{ "metadata": { "ParamSize": 629, "ParamBytes": 19125755904.0, "BitsPerParam": 3.597800643432664 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 155582464, "records": [ { "name": "lm_head.q_weight", "shape": [ 151936, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 155582464, "byteOffset": 0 } ], "md5sum": "1fe1999d0926e28eef1844df9eec3de8" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.47.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "15b73930d5d82c98bd5626e4b17f5a8d" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.47.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "3067ccf046f215a15a80d4d847278d54" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.47.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "9941d584c2f2bf793e645b24a018fd01" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 155582464, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 151936, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 155582464, "byteOffset": 0 } ], "md5sum": "a4471e2188d5d69084ee3e4e9b5c3b92" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 19447808, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 151936, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 19447808, "byteOffset": 0 } ], "md5sum": "7a49dfd4062063c1827f2c8d8348e188" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.0.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "8b51dcd4b38f3d5e4deceb22913ff87a" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 32047104, "records": [ { "name": "lm_head.q_scale", "shape": [ 151936, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 19447808, "byteOffset": 0 }, { "name": "model.layers.47.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 19447808 }, { "name": "model.layers.47.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 19451904 }, { "name": "model.layers.47.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 32034816 }, { "name": "model.norm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 32038912 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 32043008 } ], "md5sum": "6fe6f9b163d6c2f08c98e4b8b1316c90" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.0.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "dfe607e0ef72d2b4385985efaeea5a05" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.0.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "afbba4f30768db3c5bdf760d7cde047a" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.1.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "59cdffbb549988682079a6a0d5606a16" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 23732736, "records": [ { "name": "model.layers.0.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.0.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 13107200 }, { "name": "model.layers.0.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13111296 }, { "name": "model.layers.0.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13111552 }, { "name": "model.layers.0.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18354432 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19009792 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23204096 }, { "name": "model.layers.0.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23728384 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23728640 } ], "md5sum": "13ea02f1a56f2abaee832320d92dc5d0" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.1.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "a87fa113a6f8815dcc507268675f4824" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.1.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "10042ba2155c6e793d047ea1fd625c24" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.2.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "8b72c799661934f91b28ddeac760fba4" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 23728640, "records": [ { "name": "model.layers.1.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.1.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 13107200 }, { "name": "model.layers.1.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13111296 }, { "name": "model.layers.1.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13111552 }, { "name": "model.layers.1.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18354432 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19009792 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23204096 }, { "name": "model.layers.1.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23728384 } ], "md5sum": "bf6c32518ffaed58469705f7f6f45749" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.2.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "b56a2d889f6275452151f1efc67f16e8" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.2.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "afc3b2bbd0ce05e6e2052c3052464ca9" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.10.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "f49851d8b4356603f0d648ef546bb1e1" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 23728640, "records": [ { "name": "model.layers.2.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.2.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.2.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13107200 }, { "name": "model.layers.2.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13107456 }, { "name": "model.layers.2.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18350336 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19005696 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23200000 }, { "name": "model.layers.2.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23724288 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23724544 } ], "md5sum": "e5283041869445e2566055898063ad60" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.10.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "0e8a4fc900201c9a1bc48870b2afe864" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.10.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "994903368fbd7256eb7ab99b0712cad0" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.11.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "ae9f96f9367ca81fe4fcce47d1d15125" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 23732736, "records": [ { "name": "model.layers.10.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.10.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 13107200 }, { "name": "model.layers.10.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13111296 }, { "name": "model.layers.10.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13111552 }, { "name": "model.layers.10.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18354432 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19009792 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23204096 }, { "name": "model.layers.10.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23728384 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23728640 } ], "md5sum": "e2224196ab3e5f4ce89ff3ea20e1690e" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.11.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "6ee6b256cf21ac97f52d308bd78fa718" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.11.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "1d435cf168e896d3087ab8e5803eb749" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.12.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "4f976e1c04bedd47e263f2a2052c2e93" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 23728640, "records": [ { "name": "model.layers.11.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.11.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 13107200 }, { "name": "model.layers.11.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13111296 }, { "name": "model.layers.11.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13111552 }, { "name": "model.layers.11.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18354432 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19009792 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23204096 }, { "name": "model.layers.11.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23728384 } ], "md5sum": "22a5c58bb750656615accbbbe689bec3" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.12.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "1bda613ae42c4833c9c1ea6c63b783dd" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.12.