{ "metadata": { "ParamSize": 405, "ParamBytes": 6889973760.0, "BitsPerParam": 3.749252192749517 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 335544320, "records": [ { "name": "lm_head.q_weight", "shape": [ 131072, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 335544320, "byteOffset": 0 } ], "md5sum": "5ad2ae98a54286809e4e7de620f9b4be" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "lm_head.q_scale", "shape": [ 131072, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "9ed39a05bf743ad901066559536f80bc" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.33.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "8b4fa88afd65f0452d0437888c16c571" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "0d0406511b5d7c8dd384d5c9c5badbaa" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.34.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "1eb5c6af5ea3f9f460b8d7ccdab5c0cd" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "ffabf6132eebf9d7c4aeb79c5e522ffa" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 27566080, "records": [ { "name": "model.layers.33.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 0 }, { "name": "model.layers.33.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 10240 }, { "name": "model.layers.33.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 4597760 }, { "name": "model.layers.33.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13772800 }, { "name": "model.layers.34.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13783040 }, { "name": "model.layers.34.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 13793280 }, { "name": "model.layers.34.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 18380800 }, { "name": "model.layers.34.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 27555840 } ], "md5sum": "87d9f07ed51f2c33210e970afe628e56" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.35.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "a43ac17ed56efe85c68170a4133d202e" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 29501440, "records": [ { "name": "model.layers.34.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "model.layers.34.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 15728640 }, { "name": "model.layers.34.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 17694720 }, { "name": "model.layers.34.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 28180480 }, { "name": "model.layers.35.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 29491200 } ], "md5sum": "8d3ce0e5cfdd231f49bacd224ad17da4" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "e56b4bea08df0472c34ea81fece47ab4" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 31467520, "records": [ { "name": "model.layers.35.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 0 }, { "name": "model.layers.35.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 4587520 }, { "name": "model.layers.35.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13762560 }, { "name": "model.layers.35.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 13772800 }, { "name": "model.layers.35.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 29501440 } ], "md5sum": "939a7c0478f1a4db38d05a23c59bc3e8" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.36.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "095c72dd4909ac0d5c57f8c0b171176d" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "c0fbf077d2f88257fa7022d862b0dedf" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 25579520, "records": [ { "name": "model.layers.35.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.35.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.36.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.36.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 11806720 }, { "name": "model.layers.36.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 16394240 }, { "name": "model.layers.36.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 25569280 } ], "md5sum": "ee57132e382268d0cd1ac41409b242ce" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.37.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "09c0589c5bce61d0fa32af05be81c43e" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 29501440, "records": [ { "name": "model.layers.36.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "model.layers.36.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 15728640 }, { "name": "model.layers.36.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 17694720 }, { "name": "model.layers.36.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 28180480 }, { "name": "model.layers.37.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 29491200 } ], "md5sum": "c1f670bbbcf284e0e1c2b9c8b7c59394" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.37.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "42fc16c94c8211c8400ce31140e9f3f4" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 31467520, "records": [ { "name": "model.layers.37.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 0 }, { "name": "model.layers.37.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 4587520 }, { "name": "model.layers.37.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13762560 }, { "name": "model.layers.37.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 13772800 }, { "name": "model.layers.37.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 29501440 } ], "md5sum": "bda23b49c3a8965ac772bcc4f37a8001" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.38.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "b2ea2679165aeb43fae785f6f29fc57a" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "79f2b58d07ba97e0a3e95348d8935a6c" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 25579520, "records": [ { "name": "model.layers.37.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.37.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.38.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.38.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 11806720 }, { "name": "model.layers.38.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 16394240 }, { "name": "model.layers.38.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 25569280 } ], "md5sum": "521300ef039a142ed9a594d6010b2d91" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.39.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "2eef6f785fc2b8cdddcf9e4f1d2e1f7b" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 29501440, "records": [ { "name": "model.layers.38.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "model.layers.38.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 15728640 }, { "name": "model.layers.38.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 17694720 }, { "name": "model.layers.38.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 28180480 }, { "name": "model.layers.39.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 29491200 } ], "md5sum": "6bdeb66a368c563ca4e961c067d7dcb3" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.39.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "41252e03ff287def0c2ecb01716698a4" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 31467520, "records": [ { "name": "model.layers.39.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 0 }, { "name": "model.layers.39.