name": "model.layers.0.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22924800
},
{
"name": "model.layers.0.self_attn.k_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 22932992
},
{
"name": "model.layers.0.self_attn.k_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 26283520
},
{
"name": "model.layers.0.self_attn.o_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 29634048
}
],
"md5sum": "74cb33d994820a882461f565a112446d"
},
{
"dataPath": "params_shard_4.bin",
"format": "raw-shard",
"nbytes": 21651456,
"records": [
{
"name": "model.layers.0.self_attn.o_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 0
},
{
"name": "model.layers.0.self_attn.q_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 3350528
},
{
"name": "model.layers.0.self_attn.q_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 6701056
},
{
"name": "model.layers.0.self_attn.v_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 10051584
},
{
"name": "model.layers.0.self_attn.v_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 13402112
},
{
"name": "model.layers.1.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 16752640
},
{
"name": "model.layers.1.mlp.down_u_proj.weight",
"shape": [
4096,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 16760832
}
],
"md5sum": "02d6a5c832c0edbfa27ba5a82b024d69"
},
{
"dataPath": "params_shard_5.bin",
"format": "raw-shard",
"nbytes": 31177728,
"records": [
{
"name": "model.layers.1.mlp.down_v_proj.weight",
"shape": [
597,
11008
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 0
},
{
"name": "model.layers.1.mlp.gate_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 13143552
},
{
"name": "model.layers.1.mlp.gate_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 26287104
}
],
"md5sum": "bd073b40f60915a902cb4eb0d6e3e105"
},
{
"dataPath": "params_shard_6.bin",
"format": "raw-shard",
"nbytes": 31444480,
"records": [
{
"name": "model.layers.1.mlp.up_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 0
},
{
"name": "model.layers.1.mlp.up_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 13143552
},
{
"name": "model.layers.1.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 18034176
},
{
"name": "model.layers.1.self_attn.k_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 18042368
},
{
"name": "model.layers.1.self_attn.k_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 21392896
},
{
"name": "model.layers.1.self_attn.o_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 24743424
},
{
"name": "model.layers.1.self_attn.o_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 28093952
}
],
"md5sum": "672939c072a2902c6e0aa7439425aa3f"
},
{
"dataPath": "params_shard_7.bin",
"format": "raw-shard",
"nbytes": 31444480,
"records": [
{
"name": "model.layers.1.self_attn.q_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 0
},
{
"name": "model.layers.1.self_attn.q_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 3350528
},
{
"name": "model.layers.1.self_attn.v_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 6701056
},
{
"name": "model.layers.1.self_attn.v_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 10051584
},
{
"name": "model.layers.10.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 13402112
},
{
"name": "model.layers.10.mlp.down_u_proj.weight",
"shape": [
4096,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 13410304
},
{
"name": "model.layers.10.mlp.down_v_proj.weight",
"shape": [
597,
11008
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 18300928
}
],
"md5sum": "4b7487811f4d53e9baff1049fc581663"
},
{
"dataPath": "params_shard_8.bin",
"format": "raw-shard",
"nbytes": 31177728,
"records": [
{
"name": "model.layers.10.mlp.gate_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 0
},
{
"name": "model.layers.10.mlp.gate_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 13143552
},
{
"name": "model.layers.10.mlp.up_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 18034176
}
],
"md5sum": "84bbabc0c592e9da35bc7cb8522ef572"
},
{
"dataPath": "params_shard_9.bin",
"format": "raw-shard",
"nbytes": 31711232,
"records": [
{
"name": "model.layers.10.mlp.up_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 0
},
{
"name": "model.layers.10.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 4890624
},
{
"name": "model.layers.10.self_attn.k_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 4898816
},
{
"name": "model.layers.10.self_attn.k_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 8249344
},
{
"name": "model.layers.10.self_attn.o_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 11599872
},
{
"name": "model.layers.10.self_attn.o_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 14950400
},
{
"name": "model.layers.10.self_attn.q_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 18300928
},
{
"name": "model.layers.10.self_attn.q_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 21651456
},
{
"name": "model.layers.10.self_attn.v_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 25001984
},
{
"name": "model.layers.10.self_attn.v_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 28352512
},
{
"name": "model.layers.11.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 31703040
}
],
"md5sum": "a52a26cc016afd299ca310b48a2c80a6"
},
{
"dataPath": "params_shard_10.bin",
"format": "raw-shard",
"nbytes": 31177728,
"records": [
{
"name": "model.layers.11.mlp.down_u_proj.weight",
"shape": [
4096,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 0
},
{
"name": "model.layers.11.mlp.down_v_proj.weight",
"shape": [
597,
11008
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 4890624
},
{
"name": "model.layers.11.mlp.gate_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 18034176
}
],
"md5sum": "708db4cbbff185544ea56b89c9fef65c"
},
{
"dataPath": "params_shard_11.bin",
"format": "raw-shard",
"nbytes": 32984576,
"records": [
{
"name": "model.layers.11.mlp.gate_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 0
},
{
"name": "model.layers.11.mlp.up_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 4890624
},
{
"name": "model.layers.11.mlp.up_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 18034176
},
{
"name": "model.layers.11.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22924800
},
{
"name": "model.layers.11.self_attn.k_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 22932992
},
{
"name": "model.layers.11.self_attn.k_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 26283520
},
{
"name": "model.layers.11.self_attn.o_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 29634048
}
],
"md5sum": "bbcacd48a84ca2c440345ea3c64bfd88"
},
{
"dataPath": "params_shard_12.bin",
"format": "raw-shard",
"nbytes": 21651456,
"records": [
{
"name": "model.layers.11.self_attn.o_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 0
},
{
"name": "model.layers.11.self_attn.q_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 3350528
},
{
"name": "model.layers.11.self_attn.q_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 6701056
},
{
"name": "model.layers.11.self_attn.v_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 10051584
},
{
"name": "model.layers.11.self_attn.v_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 13402112
},
{
"name": "model.layers.12.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 16752640
},
{
"name": "model.layers.12.mlp.down_u_proj.weight",
"shape": [
4096,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 16760832
}
],
"md5sum": "87a74739226e315a3191e2c5422d0c3a"
},
{
"dataPath": "params_shard_13.bin",
"format": "raw-shard",
"nbytes": 31177728,
"records": [
{
"name": "model.layers.12.mlp.down_v_proj.weight",
"shape": [
597,
11008
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 0
},
{
"name": "model.layers.12.mlp.gate_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 13143552
},
{
"name": "model.layers.12.mlp.gate_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 26287104
}
],
"md5sum": "2a91e6c9a1fe1d610ad0fc9e96216c3f"
},
{
"dataPath": "params_shard_14.bin",
"format": "raw-shard",
"nbytes": 31444480,
"records": [
{
"name": "model.layers.12.mlp.up_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 0
},
{