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "01b6f3699dcbb4e601ab94f595d54436" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.9.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "35699cd1f15f5aadab0a749233b7f7a5" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 23728640, "records": [ { "name": "model.layers.12.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.12.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.12.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13107200 }, { "name": "model.layers.12.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13107456 }, { "name": "model.layers.12.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18350336 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19005696 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23200000 }, { "name": "model.layers.12.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23724288 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23724544 } ], "md5sum": "46634d21af2c76e627c2d81205cb7ebe" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.9.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "ff42a7f26410aa0c60c7c204a78f66ec" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.9.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "b5e16adb3c789b741420269c94ddc591" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.13.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "7d597b622f0ae7ead975c36cd3c5ac35" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.13.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "10d738a318ae86f5097fb09a671af160" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.13.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "054c1d3148270f5c542211ed47408474" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 31609088, "records": [ { "name": "model.layers.9.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12582912 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12587008 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12591104 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 12595200 }, { "name": "model.layers.13.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 12599296 }, { "name": "model.layers.13.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 25182208 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 25706496 }, { "name": "model.layers.13.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 25710592 }, { "name": "model.layers.13.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 25710848 }, { "name": "model.layers.13.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 30953728 } ], "md5sum": "17a47049e8e481fe484b398ce7779a7f" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.14.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "1bdec306bef9346b4e59565f1fb68f1f" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.14.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "42fc187986613821c74b8db83f515812" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.14.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "c87621ed9e498f1c5dae85a07a28905e" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.15.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "87b7fcdec2f6a4686d50147d99c038ba" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 28451584, "records": [ { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 4194304 }, { "name": "model.layers.13.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 4718592 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 4718848 }, { "name": "model.layers.14.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 4722944 }, { "name": "model.layers.14.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 17305856 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 17830144 }, { "name": "model.layers.14.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 17834240 }, { "name": "model.layers.14.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 17834496 }, { "name": "model.layers.14.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 23077376 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 23732736 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 27927040 }, { "name": "model.layers.14.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 28451328 } ], "md5sum": "2b7cb3376b289fc3e25b16332154083a" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.15.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "a7feb5df87ad5a44268f54ddf461bb94" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.15.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "f20c4a33fc4949ce672d0c95292df963" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.16.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "86e5145003ffee84cfceb6b1428edcdc" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 23736832, "records": [ { "name": "model.layers.15.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.15.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.15.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13107200 }, { "name": "model.layers.15.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13107456 }, { "name": "model.layers.15.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18350336 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19005696 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23200000 }, { "name": "model.layers.15.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23724288 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23724544 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23728640 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23732736 } ], "md5sum": "8cbf9ecfc413ac35d95ac622d611c57d" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.16.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "a0700a6bbce3af953e902cf578ad9905" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.16.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "e176a30e12068c5f9559547c6fa21bee" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.17.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "9067737208df5849bde1a566c5790f46" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 23732736, "records": [ { "name": "model.layers.16.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.16.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 13107200 }, { "name": "model.layers.16.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13111296 }, { "name": "model.layers.16.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13111552 }, { "name": "model.layers.16.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18354432 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19009792 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23204096 }, { "name": "model.layers.16.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23728384 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23728640 } ], "md5sum": "fd85724029741c3f9f2c5b224ed8269a" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.17.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "4b693473b6f0cd2921691073f03e61db" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.17.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "847615e3b57ed8d462f79356746b1961" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.18.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "6fd4ac327723f8b8a5fcebdbda699af3" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 23728640, "records": [ { "name": "model.layers.17.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.17.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 13107200 }, { "name": "model.layers.17.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13111296 }, { "name": "model.layers.17.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13111552 }, { "name": "model.layers.17.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18354432 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19009792 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23204096 }, { "name": "model.layers.17.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23728384 } ], "md5sum": "ac6d88ccdfb693c2c9d6de994d5ab876" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.18.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "2678bb166d049497ef6be6801a0a06e0" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.18.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "156607ac5ac53001ddc2dc14223aa808" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.19.