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 4587520 }, { "name": "model.layers.39.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13762560 }, { "name": "model.layers.39.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 13772800 }, { "name": "model.layers.39.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 29501440 } ], "md5sum": "1b370f247ff95b04d2c86d820e3f43ac" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 335544320, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 131072, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 335544320, "byteOffset": 0 } ], "md5sum": "40ad319ba2ec8d5bc15d68585d6456fb" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 131072, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "1c0a6b70578fa907bf211788c218c48b" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "2428f09790faea2bdeb52e9ea674584a" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "1f2fd420b9be62b8fc3404b2204f6970" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 25589760, "records": [ { "name": "model.layers.39.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.39.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.norm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11806720 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 11816960 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 16404480 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 25579520 } ], "md5sum": "60dc3ef6b5bd692dde5b2d0c9e9ec4fb" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "b43b604c47aa2769b3d54f3fd9134d7b" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 29501440, "records": [ { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 15728640 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 17694720 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 28180480 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 29491200 } ], "md5sum": "ac930b7237604d076852e3953aa7974b" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "9ef9d991652e69b9e25ed0e1c9ead07c" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 31467520, "records": [ { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 0 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 4587520 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13762560 }, { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 13772800 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 29501440 } ], "md5sum": "564e433263f17b7635f0adfed27bb236" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "ba3777fc784476006ccfa862d03a93f4" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "500b1680e3347a4b8a952cd7f802e95d" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 25579520, "records": [ { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 11806720 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 16394240 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 25569280 } ], "md5sum": "1fdec3b20d3aee02c398779fdb8db4a0" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "076a353e970acf90aa288a4572d67917" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 29501440, "records": [ { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 15728640 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 17694720 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 28180480 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 29491200 } ], "md5sum": "aee72c28a57450b1084949d1594361f2" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "78c40b93a375929ba33a2db7d55ab7d2" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 31467520, "records": [ { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 0 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 4587520 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13762560 }, { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 13772800 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 29501440 } ], "md5sum": "3fae5dc594cfdabc7f66436b9361c8aa" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "9d0fd321470cee319aa52c1a662b7b2a" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "02b4d5f28903efd67d876c97fb9b0e7b" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 25579520, "records": [ { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 11806720 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 16394240 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 25569280 } ], "md5sum": "96245d02a4935f1fdfbb92e1e82bf616" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "a4a6ded91507f7ba7d5c994d1ca77ac7" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 29501440, "records": [ { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 15728640 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 17694720 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 28180480 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 29491200 } ], "md5sum": "6669ec4d4a292faa20f0154f9f5afe23" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "d0286bec9873a37dec039b53fa4b8c10" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 31467520, "records": [ { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 0 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 4587520 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13762560 }, { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 13772800 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 29501440 } ], "md5sum": "9643698be58fd5156d532c3eb4613e5c" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "fe91ca023bfefd87391ffffc5a83db2e" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 11796480 } ], "md5sum": "e56610ad8be901c16739eb4d79a4e503" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "c937e609d63c9f174c365b413222fdbc" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 29501440, "records": [ { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 15728640 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 17694720 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 28180480 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 29491200 } ], "md5sum": "6a53fca12073ee7a8b0d03e3e8ef588c" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "1b538516942c47c42613d4bac49f77f9" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 31467520, "records": [ { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 0 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 4587520 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13762560 }, { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 13772800 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 29501440 } ], "md5sum": "ea553acb0ac09e4180996a4ddc5274c3" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "8f82d9e5ba54fb3ded5d8ad88fc6870f" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "779fb9857adcdbcb38ef71e7e293283e" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 25579520, "records": [ { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 11806720 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 16394240 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 25569280 } ], "md5sum": "1c7118e4ec3f95cf84e589a8b100489e" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "1f68eee05942032116390199eb49ba53" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 29501440, "records": [ { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 15728640 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 17694720 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 28180480 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 29491200 } ], "md5sum": "3e846099b78a7c159edf50b2d5354a3f" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "db24e3821d1e9397d8f05db0e8c2eecc" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 31467520, "records": [ { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 0 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 4587520 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13762560 }, { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 13772800 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 29501440 } ], "md5sum": "29d4ad890532dac7a0667489933efe1d" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "eb03654273c0e4db86994cbb71924e33" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "6720e675d691a21c4190400123b20744" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 25579520, "records": [ { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 11806720 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 16394240 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 25569280 } ], "md5sum": "792c7a76a60c1f53400c4a8f0f828740" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "b3dcb09b99a1f778220ae1e060177009" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 29501440, "records": [ { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 15728640 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 17694720 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 28180480 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 29491200 } ], "md5sum": "c0fa17a93535530fc11f78abf31ab1d0" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "ebcdea7db3e52507fd857cf2068ff0b5" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 31467520, "records": [ { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 0 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 4587520 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13762560 }, { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 13772800 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 29501440 } ], "md5sum": "63134a41b82d4cadb6229ee7c8bff8ca" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "37d694a67a98a5965772b3185369f706" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 11796480 } ], "md5sum": "fd72735b2a8e1766aaa576a8d6663ce5" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "87008a1871c13d45a0a4ce0c4c91176b" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 29501440, "records": [ { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 15728640 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 17694720 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 28180480 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 29491200 } ], "md5sum": "f739d004dbb5e5ae3b2ebfb45434fbac" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "cfb5e9c5f16ba705089f552a90870fc3" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "5e0e0ebb8bee35974ae3658249fb62e4" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 18380800, "records": [ { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 0 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 4587520 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 4597760 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 4608000 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 9195520 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 18370560 } ], "md5sum": "2b36e37ac720e97ac4ebac0a0cadfc9b" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "783c24f8236a5ef174846cfa8d40fb2a" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 29501440, "records": [ { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 15728640 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 17694720 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 28180480 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 29491200 } ], "md5sum": "5598b1c389731cb746f6b19d3c77123c" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "b75edc6a3f275e4a4b2903472702e1b6" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 31467520, "records": [ { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 0 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 4587520 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13762560 }, { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 13772800 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 29501440 } ], "md5sum": "7d8e89c3fd7faa7c0a5c3c527d01313b" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "c2946860518f7763b2e26485a8795aaa" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "a247c8cd5a6d8ef6aed7af84a0b6a295" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 25579520, "records": [ { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 11806720 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 16394240 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 25569280 } ], "md5sum": "3a6815839beb0828338c80ff25c86de4" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "971a3d88fe1db5bd289ddd680ed57170" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 29501440, "records": [ { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 15728640 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 17694720 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 28180480 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 29491200 } ], "md5sum": "334231e9804d2adb3b6541a00cf8b975" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "fc3cc5cbf1f9a6e766af2e9246a0dc1b" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "58ed23b868bba94dd075d9ef5341d4d5" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 18380800, "records": [ { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 0 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 4587520 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 4597760 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 4608000 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 9195520 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 18370560 } ], "md5sum": "42f86daf45c31523ac59556bc8fbe5d6" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "9213d62f07a4c68e723c98426f9aedc1" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 29501440, "records": [ { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 15728640 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 17694720 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 28180480 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 29491200 } ], "md5sum": "398ad73266a74146844dd5fc9fdeb5e5" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "047de9686a7489ccc91e1c46c9526ae8" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 31467520, "records": [ { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 0 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 4587520 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13762560 }, { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 13772800 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 29501440 } ], "md5sum": "7ab65a0aade78ef533a06e30c65425ad" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "ab7772b1652f45afbc500564b9dcece5" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "d404e13c87b7cb24b0ea81d7f897518d" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 25579520, "records": [ { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 11806720 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 16394240 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 25569280 } ], "md5sum": "e1853f18c12c4df1615ff7448fb9b011" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "45ec04a30ac83cf50463ba46665cbd06" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 29501440, "records": [ { "name": "model.layers.18.