"name": "model.layers.12.mlp.up_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 13143552
},
{
"name": "model.layers.12.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 18034176
},
{
"name": "model.layers.12.self_attn.k_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 18042368
},
{
"name": "model.layers.12.self_attn.k_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 21392896
},
{
"name": "model.layers.12.self_attn.o_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 24743424
},
{
"name": "model.layers.12.self_attn.o_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 28093952
}
],
"md5sum": "b5d3198162fd6663a4230742ec65a700"
},
{
"dataPath": "params_shard_15.bin",
"format": "raw-shard",
"nbytes": 31444480,
"records": [
{
"name": "model.layers.12.self_attn.q_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 0
},
{
"name": "model.layers.12.self_attn.q_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 3350528
},
{
"name": "model.layers.12.self_attn.v_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 6701056
},
{
"name": "model.layers.12.self_attn.v_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 10051584
},
{
"name": "model.layers.13.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 13402112
},
{
"name": "model.layers.13.mlp.down_u_proj.weight",
"shape": [
4096,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 13410304
},
{
"name": "model.layers.13.mlp.down_v_proj.weight",
"shape": [
597,
11008
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 18300928
}
],
"md5sum": "7170783734e2faf2aaea72c80fff2a97"
},
{
"dataPath": "params_shard_16.bin",
"format": "raw-shard",
"nbytes": 31177728,
"records": [
{
"name": "model.layers.13.mlp.gate_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 0
},
{
"name": "model.layers.13.mlp.gate_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 13143552
},
{
"name": "model.layers.13.mlp.up_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 18034176
}
],
"md5sum": "cfad63403be6542cf8a253d563389665"
},
{
"dataPath": "params_shard_17.bin",
"format": "raw-shard",
"nbytes": 31711232,
"records": [
{
"name": "model.layers.13.mlp.up_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 0
},
{
"name": "model.layers.13.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 4890624
},
{
"name": "model.layers.13.self_attn.k_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 4898816
},
{
"name": "model.layers.13.self_attn.k_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 8249344
},
{
"name": "model.layers.13.self_attn.o_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 11599872
},
{
"name": "model.layers.13.self_attn.o_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 14950400
},
{
"name": "model.layers.13.self_attn.q_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 18300928
},
{
"name": "model.layers.13.self_attn.q_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 21651456
},
{
"name": "model.layers.13.self_attn.v_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 25001984
},
{
"name": "model.layers.13.self_attn.v_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 28352512
},
{
"name": "model.layers.14.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 31703040
}
],
"md5sum": "35c79b3a2f53d8e339bd9559642ea977"
},
{
"dataPath": "params_shard_18.bin",
"format": "raw-shard",
"nbytes": 31177728,
"records": [
{
"name": "model.layers.14.mlp.down_u_proj.weight",
"shape": [
4096,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 0
},
{
"name": "model.layers.14.mlp.down_v_proj.weight",
"shape": [
597,
11008
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 4890624
},
{
"name": "model.layers.14.mlp.gate_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 18034176
}
],
"md5sum": "cec546777db34df6d862a2e795be6357"
},
{
"dataPath": "params_shard_19.bin",
"format": "raw-shard",
"nbytes": 32984576,
"records": [
{
"name": "model.layers.14.mlp.gate_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 0
},
{
"name": "model.layers.14.mlp.up_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 4890624
},
{
"name": "model.layers.14.mlp.up_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 18034176
},
{
"name": "model.layers.14.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22924800
},
{
"name": "model.layers.14.self_attn.k_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 22932992
},
{
"name": "model.layers.14.self_attn.k_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 26283520
},
{
"name": "model.layers.14.self_attn.o_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 29634048
}
],
"md5sum": "12d5170ae607a79cc1f68c0c31f0dd4f"
},
{
"dataPath": "params_shard_20.bin",
"format": "raw-shard",
"nbytes": 21651456,
"records": [
{
"name": "model.layers.14.self_attn.o_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 0
},
{
"name": "model.layers.14.self_attn.q_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 3350528
},
{
"name": "model.layers.14.self_attn.q_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 6701056
},
{
"name": "model.layers.14.self_attn.v_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 10051584
},
{
"name": "model.layers.14.self_attn.v_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 13402112
},
{
"name": "model.layers.15.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 16752640
},
{
"name": "model.layers.15.mlp.down_u_proj.weight",
"shape": [
4096,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 16760832
}
],
"md5sum": "d40c21ca01469d68f0eb3385cf5a7214"
},
{
"dataPath": "params_shard_21.bin",
"format": "raw-shard",
"nbytes": 31177728,
"records": [
{
"name": "model.layers.15.mlp.down_v_proj.weight",
"shape": [
597,
11008
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 0
},
{
"name": "model.layers.15.mlp.gate_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 13143552
},
{
"name": "model.layers.15.mlp.gate_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 26287104
}
],
"md5sum": "b31b3e10a28acea04be7cdf20b26c032"
},
{
"dataPath": "params_shard_22.bin",
"format": "raw-shard",
"nbytes": 31444480,
"records": [
{
"name": "model.layers.15.mlp.up_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 0
},
{
"name": "model.layers.15.mlp.up_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 13143552
},
{
"name": "model.layers.15.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 18034176
},
{
"name": "model.layers.15.self_attn.k_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 18042368
},
{
"name": "model.layers.15.self_attn.k_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 21392896
},
{
"name": "model.layers.15.self_attn.o_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 24743424
},
{
"name": "model.layers.15.self_attn.o_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 28093952
}
],
"md5sum": "a209d2de01d5fd039297f1425b0753d0"
},
{
"dataPath": "params_shard_23.bin",
"format": "raw-shard",
"nbytes": 31444480,
"records": [
{
"name": "model.layers.15.self_attn.q_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 0
},
{
"name": "model.layers.15.self_attn.q_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 3350528
},
{
"name": "model.layers.15.self_attn.v_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 6701056
},
{
"name": "model.layers.15.self_attn.v_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 10051584
},
{
"name": "model.layers.16.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 13402112
},
{
"name": "model.layers.16.mlp.down_u_proj.weight",
"shape": [
4096,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 13410304
},
{
"name": "model.layers.16.mlp.down_v_proj.weight",
"shape": [
597,
11008
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 18300928
}
],
"md5sum": "bf1fbc7a6e18744237fa4e364c295d38"
},
{
"dataPath": "params_shard_24.bin",
"format": "raw-shard",
"nbytes": 31177728,
"records": [
{
"name": "model.layers.16.mlp.gate_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 0
},
{
"name": "model.layers.16.mlp.gate_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 13143552
},
{
"name": "model.layers.16.mlp.up_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 18034176
}
],