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "5023706298e7b6ed87083a39e424d643" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 23736832, "records": [ { "name": "model.layers.18.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.18.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.18.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13107200 }, { "name": "model.layers.18.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13107456 }, { "name": "model.layers.18.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18350336 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19005696 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23200000 }, { "name": "model.layers.18.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23724288 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23724544 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23728640 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23732736 } ], "md5sum": "743ff3c945e2168c73d168e6bbb020f4" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.19.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "81194f252612b664ea3c26db981a3864" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.19.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "5c1c769c6bfb716c1b456fe0c40d1121" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.20.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "0cf0a5b3d4e9b75cf293ff1280e67f9c" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 23732736, "records": [ { "name": "model.layers.19.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.19.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 13107200 }, { "name": "model.layers.19.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13111296 }, { "name": "model.layers.19.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13111552 }, { "name": "model.layers.19.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18354432 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19009792 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23204096 }, { "name": "model.layers.19.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23728384 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23728640 } ], "md5sum": "890608d991c8f086f4e0d82c83976078" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.20.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "c2455bcbee7ccdd75be90100d4e81655" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.20.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "ab853c9df4b1b1a1be47f6fcb6963e1a" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.21.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "4ab12f808b9d38681dc9d5b28400f808" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 23728640, "records": [ { "name": "model.layers.20.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.20.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 13107200 }, { "name": "model.layers.20.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13111296 }, { "name": "model.layers.20.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13111552 }, { "name": "model.layers.20.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18354432 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19009792 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23204096 }, { "name": "model.layers.20.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23728384 } ], "md5sum": "81d9d05216f343d716b98b3d3587b302" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.21.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "8df4c8036578f55eced9728f5646708e" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.21.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "8af276790348807432b396ff24a981d6" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.3.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "763c930211d7e0442ffd19790c87ad45" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 23736832, "records": [ { "name": "model.layers.21.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.21.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.21.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13107200 }, { "name": "model.layers.21.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13107456 }, { "name": "model.layers.21.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18350336 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19005696 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23200000 }, { "name": "model.layers.21.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23724288 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23724544 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23728640 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23732736 } ], "md5sum": "391fef2b3a76307fd265c910d1ec10e1" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.3.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "3bf595ff409ff2a79816c86efb85386b" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.3.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "95ced15d3ab0474a9484c609d86996a8" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.4.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "f2cb552bf2261a9c69b7b84ad772f695" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 23732736, "records": [ { "name": "model.layers.3.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.3.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 13107200 }, { "name": "model.layers.3.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13111296 }, { "name": "model.layers.3.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13111552 }, { "name": "model.layers.3.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18354432 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19009792 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23204096 }, { "name": "model.layers.3.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23728384 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23728640 } ], "md5sum": "18589cee17335abc00296886e2c65615" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.4.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "8cac119bfddcbbbbf06d21b10bb71251" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.4.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "3be23517a5df4d1602a80a6717aa77a6" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.5.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "be1e766b3ee4b2f4de108bb177433f5e" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 23728640, "records": [ { "name": "model.layers.4.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.4.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 13107200 }, { "name": "model.layers.4.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13111296 }, { "name": "model.layers.4.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13111552 }, { "name": "model.layers.4.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18354432 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19009792 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23204096 }, { "name": "model.layers.4.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23728384 } ], "md5sum": "14128e60ea346934408b75c86dd5680d" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.5.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "8225bcaffb2b727713db710c5761f0f7" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.5.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "1ee7b9acc60576f7b3f14844e9e8216c" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.22.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "b89c4140fba349b6570e8687d8aead45" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 23736832, "records": [ { "name": "model.layers.5.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.5.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.5.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13107200 }, { "name": "model.layers.5.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13107456 }, { "name": "model.layers.5.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18350336 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19005696 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23200000 }, { "name": "model.layers.5.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23724288 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23724544 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23728640 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23732736 } ], "md5sum": "41f85c4542b1da7e3178ef3bdd5f20b1" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.22.