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 15728640 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 17694720 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 28180480 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 29491200 } ], "md5sum": "4c26e8615c964560c27b1163d811bbfe" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "378ad4e1f5420c58a6904d7edcbc0aa2" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 31467520, "records": [ { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 0 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 4587520 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13762560 }, { "name": "model.layers.19.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 13772800 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 29501440 } ], "md5sum": "8941541413e7de6f0c04de9376c5db22" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "60f6c299e9787a6b2895e2732b735404" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "16076bce096411c88222a900f506d3b6" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 25579520, "records": [ { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 11806720 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 16394240 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 25569280 } ], "md5sum": "3f6fafd3e75e7406cd7434cdac4f41aa" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "e84607509391787f6aeaad4373f1b5e9" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 29501440, "records": [ { "name": "model.layers.20.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 15728640 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 17694720 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 28180480 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 29491200 } ], "md5sum": "02e29d9668a59c44045cbc575e9783df" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "7f6d94f9124e9d2ce36b5bfcc9177706" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 31467520, "records": [ { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 0 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 4587520 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13762560 }, { "name": "model.layers.21.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 13772800 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 29501440 } ], "md5sum": "d9d81bab8d743c37c87e82fbab7a72c9" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "65882cf5661789ffe9d3c188dc34235e" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "3a1a325f4b64511eea2ce0ecd942b1b3" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 25579520, "records": [ { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 11806720 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 16394240 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 25569280 } ], "md5sum": "6ee9001c221f65a2a45f33df78399e23" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "0c401a5b69801e5541eb60c5344854f4" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 29501440, "records": [ { "name": "model.layers.22.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "model.layers.22.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 15728640 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 17694720 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 28180480 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 29491200 } ], "md5sum": "0b5a77c41b9cdc83bf857333ce68112e" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "e248e71e9d7a2e1b01f756bb3c648bb7" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 31467520, "records": [ { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 0 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 4587520 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13762560 }, { "name": "model.layers.23.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 13772800 }, { "name": "model.layers.23.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 29501440 } ], "md5sum": "7e39b2a8a7e1cfbf60e97678415bda20" }, { "dataPath": "params_shard_112.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "817dd9a4f76973848d76e98b34c08eaf" }, { "dataPath": "params_shard_113.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 11796480 } ], "md5sum": "572b5ccfff9110752629363789d1ba8b" }, { "dataPath": "params_shard_114.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "1cd59fd5e97a360edb3f9b2854858983" }, { "dataPath": "params_shard_115.bin", "format": "raw-shard", "nbytes": 29501440, "records": [ { "name": "model.layers.24.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "model.layers.24.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 15728640 }, { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 17694720 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 28180480 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 29491200 } ], "md5sum": "7c79c4ab320795c9b0a20eb58314efa4" }, { "dataPath": "params_shard_116.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "cf0d9463054fa29b11f717d50e59b553" }, { "dataPath": "params_shard_117.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "36e2bcfaa564e98288dd936c2835279e" }, { "dataPath": "params_shard_118.bin", "format": "raw-shard", "nbytes": 18380800, "records": [ { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 0 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 4587520 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 4597760 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 4608000 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 9195520 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 18370560 } ], "md5sum": "288842684545bcc5bd5edc2e3b2b7ba1" }, { "dataPath": "params_shard_119.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "bcefaa672100f0d80165b633efd989ab" }, { "dataPath": "params_shard_120.bin", "format": "raw-shard", "nbytes": 29501440, "records": [ { "name": "model.layers.25.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "model.layers.25.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 15728640 }, { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 17694720 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 28180480 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 29491200 } ], "md5sum": "a7489e3137d04beecf8d14fd7d726535" }, { "dataPath": "params_shard_121.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "8285efeb82cb135cc27f065534bc88f1" }, { "dataPath": "params_shard_122.bin", "format": "raw-shard", "nbytes": 31467520, "records": [ { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 0 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 4587520 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13762560 }, { "name": "model.layers.26.