"md5sum": "c23e3ed48549710ce8e7df8c2f1ce145"
},
{
"dataPath": "params_shard_25.bin",
"format": "raw-shard",
"nbytes": 31711232,
"records": [
{
"name": "model.layers.16.mlp.up_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 0
},
{
"name": "model.layers.16.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 4890624
},
{
"name": "model.layers.16.self_attn.k_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 4898816
},
{
"name": "model.layers.16.self_attn.k_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 8249344
},
{
"name": "model.layers.16.self_attn.o_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 11599872
},
{
"name": "model.layers.16.self_attn.o_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 14950400
},
{
"name": "model.layers.16.self_attn.q_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 18300928
},
{
"name": "model.layers.16.self_attn.q_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 21651456
},
{
"name": "model.layers.16.self_attn.v_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 25001984
},
{
"name": "model.layers.16.self_attn.v_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 28352512
},
{
"name": "model.layers.17.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 31703040
}
],
"md5sum": "88daa14ac30802e48cbc8b1e27daf245"
},
{
"dataPath": "params_shard_26.bin",
"format": "raw-shard",
"nbytes": 31177728,
"records": [
{
"name": "model.layers.17.mlp.down_u_proj.weight",
"shape": [
4096,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 0
},
{
"name": "model.layers.17.mlp.down_v_proj.weight",
"shape": [
597,
11008
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 4890624
},
{
"name": "model.layers.17.mlp.gate_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 18034176
}
],
"md5sum": "279ee6f7d0b67213bcd59374b95f3cff"
},
{
"dataPath": "params_shard_27.bin",
"format": "raw-shard",
"nbytes": 32984576,
"records": [
{
"name": "model.layers.17.mlp.gate_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 0
},
{
"name": "model.layers.17.mlp.up_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 4890624
},
{
"name": "model.layers.17.mlp.up_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 18034176
},
{
"name": "model.layers.17.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22924800
},
{
"name": "model.layers.17.self_attn.k_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 22932992
},
{
"name": "model.layers.17.self_attn.k_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 26283520
},
{
"name": "model.layers.17.self_attn.o_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 29634048
}
],
"md5sum": "69f81e742f76579be2ffc067fc9c4c8a"
},
{
"dataPath": "params_shard_28.bin",
"format": "raw-shard",
"nbytes": 21651456,
"records": [
{
"name": "model.layers.17.self_attn.o_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 0
},
{
"name": "model.layers.17.self_attn.q_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 3350528
},
{
"name": "model.layers.17.self_attn.q_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 6701056
},
{
"name": "model.layers.17.self_attn.v_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 10051584
},
{
"name": "model.layers.17.self_attn.v_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 13402112
},
{
"name": "model.layers.18.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 16752640
},
{
"name": "model.layers.18.mlp.down_u_proj.weight",
"shape": [
4096,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 16760832
}
],
"md5sum": "0bc0522920469ad7321a1617b56bdd30"
},
{
"dataPath": "params_shard_29.bin",
"format": "raw-shard",
"nbytes": 31177728,
"records": [
{
"name": "model.layers.18.mlp.down_v_proj.weight",
"shape": [
597,
11008
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 0
},
{
"name": "model.layers.18.mlp.gate_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 13143552
},
{
"name": "model.layers.18.mlp.gate_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 26287104
}
],
"md5sum": "bdd49c0e9c6216a2834419b9d665f36f"
},
{
"dataPath": "params_shard_30.bin",
"format": "raw-shard",
"nbytes": 31444480,
"records": [
{
"name": "model.layers.18.mlp.up_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 0
},
{
"name": "model.layers.18.mlp.up_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 13143552
},
{
"name": "model.layers.18.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 18034176
},
{
"name": "model.layers.18.self_attn.k_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 18042368
},
{
"name": "model.layers.18.self_attn.k_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 21392896
},
{
"name": "model.layers.18.self_attn.o_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 24743424
},
{
"name": "model.layers.18.self_attn.o_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 28093952
}
],
"md5sum": "f1023a561304234c113f798a26b97c47"
},
{
"dataPath": "params_shard_31.bin",
"format": "raw-shard",
"nbytes": 31444480,
"records": [
{
"name": "model.layers.18.self_attn.q_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 0
},
{
"name": "model.layers.18.self_attn.q_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 3350528
},
{
"name": "model.layers.18.self_attn.v_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 6701056
},
{
"name": "model.layers.18.self_attn.v_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 10051584
},
{
"name": "model.layers.19.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 13402112
},
{
"name": "model.layers.19.mlp.down_u_proj.weight",
"shape": [
4096,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 13410304
},
{
"name": "model.layers.19.mlp.down_v_proj.weight",
"shape": [
597,
11008
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 18300928
}
],
"md5sum": "fd6c4270fb400cf630a7451612ee3161"
},
{
"dataPath": "params_shard_32.bin",
"format": "raw-shard",
"nbytes": 31177728,
"records": [
{
"name": "model.layers.19.mlp.gate_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 0
},
{
"name": "model.layers.19.mlp.gate_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 13143552
},
{
"name": "model.layers.19.mlp.up_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 18034176
}
],
"md5sum": "b38c039e985056b415e175cc5a3ae9f9"
},
{
"dataPath": "params_shard_33.bin",
"format": "raw-shard",
"nbytes": 31711232,
"records": [
{
"name": "model.layers.19.mlp.up_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 0
},
{
"name": "model.layers.19.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 4890624
},
{
"name": "model.layers.19.self_attn.k_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 4898816
},
{
"name": "model.layers.19.self_attn.k_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 8249344
},
{
"name": "model.layers.19.self_attn.o_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 11599872
},
{
"name": "model.layers.19.self_attn.o_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 14950400
},
{
"name": "model.layers.19.self_attn.q_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 18300928
},
{
"name": "model.layers.19.self_attn.q_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 21651456
},
{
"name": "model.layers.19.self_attn.v_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 25001984
},
{
"name": "model.layers.19.self_attn.v_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 28352512
},
{
"name": "model.layers.2.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 31703040
}
],
"md5sum": "20e5253ed5574af013f70bbccd160aed"
},
{
"dataPath": "params_shard_34.bin",
"format": "raw-shard",
"nbytes": 31177728,
"records": [
{
"name": "model.layers.2.mlp.down_u_proj.weight",
"shape": [
4096,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 0
},
{
"name": "model.layers.2.mlp.down_v_proj.weight",
"shape": [
597,
11008
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 4890624
},
{
"name": "model.layers.2.mlp.gate_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 18034176
}
],
"md5sum": "5444d28508918f98e1993a55f7b53634"
},
{
"dataPath": "params_shard_35.bin",
"format": "raw-shard",
"nbytes": 32984576,
"records": [
{
"name": "model.layers.2.mlp.gate_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 0