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "93f86b4d905ecd30905796c85bd1e514" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.22.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "f7143fca20da40a4ec0825dfbc419717" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.23.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "8893b5a69fc64dcc380e7e99cc02b467" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 23732736, "records": [ { "name": "model.layers.22.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.22.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 13107200 }, { "name": "model.layers.22.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13111296 }, { "name": "model.layers.22.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13111552 }, { "name": "model.layers.22.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18354432 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19009792 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23204096 }, { "name": "model.layers.22.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23728384 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23728640 } ], "md5sum": "2f0ff33a968a988dcc983789da72075d" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.23.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "c448111da62e6e64c6b46ca6b5357f10" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.23.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "3100f523fcef8f8e0a5f15c412e68cb9" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.24.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "0ac24a8ae8e807f21bd7243db639e947" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 23732736, "records": [ { "name": "model.layers.23.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.23.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 13107200 }, { "name": "model.layers.23.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13111296 }, { "name": "model.layers.23.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13111552 }, { "name": "model.layers.23.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18354432 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19009792 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23204096 }, { "name": "model.layers.23.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23728384 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23728640 } ], "md5sum": "74ee41a3b6c90028496e0bdd50302b80" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.24.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "c506d69a8260b4e1fdc571690cf043f2" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.24.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "fc45b1450a6686b2d1ebec22613a4035" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.25.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "baaaedc87045fdd43b0175e7a172361d" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 23728640, "records": [ { "name": "model.layers.24.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.24.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 13107200 }, { "name": "model.layers.24.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13111296 }, { "name": "model.layers.24.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13111552 }, { "name": "model.layers.24.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18354432 }, { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19009792 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23204096 }, { "name": "model.layers.24.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23728384 } ], "md5sum": "1a5309582bf6fea6821e63d65ff847a7" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.25.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "06a41bccc99c21f9fe3dec3f06cff2c6" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.25.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "455f551c9acbd01d881bf9a63ef95de9" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.26.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "19ef6a08e7c250771dccbbc817755614" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 23736832, "records": [ { "name": "model.layers.25.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.25.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.25.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13107200 }, { "name": "model.layers.25.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13107456 }, { "name": "model.layers.25.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18350336 }, { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19005696 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23200000 }, { "name": "model.layers.25.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23724288 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23724544 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23728640 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23732736 } ], "md5sum": "e8ca7155c60eaa4fe1a47ff9932c806e" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.26.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "56ba7e67c34723178ebb70cb62f719ec" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.26.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "5eb3f291547d7320b71c915ef55e7f60" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.27.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "4c5cb8b064e6c595c8330531da67bd3a" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 23732736, "records": [ { "name": "model.layers.26.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.26.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 13107200 }, { "name": "model.layers.26.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13111296 }, { "name": "model.layers.26.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13111552 }, { "name": "model.layers.26.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18354432 }, { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19009792 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23204096 }, { "name": "model.layers.26.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23728384 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23728640 } ], "md5sum": "57dc94887d251f961f6fc5a7d3c2329a" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.27.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "80d70b925e1eb56dcfe27d6a2e22c144" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.27.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "14cd1b05124700a0bea5a56483ffffeb" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.28.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "493aa948660d884b0bea79e969f3af64" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 23728640, "records": [ { "name": "model.layers.27.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.27.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 13107200 }, { "name": "model.layers.27.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13111296 }, { "name": "model.layers.27.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13111552 }, { "name": "model.layers.27.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18354432 }, { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19009792 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23204096 }, { "name": "model.layers.27.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23728384 } ], "md5sum": "27a34ba825003824d487c6aca73ca7f0" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.28.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "0bdd4ef3f8140f7f1e98b93038b980d7" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.28.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "e8ad6c3051328d2ef4de8d4de1632b57" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.29.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "2ee50ad153302f6bf076790ea2b6a1af" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 23736832, "records": [ { "name": "model.layers.28.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.28.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.28.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13107200 }, { "name": "model.layers.28.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13107456 }, { "name": "model.layers.28.