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 13772800 }, { "name": "model.layers.26.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 29501440 } ], "md5sum": "dc0b5343661fe8c1d0edefdf27940d5e" }, { "dataPath": "params_shard_123.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "4ac1c3f3930cf0bf03c790888276c816" }, { "dataPath": "params_shard_124.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "b1bd79a92478b0c79b3441f9af0499d3" }, { "dataPath": "params_shard_125.bin", "format": "raw-shard", "nbytes": 25579520, "records": [ { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 11806720 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 16394240 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 25569280 } ], "md5sum": "b2cee02cb666d4950731e2f4fb35699c" }, { "dataPath": "params_shard_126.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "21e0ff529eb0e54e914625b6f8932faa" }, { "dataPath": "params_shard_127.bin", "format": "raw-shard", "nbytes": 29501440, "records": [ { "name": "model.layers.27.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "model.layers.27.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 15728640 }, { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 17694720 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 28180480 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 29491200 } ], "md5sum": "d8f515fb8dc1b3c7aade7b31718eea76" }, { "dataPath": "params_shard_128.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "e58ef2a290e8a8ed9f4aca6cf121ba51" }, { "dataPath": "params_shard_129.bin", "format": "raw-shard", "nbytes": 31467520, "records": [ { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 0 }, { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 4587520 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13762560 }, { "name": "model.layers.28.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 13772800 }, { "name": "model.layers.28.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 29501440 } ], "md5sum": "fb2e427f642a128e370c31d83d5192be" }, { "dataPath": "params_shard_130.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "5156dafb3409f96472a6c8648b5d90fd" }, { "dataPath": "params_shard_131.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "e84a49ba364ed8998ead2b5c70c88662" }, { "dataPath": "params_shard_132.bin", "format": "raw-shard", "nbytes": 25579520, "records": [ { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 11806720 }, { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 16394240 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 25569280 } ], "md5sum": "5b05ac29ffeb0b1c74b75178fa973c24" }, { "dataPath": "params_shard_133.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "5c4fc7e676df5c7da55a87d25587c9d0" }, { "dataPath": "params_shard_134.bin", "format": "raw-shard", "nbytes": 29501440, "records": [ { "name": "model.layers.29.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "model.layers.29.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 15728640 }, { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 17694720 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 28180480 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 29491200 } ], "md5sum": "f80e8f9107d232318af0c2bbecab6115" }, { "dataPath": "params_shard_135.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "fa825d40492145f75cec39ae1912a49a" }, { "dataPath": "params_shard_136.bin", "format": "raw-shard", "nbytes": 31467520, "records": [ { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 0 }, { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 4587520 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13762560 }, { "name": "model.layers.30.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 13772800 }, { "name": "model.layers.30.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 29501440 } ], "md5sum": "49942dc716ecae284273e923d89ac223" }, { "dataPath": "params_shard_137.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "03ad439b22b0e337435452f036b3cda1" }, { "dataPath": "params_shard_138.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "f0f5298dffe52a299393532b3970f063" }, { "dataPath": "params_shard_139.bin", "format": "raw-shard", "nbytes": 25579520, "records": [ { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 11806720 }, { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 16394240 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 25569280 } ], "md5sum": "0fbd7d857d340f0d785cb39942d791a4" }, { "dataPath": "params_shard_140.bin", "format": "raw-shard", "nbytes": 36700160, "records": [ { "name": "model.layers.32.mlp.down_proj.q_weight", "shape": [ 5120, 1792 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 36700160, "byteOffset": 0 } ], "md5sum": "69a4873e8b2acb42ba7ed3535f44c84a" }, { "dataPath": "params_shard_141.bin", "format": "raw-shard", "nbytes": 29501440, "records": [ { "name": "model.layers.31.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 0 }, { "name": "model.layers.31.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 15728640 }, { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 17694720 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 28180480 }, { "name": "model.layers.32.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 29491200 } ], "md5sum": "a294c797a0dea6bdf4d6be7682db25ae" }, { "dataPath": "params_shard_142.bin", "format": "raw-shard", "nbytes": 73400320, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_weight", "shape": [ 28672, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 73400320, "byteOffset": 0 } ], "md5sum": "cdc586fa6c29deedd1fa32453070d9f4" }, { "dataPath": "params_shard_143.bin", "format": "raw-shard", "nbytes": 31467520, "records": [ { "name": "model.layers.32.mlp.down_proj.q_scale", "shape": [ 5120, 448 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4587520, "byteOffset": 0 }, { "name": "model.layers.32.mlp.gate_up_proj.q_scale", "shape": [ 28672, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9175040, "byteOffset": 4587520 }, { "name": "model.layers.32.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13762560 }, { "name": "model.layers.32.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 13772800 }, { "name": "model.layers.32.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 29501440 } ], "md5sum": "c74bbee9f9b0017b9fdb19e992737c5e" }, { "dataPath": "params_shard_144.bin", "format": "raw-shard", "nbytes": 29491200, "records": [ { "name": "model.layers.32.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.32.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.33.self_attn.qkv_proj.q_weight", "shape": [ 6144, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 15728640, "byteOffset": 11796480 }, { "name": "model.layers.33.self_attn.qkv_proj.q_scale", "shape": [ 6144, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1966080, "byteOffset": 27525120 } ], "md5sum": "3506be4010f23e0c4793e67a31924d8e" }, { "dataPath": "params_shard_145.bin", "format": "raw-shard", "nbytes": 11796480, "records": [ { "name": "model.layers.33.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.33.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 } ], "md5sum": "12de6f5c58a77e7db0049e2e7bab71a9" } ] }