},
{
"name": "model.layers.2.mlp.up_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 4890624
},
{
"name": "model.layers.2.mlp.up_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 18034176
},
{
"name": "model.layers.2.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22924800
},
{
"name": "model.layers.2.self_attn.k_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 22932992
},
{
"name": "model.layers.2.self_attn.k_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 26283520
},
{
"name": "model.layers.2.self_attn.o_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 29634048
}
],
"md5sum": "d937c6dcc9e1954a5aabf65ca0bcdde2"
},
{
"dataPath": "params_shard_36.bin",
"format": "raw-shard",
"nbytes": 21651456,
"records": [
{
"name": "model.layers.2.self_attn.o_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 0
},
{
"name": "model.layers.2.self_attn.q_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 3350528
},
{
"name": "model.layers.2.self_attn.q_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 6701056
},
{
"name": "model.layers.2.self_attn.v_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 10051584
},
{
"name": "model.layers.2.self_attn.v_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 13402112
},
{
"name": "model.layers.20.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 16752640
},
{
"name": "model.layers.20.mlp.down_u_proj.weight",
"shape": [
4096,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 16760832
}
],
"md5sum": "3fe3dfc7378c773e67f69b7fbd7a5e97"
},
{
"dataPath": "params_shard_37.bin",
"format": "raw-shard",
"nbytes": 31177728,
"records": [
{
"name": "model.layers.20.mlp.down_v_proj.weight",
"shape": [
597,
11008
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 0
},
{
"name": "model.layers.20.mlp.gate_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 13143552
},
{
"name": "model.layers.20.mlp.gate_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 26287104
}
],
"md5sum": "7e8f1ee604bec9d97d09203b1b936bad"
},
{
"dataPath": "params_shard_38.bin",
"format": "raw-shard",
"nbytes": 31444480,
"records": [
{
"name": "model.layers.20.mlp.up_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 0
},
{
"name": "model.layers.20.mlp.up_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 13143552
},
{
"name": "model.layers.20.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 18034176
},
{
"name": "model.layers.20.self_attn.k_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 18042368
},
{
"name": "model.layers.20.self_attn.k_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 21392896
},
{
"name": "model.layers.20.self_attn.o_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 24743424
},
{
"name": "model.layers.20.self_attn.o_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 28093952
}
],
"md5sum": "8cca9ab2959eb6aebc4ae2991d5c2352"
},
{
"dataPath": "params_shard_39.bin",
"format": "raw-shard",
"nbytes": 31444480,
"records": [
{
"name": "model.layers.20.self_attn.q_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 0
},
{
"name": "model.layers.20.self_attn.q_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 3350528
},
{
"name": "model.layers.20.self_attn.v_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 6701056
},
{
"name": "model.layers.20.self_attn.v_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 10051584
},
{
"name": "model.layers.21.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 13402112
},
{
"name": "model.layers.21.mlp.down_u_proj.weight",
"shape": [
4096,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 13410304
},
{
"name": "model.layers.21.mlp.down_v_proj.weight",
"shape": [
597,
11008
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 18300928
}
],
"md5sum": "b843fd1bb9db48685c1259775af898ae"
},
{
"dataPath": "params_shard_40.bin",
"format": "raw-shard",
"nbytes": 31177728,
"records": [
{
"name": "model.layers.21.mlp.gate_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 0
},
{
"name": "model.layers.21.mlp.gate_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 13143552
},
{
"name": "model.layers.21.mlp.up_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 18034176
}
],
"md5sum": "4c3b64b326cf90c744859cbb42988196"
},
{
"dataPath": "params_shard_41.bin",
"format": "raw-shard",
"nbytes": 31711232,
"records": [
{
"name": "model.layers.21.mlp.up_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 0
},
{
"name": "model.layers.21.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 4890624
},
{
"name": "model.layers.21.self_attn.k_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 4898816
},
{
"name": "model.layers.21.self_attn.k_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 8249344
},
{
"name": "model.layers.21.self_attn.o_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 11599872
},
{
"name": "model.layers.21.self_attn.o_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 14950400
},
{
"name": "model.layers.21.self_attn.q_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 18300928
},
{
"name": "model.layers.21.self_attn.q_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 21651456
},
{
"name": "model.layers.21.self_attn.v_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 25001984
},
{
"name": "model.layers.21.self_attn.v_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 28352512
},
{
"name": "model.layers.22.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 31703040
}
],
"md5sum": "062da27f3dd90de90f240b7a51fd5e17"
},
{
"dataPath": "params_shard_42.bin",
"format": "raw-shard",
"nbytes": 31177728,
"records": [
{
"name": "model.layers.22.mlp.down_u_proj.weight",
"shape": [
4096,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 0
},
{
"name": "model.layers.22.mlp.down_v_proj.weight",
"shape": [
597,
11008
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 4890624
},
{
"name": "model.layers.22.mlp.gate_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 18034176
}
],
"md5sum": "c73820029523815e1d57efa4be8e7bd6"
},
{
"dataPath": "params_shard_43.bin",
"format": "raw-shard",
"nbytes": 32984576,
"records": [
{
"name": "model.layers.22.mlp.gate_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 0
},
{
"name": "model.layers.22.mlp.up_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 4890624
},
{
"name": "model.layers.22.mlp.up_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 18034176
},
{
"name": "model.layers.22.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22924800
},
{
"name": "model.layers.22.self_attn.k_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 22932992
},
{
"name": "model.layers.22.self_attn.k_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 26283520
},
{
"name": "model.layers.22.self_attn.o_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 29634048
}
],
"md5sum": "97c188b65c9132581f6e2649f242f2c2"
},
{
"dataPath": "params_shard_44.bin",
"format": "raw-shard",
"nbytes": 21651456,
"records": [
{
"name": "model.layers.22.self_attn.o_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 0
},
{
"name": "model.layers.22.self_attn.q_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 3350528
},
{
"name": "model.layers.22.self_attn.q_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 6701056
},
{
"name": "model.layers.22.self_attn.v_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 10051584
},
{
"name": "model.layers.22.self_attn.v_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 13402112
},
{
"name": "model.layers.23.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 16752640
},
{
"name": "model.layers.23.mlp.down_u_proj.weight",
"shape": [
4096,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 16760832
}
],
"md5sum": "9e243fbe3f836bfa9c2e15b17988e2ef"
},
{
"dataPath": "params_shard_45.bin",
"format": "raw-shard",
"nbytes": 31177728,
"records": [
{
"name": "model.layers.23.mlp.down_v_proj.weight",
"shape": [
597,
11008
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 0
},
{
"name": "model.layers.23.mlp.gate_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 13143552
},
{
"name": "model.layers.23.mlp.gate_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 26287104