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18350336 }, { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19005696 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23200000 }, { "name": "model.layers.28.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23724288 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23724544 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23728640 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23732736 } ], "md5sum": "f26d2b60b05c3d1562b6e8ddbcc0a8a7" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.29.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "9bf125aa6f3acd5e4bf6addd85cb22c4" }, { "dataPath": "params_shard_112.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.29.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "8aa9d8478c875c5f8c286b37308126a0" }, { "dataPath": "params_shard_113.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.30.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "2750528e871d339918f5fc8214c8a052" }, { "dataPath": "params_shard_114.bin", "format": "raw-shard", "nbytes": 23732736, "records": [ { "name": "model.layers.29.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.29.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 13107200 }, { "name": "model.layers.29.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13111296 }, { "name": "model.layers.29.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13111552 }, { "name": "model.layers.29.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18354432 }, { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19009792 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23204096 }, { "name": "model.layers.29.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23728384 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23728640 } ], "md5sum": "a7a55e2481849287f633f08ac0cee079" }, { "dataPath": "params_shard_115.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.30.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "976bd79d510b46dded6014fdf62abf42" }, { "dataPath": "params_shard_116.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.30.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "e16054112124f4531761193556a0a9a6" }, { "dataPath": "params_shard_117.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.31.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "dfd33650c70b6577e916d2e7c8d2fff9" }, { "dataPath": "params_shard_118.bin", "format": "raw-shard", "nbytes": 23728640, "records": [ { "name": "model.layers.30.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.30.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 13107200 }, { "name": "model.layers.30.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13111296 }, { "name": "model.layers.30.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13111552 }, { "name": "model.layers.30.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18354432 }, { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19009792 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23204096 }, { "name": "model.layers.30.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23728384 } ], "md5sum": "cd9f993db3d158a587aca131bc6dc92e" }, { "dataPath": "params_shard_119.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.31.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "3ed64c39cfff58de04e76bbeb073dc42" }, { "dataPath": "params_shard_120.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.31.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "cff1519d448b13d17144d035fb128c44" }, { "dataPath": "params_shard_121.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.32.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "8e2ca3676a73d33ced23b1d0750076d9" }, { "dataPath": "params_shard_122.bin", "format": "raw-shard", "nbytes": 23736832, "records": [ { "name": "model.layers.31.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.31.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.31.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13107200 }, { "name": "model.layers.31.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13107456 }, { "name": "model.layers.31.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18350336 }, { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19005696 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23200000 }, { "name": "model.layers.31.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23724288 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23724544 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23728640 }, { "name": "model.layers.32.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23732736 } ], "md5sum": "4db16bfdf1c59212f638fc773c673045" }, { "dataPath": "params_shard_123.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.32.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "ba95ebcba5a497eff1f9857e0689c8e1" }, { "dataPath": "params_shard_124.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.32.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "d016f66854d5bae8378939dfdeec9cee" }, { "dataPath": "params_shard_125.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.33.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "701c213c8327d153eeded2c3a24b3f06" }, { "dataPath": "params_shard_126.bin", "format": "raw-shard", "nbytes": 23732736, "records": [ { "name": "model.layers.32.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.32.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.32.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 13107200 }, { "name": "model.layers.32.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13111296 }, { "name": "model.layers.32.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13111552 }, { "name": "model.layers.32.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18354432 }, { "name": "model.layers.32.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19009792 }, { "name": "model.layers.32.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23204096 }, { "name": "model.layers.32.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23728384 }, { "name": "model.layers.33.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23728640 } ], "md5sum": "9026314914b22e234aa8886758f41c62" }, { "dataPath": "params_shard_127.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.33.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "3c2bcf3e015af27cc0376a682942d8a8" }, { "dataPath": "params_shard_128.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.33.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "cb0168df0cc5580369151fa69275aa58" }, { "dataPath": "params_shard_129.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.34.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "17c3ba3a5a155d5c27b83db70ebc6bf7" }, { "dataPath": "params_shard_130.bin", "format": "raw-shard", "nbytes": 23728640, "records": [ { "name": "model.layers.33.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.33.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.33.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 13107200 }, { "name": "model.layers.33.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13111296 }, { "name": "model.layers.33.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13111552 }, { "name": "model.layers.33.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18354432 }, { "name": "model.layers.33.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19009792 }, { "name": "model.layers.33.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23204096 }, { "name": "model.layers.33.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23728384 } ], "md5sum": "de36a31aeb9d3c8946ec0478375d7ddc" }, { "dataPath": "params_shard_131.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.34.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "287261ebec8f089117d3d0628899185d" }, { "dataPath": "params_shard_132.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.34.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "f3dd7626a2891e77a4cfee5e3d1b2851" }, { "dataPath": "params_shard_133.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.35.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "6cab07462e648f4f5a1afc88436415f6" }, { "dataPath": "params_shard_134.bin", "format": "raw-shard", "nbytes": 23736832, "records": [ { "name": "model.layers.34.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.34.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.34.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13107200 }, { "name": "model.layers.34.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13107456 }, { "name": "model.layers.34.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18350336 }, { "name": "model.layers.34.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19005696 }, { "name": "model.layers.34.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23200000 }, { "name": "model.layers.34.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23724288 }, { "name": "model.layers.34.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23724544 }, { "name": "model.layers.34.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23728640 }, { "name": "model.layers.35.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23732736 } ], "md5sum": "581d2b36a521a0e204a335fb71819a05" }, { "dataPath": "params_shard_135.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.35.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "9cdad9ad40613d2777a97280647ed6a4" }, { "dataPath": "params_shard_136.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.35.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "7c61a591a94bd78b6c572cdaaba857df" }, { "dataPath": "params_shard_137.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.36.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "d4c5d2ac7061d881c39b1f4643e28bd4" }, { "dataPath": "params_shard_138.bin", "format": "raw-shard", "nbytes": 23732736, "records": [ { "name": "model.layers.35.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.35.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.35.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 13107200 }, { "name": "model.layers.35.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13111296 }, { "name": "model.layers.35.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13111552 }, { "name": "model.layers.35.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18354432 }, { "name": "model.layers.35.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19009792 }, { "name": "model.layers.35.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23204096 }, { "name": "model.layers.35.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23728384 }, { "name": "model.layers.36.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23728640 } ], "md5sum": "9d80b1320689ffa1684a712345683879" }, { "dataPath": "params_shard_139.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.36.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "71bc4a783697f8113c5f8d3235557eb9" }, { "dataPath": "params_shard_140.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.36.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "c2e686a81ce35c44740524d671e235d0" }, { "dataPath": "params_shard_141.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.37.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "a2769f296943fb318b8ccf8aeee25145" }, { "dataPath": "params_shard_142.bin", "format": "raw-shard", "nbytes": 23732736, "records": [ { "name": "model.layers.36.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.36.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.36.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 13107200 }, { "name": "model.layers.36.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13111296 }, { "name": "model.layers.36.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13111552 }, { "name": "model.layers.36.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18354432 }, { "name": "model.layers.36.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19009792 }, { "name": "model.layers.36.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23204096 }, { "name": "model.layers.36.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23728384 }, { "name": "model.layers.37.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23728640 } ], "md5sum": "3e0680d2692a1447506c0adafb3b2538" }, { "dataPath": "params_shard_143.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.37.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "7da2fd0451efd8e4602760f914523dbc" }, { "dataPath": "params_shard_144.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.37.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "cff04bc10483af534f3d15e9f3aa6117" }, { "dataPath": "params_shard_145.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.38.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "189567768e54e35174b31650112c809e" }, { "dataPath": "params_shard_146.bin", "format": "raw-shard", "nbytes": 23732736, "records": [ { "name": "model.layers.37.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.37.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.37.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 13107200 }, { "name": "model.layers.37.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13111296 }, { "name": "model.layers.37.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13111552 }, { "name": "model.layers.37.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18354432 }, { "name": "model.layers.37.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19009792 }, { "name": "model.layers.37.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23204096 }, { "name": "model.layers.37.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23728384 }, { "name": "model.layers.38.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23728640 } ], "md5sum": "5cebe89222312bd1b7e97ba06d507503" }, { "dataPath": "params_shard_147.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.38.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "97466c76eef760899b7783e823e8d700" }, { "dataPath": "params_shard_148.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.38.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "fc9fca258f64803055580c4dd00a2385" }, { "dataPath": "params_shard_149.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.39.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "a9c6ee12ee755a8151cdb1b755e6eb89" }, { "dataPath": "params_shard_150.bin", "format": "raw-shard", "nbytes": 23732736, "records": [ { "name": "model.layers.38.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.38.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.38.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 13107200 }, { "name": "model.layers.38.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13111296 }, { "name": "model.layers.38.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13111552 }, { "name": "model.layers.38.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18354432 }, { "name": "model.layers.38.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19009792 }, { "name": "model.layers.38.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23204096 }, { "name": "model.layers.38.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23728384 }, { "name": "model.layers.39.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23728640 } ], "md5sum": "e81ded70eec5ede3758f8fc15a063562" }, { "dataPath": "params_shard_151.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.39.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "9748a932799803c5f86915dc3a728d6d" }, { "dataPath": "params_shard_152.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.39.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "7a1af60e12c9a4c6c47b7872d7a1e601" }, { "dataPath": "params_shard_153.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.40.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "077096325b5f5d46cd28c0e1029457a0" }, { "dataPath": "params_shard_154.bin", "format": "raw-shard", "nbytes": 23732736, "records": [ { "name": "model.layers.39.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.39.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.39.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 13107200 }, { "name": "model.layers.39.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13111296 }, { "name": "model.layers.39.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13111552 }, { "name": "model.layers.39.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18354432 }, { "name": "model.layers.39.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19009792 }, { "name": "model.layers.39.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23204096 }, { "name": "model.layers.39.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23728384 }, { "name": "model.layers.40.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23728640 } ], "md5sum": "aa97a2e8ed3f2616aa272a1771e1d820" }, { "dataPath": "params_shard_155.