}
],
"md5sum": "d41f6b5c7c6aa1c9d78dd22d1ee69d14"
},
{
"dataPath": "params_shard_46.bin",
"format": "raw-shard",
"nbytes": 31444480,
"records": [
{
"name": "model.layers.23.mlp.up_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 0
},
{
"name": "model.layers.23.mlp.up_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 13143552
},
{
"name": "model.layers.23.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 18034176
},
{
"name": "model.layers.23.self_attn.k_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 18042368
},
{
"name": "model.layers.23.self_attn.k_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 21392896
},
{
"name": "model.layers.23.self_attn.o_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 24743424
},
{
"name": "model.layers.23.self_attn.o_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 28093952
}
],
"md5sum": "a4113ccc711ed3c8cc583481502c9297"
},
{
"dataPath": "params_shard_47.bin",
"format": "raw-shard",
"nbytes": 31444480,
"records": [
{
"name": "model.layers.23.self_attn.q_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 0
},
{
"name": "model.layers.23.self_attn.q_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 3350528
},
{
"name": "model.layers.23.self_attn.v_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 6701056
},
{
"name": "model.layers.23.self_attn.v_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 10051584
},
{
"name": "model.layers.24.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 13402112
},
{
"name": "model.layers.24.mlp.down_u_proj.weight",
"shape": [
4096,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 13410304
},
{
"name": "model.layers.24.mlp.down_v_proj.weight",
"shape": [
597,
11008
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 18300928
}
],
"md5sum": "58ffb0e3518122ee109ffcc4466ca87c"
},
{
"dataPath": "params_shard_48.bin",
"format": "raw-shard",
"nbytes": 31177728,
"records": [
{
"name": "model.layers.24.mlp.gate_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 0
},
{
"name": "model.layers.24.mlp.gate_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 13143552
},
{
"name": "model.layers.24.mlp.up_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 18034176
}
],
"md5sum": "15e847cc5432f2c798dda91bfde09cd9"
},
{
"dataPath": "params_shard_49.bin",
"format": "raw-shard",
"nbytes": 31711232,
"records": [
{
"name": "model.layers.24.mlp.up_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 0
},
{
"name": "model.layers.24.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 4890624
},
{
"name": "model.layers.24.self_attn.k_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 4898816
},
{
"name": "model.layers.24.self_attn.k_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 8249344
},
{
"name": "model.layers.24.self_attn.o_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 11599872
},
{
"name": "model.layers.24.self_attn.o_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 14950400
},
{
"name": "model.layers.24.self_attn.q_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 18300928
},
{
"name": "model.layers.24.self_attn.q_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 21651456
},
{
"name": "model.layers.24.self_attn.v_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 25001984
},
{
"name": "model.layers.24.self_attn.v_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 28352512
},
{
"name": "model.layers.25.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 31703040
}
],
"md5sum": "ca41030a3a756e44b1bee4a62ace4a4d"
},
{
"dataPath": "params_shard_50.bin",
"format": "raw-shard",
"nbytes": 31177728,
"records": [
{
"name": "model.layers.25.mlp.down_u_proj.weight",
"shape": [
4096,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 0
},
{
"name": "model.layers.25.mlp.down_v_proj.weight",
"shape": [
597,
11008
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 4890624
},
{
"name": "model.layers.25.mlp.gate_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 18034176
}
],
"md5sum": "e4b49b6d02c3a30dd0048387a4c48e39"
},
{
"dataPath": "params_shard_51.bin",
"format": "raw-shard",
"nbytes": 32984576,
"records": [
{
"name": "model.layers.25.mlp.gate_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 0
},
{
"name": "model.layers.25.mlp.up_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 4890624
},
{
"name": "model.layers.25.mlp.up_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 18034176
},
{
"name": "model.layers.25.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22924800
},
{
"name": "model.layers.25.self_attn.k_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 22932992
},
{
"name": "model.layers.25.self_attn.k_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 26283520
},
{
"name": "model.layers.25.self_attn.o_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 29634048
}
],
"md5sum": "e0dc2558ee0a07ddcb68dd3fc064381b"
},
{
"dataPath": "params_shard_52.bin",
"format": "raw-shard",
"nbytes": 21651456,
"records": [
{
"name": "model.layers.25.self_attn.o_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 0
},
{
"name": "model.layers.25.self_attn.q_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 3350528
},
{
"name": "model.layers.25.self_attn.q_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 6701056
},
{
"name": "model.layers.25.self_attn.v_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 10051584
},
{
"name": "model.layers.25.self_attn.v_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 13402112
},
{
"name": "model.layers.26.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 16752640
},
{
"name": "model.layers.26.mlp.down_u_proj.weight",
"shape": [
4096,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 16760832
}
],
"md5sum": "c1494547270a1205b4d495c2e89ced57"
},
{
"dataPath": "params_shard_53.bin",
"format": "raw-shard",
"nbytes": 31177728,
"records": [
{
"name": "model.layers.26.mlp.down_v_proj.weight",
"shape": [
597,
11008
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 0
},
{
"name": "model.layers.26.mlp.gate_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 13143552
},
{
"name": "model.layers.26.mlp.gate_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 26287104
}
],
"md5sum": "a93f6484c29528ef6dc4f565437909b5"
},
{
"dataPath": "params_shard_54.bin",
"format": "raw-shard",
"nbytes": 31444480,
"records": [
{
"name": "model.layers.26.mlp.up_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 0
},
{
"name": "model.layers.26.mlp.up_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 13143552
},
{
"name": "model.layers.26.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 18034176
},
{
"name": "model.layers.26.self_attn.k_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 18042368
},
{
"name": "model.layers.26.self_attn.k_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 21392896
},
{
"name": "model.layers.26.self_attn.o_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 24743424
},
{
"name": "model.layers.26.self_attn.o_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 28093952
}
],
"md5sum": "a8c0b04f363d25047d651a6dfee91d7c"
},
{
"dataPath": "params_shard_55.bin",
"format": "raw-shard",
"nbytes": 31444480,
"records": [
{
"name": "model.layers.26.self_attn.q_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 0
},
{
"name": "model.layers.26.self_attn.q_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 3350528
},
{
"name": "model.layers.26.self_attn.v_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 6701056
},
{
"name": "model.layers.26.self_attn.v_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 10051584
},
{
"name": "model.layers.27.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 13402112
},
{
"name": "model.layers.27.mlp.down_u_proj.weight",
"shape": [
4096,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 13410304
},
{
"name": "model.layers.27.mlp.down_v_proj.weight",
"shape": [
597,
11008
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 18300928
}
],
"md5sum": "6d7a0ca642a50370cb4c4d68171c1205"
},
{
"dataPath": "params_shard_56.bin",
"format": "raw-shard",
"nbytes": 31177728,
"records": [
{
"name": "model.layers.27.mlp.gate_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 0