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.40.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "a6a894aa9b7e4dcf1fe1645d65312dad" }, { "dataPath": "params_shard_156.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.40.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "092d4c1e057cbc15acc39697e6703f24" }, { "dataPath": "params_shard_157.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.41.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "7e8ee184c58a825593426ebfcf192b72" }, { "dataPath": "params_shard_158.bin", "format": "raw-shard", "nbytes": 23728640, "records": [ { "name": "model.layers.40.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.40.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.40.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 13107200 }, { "name": "model.layers.40.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13111296 }, { "name": "model.layers.40.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13111552 }, { "name": "model.layers.40.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18354432 }, { "name": "model.layers.40.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19009792 }, { "name": "model.layers.40.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23204096 }, { "name": "model.layers.40.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23728384 } ], "md5sum": "d0281946afb3a9aa8f721282adf51fb8" }, { "dataPath": "params_shard_159.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.41.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "16b12bfd8713cf0d0efd55aff5b715e2" }, { "dataPath": "params_shard_160.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.41.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "bcbf1537ffe090e90576d7d88aa1344c" }, { "dataPath": "params_shard_161.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.42.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "240e0d4e8f2d1391e6e8e01bc82581d0" }, { "dataPath": "params_shard_162.bin", "format": "raw-shard", "nbytes": 23736832, "records": [ { "name": "model.layers.41.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.41.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.41.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13107200 }, { "name": "model.layers.41.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13107456 }, { "name": "model.layers.41.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18350336 }, { "name": "model.layers.41.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19005696 }, { "name": "model.layers.41.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23200000 }, { "name": "model.layers.41.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23724288 }, { "name": "model.layers.41.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23724544 }, { "name": "model.layers.41.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23728640 }, { "name": "model.layers.42.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23732736 } ], "md5sum": "67197600fe9a016a0b52be9e098fe5ae" }, { "dataPath": "params_shard_163.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.42.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "cfc2781cba3d9658332f40ea9a5d50c4" }, { "dataPath": "params_shard_164.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.42.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "ce4bd9f342f6a6f202881324f68dbf98" }, { "dataPath": "params_shard_165.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.43.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "a9b82d852613f8217c14c211934125b6" }, { "dataPath": "params_shard_166.bin", "format": "raw-shard", "nbytes": 23732736, "records": [ { "name": "model.layers.42.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.42.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.42.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 13107200 }, { "name": "model.layers.42.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13111296 }, { "name": "model.layers.42.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13111552 }, { "name": "model.layers.42.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18354432 }, { "name": "model.layers.42.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19009792 }, { "name": "model.layers.42.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23204096 }, { "name": "model.layers.42.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23728384 }, { "name": "model.layers.43.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23728640 } ], "md5sum": "cf3b0be02c49963887b8c4fb43dc2293" }, { "dataPath": "params_shard_167.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.43.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "d652f00acb3d0df59b38b505f4204eb8" }, { "dataPath": "params_shard_168.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.43.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "aa4f1f24df998a65a2829aa937f524b9" }, { "dataPath": "params_shard_169.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.44.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "c4578f93d3a14713154350198f375c8d" }, { "dataPath": "params_shard_170.bin", "format": "raw-shard", "nbytes": 23728640, "records": [ { "name": "model.layers.43.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.43.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.43.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 13107200 }, { "name": "model.layers.43.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13111296 }, { "name": "model.layers.43.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13111552 }, { "name": "model.layers.43.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18354432 }, { "name": "model.layers.43.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19009792 }, { "name": "model.layers.43.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23204096 }, { "name": "model.layers.43.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23728384 } ], "md5sum": "23df696e1dd0437a4b6f34776a2abc94" }, { "dataPath": "params_shard_171.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.44.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "5e662d140a27999e8726a79a29ee3fd9" }, { "dataPath": "params_shard_172.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.44.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "c059d8641def3bb789faa3f116750243" }, { "dataPath": "params_shard_173.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.45.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "df01eddb8888aa0e810b45d159d7c782" }, { "dataPath": "params_shard_174.bin", "format": "raw-shard", "nbytes": 23736832, "records": [ { "name": "model.layers.44.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.44.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.44.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13107200 }, { "name": "model.layers.44.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13107456 }, { "name": "model.layers.44.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18350336 }, { "name": "model.layers.44.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19005696 }, { "name": "model.layers.44.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23200000 }, { "name": "model.layers.44.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23724288 }, { "name": "model.layers.44.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23724544 }, { "name": "model.layers.44.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23728640 }, { "name": "model.layers.45.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23732736 } ], "md5sum": "bccea2c3a47069d641c16c97712c3900" }, { "dataPath": "params_shard_175.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.45.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "a4ad57733af9f34ae4e5f6014ce1a778" }, { "dataPath": "params_shard_176.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.45.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "4b0f6d9a84b661dfff08e7f742cd12a8" }, { "dataPath": "params_shard_177.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.46.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "4ad6179be38ff0d74c3b4a4cb86b4adf" }, { "dataPath": "params_shard_178.bin", "format": "raw-shard", "nbytes": 23732736, "records": [ { "name": "model.layers.45.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.45.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.45.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 13107200 }, { "name": "model.layers.45.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13111296 }, { "name": "model.layers.45.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13111552 }, { "name": "model.layers.45.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18354432 }, { "name": "model.layers.45.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19009792 }, { "name": "model.layers.45.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23204096 }, { "name": "model.layers.45.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23728384 }, { "name": "model.layers.46.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23728640 } ], "md5sum": "8cb84c92cdbfdfa072d822c5cc038764" }, { "dataPath": "params_shard_179.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.46.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "fd0a8c83eaba1e8d3ff252f022a61495" }, { "dataPath": "params_shard_180.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.46.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "eb31527073c26ff432907b809ed57668" }, { "dataPath": "params_shard_181.bin", "format": "raw-shard", "nbytes": 30151424, "records": [ { "name": "model.layers.46.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.46.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.46.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 13107200 }, { "name": "model.layers.46.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13111296 }, { "name": "model.layers.46.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13111552 }, { "name": "model.layers.46.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18354432 }, { "name": "model.layers.46.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19009792 }, { "name": "model.layers.46.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23204096 }, { "name": "model.layers.46.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23728384 }, { "name": "model.layers.47.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23728640 }, { "name": "model.layers.47.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 24252928 }, { "name": "model.layers.47.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24253184 }, { "name": "model.layers.47.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 29496064 } ], "md5sum": "0e4e55630cb86e888c7a9c2c3d41370a" }, { "dataPath": "params_shard_182.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.6.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "1f64f2551e6b136dd33215fa2a852a94" }, { "dataPath": "params_shard_183.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.6.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "94bf98f4abde386355cc86f048705229" }, { "dataPath": "params_shard_184.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.6.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "68106407cd89d32b21d6238e34daff3b" }, { "dataPath": "params_shard_185.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.7.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "486b86bf9beb89ea9ad2e147e7405d9b" }, { "dataPath": "params_shard_186.bin", "format": "raw-shard", "nbytes": 28463872, "records": [ { "name": "model.layers.47.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.47.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 4194304 }, { "name": "model.layers.47.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 4718592 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 4718848 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 4722944 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 4727040 }, { "name": "model.layers.6.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 4731136 }, { "name": "model.layers.6.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 17314048 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 17838336 }, { "name": "model.layers.6.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 17842432 }, { "name": "model.layers.6.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 17842688 }, { "name": "model.layers.6.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 23085568 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 23740928 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 27935232 }, { "name": "model.layers.6.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 28459520 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 28459776 } ], "md5sum": "f55cf201fedc8c2ce748e9daca132372" }, { "dataPath": "params_shard_187.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.7.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "89f127a7832fa21504d391e926a22202" }, { "dataPath": "params_shard_188.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.7.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "8fbccda0d0b1851618c05c83db02673c" }, { "dataPath": "params_shard_189.bin", "format": "raw-shard", "nbytes": 100663296, "records": [ { "name": "model.layers.8.mlp.moe_down_proj.q_weight", "shape": [ 128, 2048, 96 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 100663296, "byteOffset": 0 } ], "md5sum": "a00ff4e285f43e4063392cf09f9a698c" }, { "dataPath": "params_shard_190.bin", "format": "raw-shard", "nbytes": 23732736, "records": [ { "name": "model.layers.7.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.7.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 13107200 }, { "name": "model.layers.7.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13111296 }, { "name": "model.layers.7.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13111552 }, { "name": "model.layers.7.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18354432 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19009792 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23204096 }, { "name": "model.layers.7.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23728384 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23728640 } ], "md5sum": "27af289a11cc5c159aaf95a81e413814" }, { "dataPath": "params_shard_191.bin", "format": "raw-shard", "nbytes": 201326592, "records": [ { "name": "model.layers.8.mlp.moe_gate_up_proj.q_weight", "shape": [ 128, 1536, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 201326592, "byteOffset": 0 } ], "md5sum": "605da76c12b86f1570e2fd0581305243" }, { "dataPath": "params_shard_192.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.8.mlp.moe_gate_up_proj.q_scale", "shape": [ 128, 1536, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "8fc76986187b2b65118ec69d05a5fcb2" }, { "dataPath": "params_shard_193.bin", "format": "raw-shard", "nbytes": 30151424, "records": [ { "name": "model.layers.8.mlp.moe_down_proj.q_scale", "shape": [ 128, 2048, 24 ], "dtype": "bfloat16", "format": "raw", "nbytes": 12582912, "byteOffset": 0 }, { "name": "model.layers.8.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 12582912 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 13107200 }, { "name": "model.layers.8.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 13111296 }, { "name": "model.layers.8.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 13111552 }, { "name": "model.layers.8.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 18354432 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19009792 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23204096 }, { "name": "model.layers.8.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 23728384 }, { "name": "model.layers.9.mlp.gate.weight", "shape": [ 128, 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 23728640 }, { "name": "model.layers.9.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 24252928 }, { "name": "model.layers.9.self_attn.c_attn.q_weight", "shape": [ 5120, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24253184 }, { "name": "model.layers.9.self_attn.c_attn.q_scale", "shape": [ 5120, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 655360, "byteOffset": 29496064 } ], "md5sum": "7ada4fe2b3c0bd807a2b66df07a31208" }, { "dataPath": "params_shard_194.bin", "format": "raw-shard", "nbytes": 4718848, "records": [ { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 2048, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 2048, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 524288, "byteOffset": 4194304 }, { "name": "model.layers.9.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 256, "byteOffset": 4718592 } ], "md5sum": "edff5f2f1ee0b2329e1183aaab3ffa9b" } ] }