},
{
"name": "model.layers.27.mlp.gate_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 13143552
},
{
"name": "model.layers.27.mlp.up_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 18034176
}
],
"md5sum": "31a9e1e7ba3a53941836b32c1a7d5eae"
},
{
"dataPath": "params_shard_57.bin",
"format": "raw-shard",
"nbytes": 31711232,
"records": [
{
"name": "model.layers.27.mlp.up_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 0
},
{
"name": "model.layers.27.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 4890624
},
{
"name": "model.layers.27.self_attn.k_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 4898816
},
{
"name": "model.layers.27.self_attn.k_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 8249344
},
{
"name": "model.layers.27.self_attn.o_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 11599872
},
{
"name": "model.layers.27.self_attn.o_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 14950400
},
{
"name": "model.layers.27.self_attn.q_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 18300928
},
{
"name": "model.layers.27.self_attn.q_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 21651456
},
{
"name": "model.layers.27.self_attn.v_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 25001984
},
{
"name": "model.layers.27.self_attn.v_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 28352512
},
{
"name": "model.layers.28.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 31703040
}
],
"md5sum": "a3b8b11108e7d0932f23b6e513fbe883"
},
{
"dataPath": "params_shard_58.bin",
"format": "raw-shard",
"nbytes": 31177728,
"records": [
{
"name": "model.layers.28.mlp.down_u_proj.weight",
"shape": [
4096,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 0
},
{
"name": "model.layers.28.mlp.down_v_proj.weight",
"shape": [
597,
11008
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 4890624
},
{
"name": "model.layers.28.mlp.gate_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 18034176
}
],
"md5sum": "4d2f4f61db2a4efce2b2b9fec8603766"
},
{
"dataPath": "params_shard_59.bin",
"format": "raw-shard",
"nbytes": 32984576,
"records": [
{
"name": "model.layers.28.mlp.gate_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 0
},
{
"name": "model.layers.28.mlp.up_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 4890624
},
{
"name": "model.layers.28.mlp.up_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 18034176
},
{
"name": "model.layers.28.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22924800
},
{
"name": "model.layers.28.self_attn.k_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 22932992
},
{
"name": "model.layers.28.self_attn.k_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 26283520
},
{
"name": "model.layers.28.self_attn.o_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 29634048
}
],
"md5sum": "1ede05179d3b38d8f2c1f39c78c92646"
},
{
"dataPath": "params_shard_60.bin",
"format": "raw-shard",
"nbytes": 21651456,
"records": [
{
"name": "model.layers.28.self_attn.o_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 0
},
{
"name": "model.layers.28.self_attn.q_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 3350528
},
{
"name": "model.layers.28.self_attn.q_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 6701056
},
{
"name": "model.layers.28.self_attn.v_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 10051584
},
{
"name": "model.layers.28.self_attn.v_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 13402112
},
{
"name": "model.layers.29.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 16752640
},
{
"name": "model.layers.29.mlp.down_u_proj.weight",
"shape": [
4096,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 16760832
}
],
"md5sum": "c605132b0b74e040a0428f86176e5876"
},
{
"dataPath": "params_shard_61.bin",
"format": "raw-shard",
"nbytes": 31177728,
"records": [
{
"name": "model.layers.29.mlp.down_v_proj.weight",
"shape": [
597,
11008
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 0
},
{
"name": "model.layers.29.mlp.gate_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 13143552
},
{
"name": "model.layers.29.mlp.gate_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 26287104
}
],
"md5sum": "7590e5886a948c7e58f0847fcc21f459"
},
{
"dataPath": "params_shard_62.bin",
"format": "raw-shard",
"nbytes": 31444480,
"records": [
{
"name": "model.layers.29.mlp.up_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 0
},
{
"name": "model.layers.29.mlp.up_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 13143552
},
{
"name": "model.layers.29.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 18034176
},
{
"name": "model.layers.29.self_attn.k_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 18042368
},
{
"name": "model.layers.29.self_attn.k_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 21392896
},
{
"name": "model.layers.29.self_attn.o_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 24743424
},
{
"name": "model.layers.29.self_attn.o_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 28093952
}
],
"md5sum": "0e90d44477934797458513a30b333ddf"
},
{
"dataPath": "params_shard_63.bin",
"format": "raw-shard",
"nbytes": 31444480,
"records": [
{
"name": "model.layers.29.self_attn.q_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 0
},
{
"name": "model.layers.29.self_attn.q_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 3350528
},
{
"name": "model.layers.29.self_attn.v_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 6701056
},
{
"name": "model.layers.29.self_attn.v_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 10051584
},
{
"name": "model.layers.3.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 13402112
},
{
"name": "model.layers.3.mlp.down_u_proj.weight",
"shape": [
4096,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 13410304
},
{
"name": "model.layers.3.mlp.down_v_proj.weight",
"shape": [
597,
11008
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 18300928
}
],
"md5sum": "580fc3bb5cdc621c2053e4462b62ea59"
},
{
"dataPath": "params_shard_64.bin",
"format": "raw-shard",
"nbytes": 31177728,
"records": [
{
"name": "model.layers.3.mlp.gate_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 0
},
{
"name": "model.layers.3.mlp.gate_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 13143552
},
{
"name": "model.layers.3.mlp.up_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 18034176
}
],
"md5sum": "41fdc06a0f78d20e370aca6a47543395"
},
{
"dataPath": "params_shard_65.bin",
"format": "raw-shard",
"nbytes": 31711232,
"records": [
{
"name": "model.layers.3.mlp.up_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 0
},
{
"name": "model.layers.3.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 4890624
},
{
"name": "model.layers.3.self_attn.k_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 4898816
},
{
"name": "model.layers.3.self_attn.k_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 8249344
},
{
"name": "model.layers.3.self_attn.o_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 11599872
},
{
"name": "model.layers.3.self_attn.o_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 14950400
},
{
"name": "model.layers.3.self_attn.q_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 18300928
},
{
"name": "model.layers.3.self_attn.q_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 21651456
},
{
"name": "model.layers.3.self_attn.v_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 25001984
},
{
"name": "model.layers.3.self_attn.v_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 28352512
},
{
"name": "model.layers.30.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 31703040
}
],
"md5sum": "f45d637d4ce3c0bc8db6f33d6504a4d4"
},
{
"dataPath": "params_shard_66.bin",
"format": "raw-shard",
"nbytes": 31177728,
"records": [
{
"name": "model.layers.30.mlp.down_u_proj.weight",
"shape": [
4096,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 0
},
{
"name": "model.layers.30.mlp.down_v_proj.weight",
"shape": [
597,
11008
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 4890624
},
{
"name": "model.layers.30.mlp.gate_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 18034176
}
],
"md5sum": "c13c81cb995fc9a14dd3d526179933b8"
},
{
"dataPath": "params_shard_67.bin",
"format": "raw-shard",
"nbytes": 32984576,
"records": [
{
"name": "model.layers.30.mlp.gate_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 0
},
{
"name": "model.layers.30.mlp.up_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 4890624
},
{
"name": "model.layers.30.mlp.up_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 18034176
},
{
"name": "model.layers.30.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22924800
},
{
"name": "model.layers.30.self_attn.k_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 22932992
},
{
"name": "model.layers.30.self_attn.k_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 26283520
},
{
"name": "model.layers.30.self_attn.o_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 29634048
}
],
"md5sum": "df6f70b0abbcad87d1ee51e1d05d5870"
},
{
"dataPath": "params_shard_68.bin",
"format": "raw-shard",
"nbytes": 21651456,
"records": [
{
"name": "model.layers.30.self_attn.o_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 0
},
{
"name": "model.layers.30.self_attn.q_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 3350528
},
{
"name": "model.layers.30.self_attn.q_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 6701056
},
{
"name": "model.layers.30.self_attn.v_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 10051584
},
{
"name": "model.layers.30.self_attn.v_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 13402112
},
{
"name": "model.layers.31.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 16752640
},
{
"name": "model.layers.31.mlp.down_u_proj.weight",
"shape": [
4096,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 16760832
}
],
"md5sum": "c48d2a6e9870500d78158dbdb08e2615"
},
{
"dataPath": "params_shard_69.bin",
"format": "raw-shard",
"nbytes": 31177728,
"records": [
{
"name": "model.layers.31.mlp.down_v_proj.weight",
"shape": [
597,
11008
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 0
},
{
"name": "model.layers.31.mlp.gate_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 13143552
},
{
"name": "model.layers.31.mlp.gate_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 26287104
}
],
"md5sum": "d95b5b9539551725921ee1564b58a219"
},
{
"dataPath": "params_shard_70.bin",
"format": "raw-shard",
"nbytes": 31444480,
"records": [
{
"name": "model.layers.31.mlp.up_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 0
},
{
"name": "model.layers.31.mlp.up_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 13143552
},
{
"name": "model.layers.31.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 18034176
},
{
"name": "model.layers.31.self_attn.k_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 18042368
},
{
"name": "model.layers.31.self_attn.k_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 21392896
},
{
"name": "model.layers.31.self_attn.o_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 24743424
},
{
"name": "model.layers.31.self_attn.o_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 28093952
}
],
"md5sum": "7bd17c62e69114fa2e833d453f9a934d"
},
{
"dataPath": "params_shard_71.bin",
"format": "raw-shard",
"nbytes": 31444480,
"records": [
{
"name": "model.layers.31.self_attn.q_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 0
},
{
"name": "model.layers.31.self_attn.q_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 3350528
},
{
"name": "model.layers.31.self_attn.v_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 6701056
},
{
"name": "model.layers.31.self_attn.v_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 10051584
},
{
"name": "model.layers.4.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 13402112
},
{
"name": "model.layers.4.mlp.down_u_proj.weight",
"shape": [
4096,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 13410304
},
{
"name": "model.layers.4.mlp.down_v_proj.weight",
"shape": [
597,
11008
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 18300928
}
],
"md5sum": "d0671c084da6adf38f1e4adaadde50fa"
},
{
"dataPath": "params_shard_72.bin",
"format": "raw-shard",
"nbytes": 31177728,
"records": [
{
"name": "model.layers.4.mlp.gate_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 0
},
{
"name": "model.layers.4.mlp.gate_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 13143552
},
{
"name": "model.layers.4.mlp.up_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 18034176
}
],
"md5sum": "418416b96275adf9da88b8f4b51be9a2"
},
{
"dataPath": "params_shard_73.bin",
"format": "raw-shard",
"nbytes": 31711232,
"records": [
{
"name": "model.layers.4.mlp.up_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 0
},
{
"name": "model.layers.4.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 4890624
},
{
"name": "model.layers.4.self_attn.k_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 4898816
},
{
"name": "model.layers.4.self_attn.k_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 8249344
},
{
"name": "model.layers.4.self_attn.o_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 11599872
},
{
"name": "model.layers.4.self_attn.o_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 14950400
},
{
"name": "model.layers.4.self_attn.q_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 18300928
},
{
"name": "model.layers.4.self_attn.q_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 21651456
},
{
"name": "model.layers.4.self_attn.v_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 25001984
},
{
"name": "model.layers.4.self_attn.v_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 28352512
},
{
"name": "model.layers.5.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 31703040
}
],
"md5sum": "38686d17036dc8ab7c11fc929bef0a85"
},
{
"dataPath": "params_shard_74.bin",
"format": "raw-shard",
"nbytes": 31177728,
"records": [
{
"name": "model.layers.5.mlp.down_u_proj.weight",
"shape": [
4096,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 0
},
{
"name": "model.layers.5.mlp.down_v_proj.weight",
"shape": [
597,
11008
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 4890624
},
{
"name": "model.layers.5.mlp.gate_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 18034176
}
],
"md5sum": "a8e69006295013c2276a8670d83892be"
},
{
"dataPath": "params_shard_75.bin",
"format": "raw-shard",
"nbytes": 32984576,
"records": [
{
"name": "model.layers.5.mlp.gate_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 0
},
{
"name": "model.layers.5.mlp.up_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 4890624
},
{
"name": "model.layers.5.mlp.up_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 18034176
},
{
"name": "model.layers.5.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22924800
},
{
"name": "model.layers.5.self_attn.k_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 22932992
},
{
"name": "model.layers.5.self_attn.k_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 26283520
},
{
"name": "model.layers.5.self_attn.o_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 29634048
}
],
"md5sum": "d8908f635b17a786593a73e8039501f3"
},
{
"dataPath": "params_shard_76.bin",
"format": "raw-shard",
"nbytes": 21651456,
"records": [
{
"name": "model.layers.5.self_attn.o_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 0
},
{
"name": "model.layers.5.self_attn.q_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 3350528
},
{
"name": "model.layers.5.self_attn.q_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 6701056
},
{
"name": "model.layers.5.self_attn.v_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 10051584
},
{
"name": "model.layers.5.self_attn.v_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 13402112
},
{
"name": "model.layers.6.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 16752640
},
{
"name": "model.layers.6.mlp.down_u_proj.weight",
"shape": [
4096,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 16760832
}
],
"md5sum": "8db2f2b7aceecab34436bf861303b1bd"
},
{
"dataPath": "params_shard_77.bin",
"format": "raw-shard",
"nbytes": 31177728,
"records": [
{
"name": "model.layers.6.mlp.down_v_proj.weight",
"shape": [
597,
11008
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 0
},
{
"name": "model.layers.6.mlp.gate_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 13143552
},
{
"name": "model.layers.6.mlp.gate_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 26287104
}
],
"md5sum": "a410a494734a7b554369d6ba6175f3ef"
},
{
"dataPath": "params_shard_78.bin",
"format": "raw-shard",
"nbytes": 31444480,
"records": [
{
"name": "model.layers.6.mlp.up_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 0
},
{
"name": "model.layers.6.mlp.up_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 13143552
},
{
"name": "model.layers.6.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 18034176
},
{
"name": "model.layers.6.self_attn.k_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 18042368
},
{
"name": "model.layers.6.self_attn.k_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 21392896
},
{
"name": "model.layers.6.self_attn.o_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 24743424
},
{
"name": "model.layers.6.self_attn.o_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 28093952
}
],
"md5sum": "3da4a28a4873a678fe78cb3682b1f0b5"
},
{
"dataPath": "params_shard_79.bin",
"format": "raw-shard",
"nbytes": 31444480,
"records": [
{
"name": "model.layers.6.self_attn.q_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 0
},
{
"name": "model.layers.6.self_attn.q_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 3350528
},
{
"name": "model.layers.6.self_attn.v_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 6701056
},
{
"name": "model.layers.6.self_attn.v_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 10051584
},
{
"name": "model.layers.7.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 13402112
},
{
"name": "model.layers.7.mlp.down_u_proj.weight",
"shape": [
4096,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 13410304
},
{
"name": "model.layers.7.mlp.down_v_proj.weight",
"shape": [
597,
11008
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 18300928
}
],
"md5sum": "0eae1a6a3b53684e554c1eba00e5efe1"
},
{
"dataPath": "params_shard_80.bin",
"format": "raw-shard",
"nbytes": 31177728,
"records": [
{
"name": "model.layers.7.mlp.gate_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 0
},
{
"name": "model.layers.7.mlp.gate_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 13143552
},
{
"name": "model.layers.7.mlp.up_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 18034176
}
],
"md5sum": "969196cd4e35e0d04b2cf6a69911e619"
},
{
"dataPath": "params_shard_81.bin",
"format": "raw-shard",
"nbytes": 31711232,
"records": [
{
"name": "model.layers.7.mlp.up_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 0
},
{
"name": "model.layers.7.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 4890624
},
{
"name": "model.layers.7.self_attn.k_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 4898816
},
{
"name": "model.layers.7.self_attn.k_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 8249344
},
{
"name": "model.layers.7.self_attn.o_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 11599872
},
{
"name": "model.layers.7.self_attn.o_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 14950400
},
{
"name": "model.layers.7.self_attn.q_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 18300928
},
{
"name": "model.layers.7.self_attn.q_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 21651456
},
{
"name": "model.layers.7.self_attn.v_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 25001984
},
{
"name": "model.layers.7.self_attn.v_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 28352512
},
{
"name": "model.layers.8.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 31703040
}
],
"md5sum": "cee6d7c9d529aaee0673ea892c7a0737"
},
{
"dataPath": "params_shard_82.bin",
"format": "raw-shard",
"nbytes": 31177728,
"records": [
{
"name": "model.layers.8.mlp.down_u_proj.weight",
"shape": [
4096,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 0
},
{
"name": "model.layers.8.mlp.down_v_proj.weight",
"shape": [
597,
11008
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 4890624
},
{
"name": "model.layers.8.mlp.gate_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 18034176
}
],
"md5sum": "acfc453a9f63d2f75260072cb05532a3"
},
{
"dataPath": "params_shard_83.bin",
"format": "raw-shard",
"nbytes": 32984576,
"records": [
{
"name": "model.layers.8.mlp.gate_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 0
},
{
"name": "model.layers.8.mlp.up_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 4890624
},
{
"name": "model.layers.8.mlp.up_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 18034176
},
{
"name": "model.layers.8.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 22924800
},
{
"name": "model.layers.8.self_attn.k_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 22932992
},
{
"name": "model.layers.8.self_attn.k_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 26283520
},
{
"name": "model.layers.8.self_attn.o_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 29634048
}
],
"md5sum": "c59b33d0c8da494bda9e3bad7b57e0d9"
},
{
"dataPath": "params_shard_84.bin",
"format": "raw-shard",
"nbytes": 21651456,
"records": [
{
"name": "model.layers.8.self_attn.o_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 0
},
{
"name": "model.layers.8.self_attn.q_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 3350528
},
{
"name": "model.layers.8.self_attn.q_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 6701056
},
{
"name": "model.layers.8.self_attn.v_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 10051584
},
{
"name": "model.layers.8.self_attn.v_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 13402112
},
{
"name": "model.layers.9.input_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 16752640
},
{
"name": "model.layers.9.mlp.down_u_proj.weight",
"shape": [
4096,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 16760832
}
],
"md5sum": "22fb82602164dca0d0e0aebd852308d4"
},
{
"dataPath": "params_shard_85.bin",
"format": "raw-shard",
"nbytes": 31177728,
"records": [
{
"name": "model.layers.9.mlp.down_v_proj.weight",
"shape": [
597,
11008
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 0
},
{
"name": "model.layers.9.mlp.gate_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 13143552
},
{
"name": "model.layers.9.mlp.gate_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 26287104
}
],
"md5sum": "4c5153db8c4de673635340afe44f913d"
},
{
"dataPath": "params_shard_86.bin",
"format": "raw-shard",
"nbytes": 31444480,
"records": [
{
"name": "model.layers.9.mlp.up_u_proj.weight",
"shape": [
11008,
597
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 13143552,
"byteOffset": 0
},
{
"name": "model.layers.9.mlp.up_v_proj.weight",
"shape": [
597,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 4890624,
"byteOffset": 13143552
},
{
"name": "model.layers.9.post_attention_layernorm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 18034176
},
{
"name": "model.layers.9.self_attn.k_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 18042368
},
{
"name": "model.layers.9.self_attn.k_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 21392896
},
{
"name": "model.layers.9.self_attn.o_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 24743424
},
{
"name": "model.layers.9.self_attn.o_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 28093952
}
],
"md5sum": "cd5b839ac8515b00a683d19d441590ce"
},
{
"dataPath": "params_shard_87.bin",
"format": "raw-shard",
"nbytes": 13410304,
"records": [
{
"name": "model.layers.9.self_attn.q_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 0
},
{
"name": "model.layers.9.self_attn.q_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 3350528
},
{
"name": "model.layers.9.self_attn.v_u_proj.weight",
"shape": [
4096,
409
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 6701056
},
{
"name": "model.layers.9.self_attn.v_v_proj.weight",
"shape": [
409,
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 3350528,
"byteOffset": 10051584
},
{
"name": "model.norm.weight",
"shape": [
4096
],
"dtype": "float16",
"format": "f32-to-bf16",
"nbytes": 8192,
"byteOffset": 13402112
}
],
"md5sum": "e78ef78f9da1a4eaf3d26e3bba25e80d"
}
]
}