{ "metadata": { "ParamSize": 805, "ParamBytes": 31066067264.0, "BitsPerParam": 3.4852341809509815 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 105012480, "records": [ { "name": "lm_head.q_weight", "shape": [ 32016, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 105012480, "byteOffset": 0 } ], "md5sum": "0ee8b5cc3c25c0a7e2205fdb369e40ae" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.78.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "9ba2ac1e988bafc14f81b6a687a91824" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.78.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "65abd24b425e817e1eda25f679a006ac" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.78.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "3f95f6a04aca6c6f54ada4b897207a19" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.78.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "e7765e81124220485041c61545f72540" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.79.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "a25ba5de501ea2d4c974a5fa14c07e60" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 28281760, "records": [ { "name": "lm_head.q_scale", "shape": [ 32016, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 13126560, "byteOffset": 0 }, { "name": "model.layers.78.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 13126560 }, { "name": "model.layers.78.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 13142944 }, { "name": "model.layers.78.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24890272 }, { "name": "model.layers.78.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 24906656 }, { "name": "model.layers.79.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 28265376 } ], "md5sum": "81d0bc65162347724601f698521e6da3" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.79.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "3dfdf57ead261c5f5265928c471018a8" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.79.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "eff429f63d9111f9a861dceb319cbb16" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.79.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "10a2226ff68f16bb2e06ccef6956bf37" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.79.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "72f63a41932c8a63690cfd8254aa9475" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 105012480, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 32016, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 105012480, "byteOffset": 0 } ], "md5sum": "d98afb40f766b7f591fafcb31aba0eef" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "a6077b12b339958934a41bb43960ed17" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 32480160, "records": [ { "name": "model.layers.79.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.79.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.79.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.79.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.norm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19320832 }, { "name": "model.embed_tokens.q_scale", "shape": [ 32016, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 13126560, "byteOffset": 19337216 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 32463776 } ], "md5sum": "afa849121809ed2085c7d56efe694722" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "18031229c7732bd6aa8890562c88d240" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "e35b8d95d60db3e4d85d6351e4c6dcb5" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "d9009dde4fb4cbe0943e3723e7c6879c" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "c9561d3e787baa023300960ba302ce4f" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "70fe6b456b1455b06b46ce66f5b7170b" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "0e00301d50c093841349a42e49834ab6" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "c9000c73693fdbad2dc1c71606af39c3" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "7417da26672bc502088302ee4b3055d8" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 31100928, "records": [ { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19320832 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 19337216 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31084544 } ], "md5sum": "5ecfa9767daab5bdcd4bd5333f0b905a" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "c09d24ec57ec51fedbee01158f906ffa" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "cbb17b8d3b0a9317b34306dd0e8f4a43" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "580fd8dbb12eba4ae1cfe6e019ed80a5" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "a018f5e67a07bee2e96652fbcb1a531f" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 3358720 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 26869760 } ], "md5sum": "38f6903c2984908bd0ef6750e8459927" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "a85731342e2fb18c2eba7a0f4667a915" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "f23f59c69e8f5da843a82a5c099b811f" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "f8cacf8960532a04f8bda46c69c6420d" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "ef8b65c9dd8f0a7f7f1ce07e79e328e0" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "14d10c53ede4b57a1c17ae8fc2db609c" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "075bdb0d67fc48a6daf3adefb1a5678d" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 22712320, "records": [ { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 3375104 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15122432 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 15138816 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 19337216 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 22695936 } ], "md5sum": "716a589e517e5dd73f57a683bd96b8fe" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "c9810d5b8f850d45ebf0324de6187c70" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "d40fae7dd8271b44e42660ee119ee3ae" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "01b7119387b7a5e3ee75000359664f1f" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "0ab809e681e9f4695c66123417a676aa" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "7dd09df058e11bbc824e80db83888ebd" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "8d2d5281a6bf22182bced20b9bfb8ebe" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "cc172bfc3e4b84f4f644934e5784dc30" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "c3803ea5517ca2acb661032f69064dca" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 31100928, "records": [ { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 11763712 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15122432 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 15138816 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26886144 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 26902528 } ], "md5sum": "3b4f5fce003f057b29df662dd087dc25" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "7d5873e4284e9467d3b3907028e65150" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "65d4e7cd6518020aa7441cba5cc280a5" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "92cac0c897d37c8507dbd77c6f950c01" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "5cf636b88afd1c4e3616804088ffec8b" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "dcb69acf34c62c3b1a5a81bc297ad29a" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "d0371b9324d01e0e87fcfdeaff555a38" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 22712320, "records": [ { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 3375104 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15122432 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 15138816 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 19337216 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 22695936 } ], "md5sum": "15107a3e6697f27646ac074d03263525" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "403bfc0289382636dca732936290a60d" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "69a21b4fd49121cf94f16d2dde63d7ba" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "b3ffba1b45077d311efd7066898d5964" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "136ec71a82e28e7bc1b8693efd27ae39" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "dc998ad00ce47f89bcf30ddc14f81c32" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "2624c8eb27be11e70b6208c6933ee49a" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "9f691c621c5764e1f4265172a6f288f8" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "15ddcaefbb38a81e1f776fc3282e6823" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "2c8fd23d38a1025049a705c3a553858b" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 26894336, "records": [ { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 19320832 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 23519232 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26877952 } ], "md5sum": "e242740c5afd7abb7154ca359d6670c1" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "fcef838efc5063088333a4789d33e100" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "c02738235bd13b2ee7990019ca47e6e3" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "51e2bd02dbea9ff151d8e8db33bf070d" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "897a9adeed41bca05888643e7d2e12b8" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "9deb5094ac32049e5a9a1b6d68af4741" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "74e25cf4d184d412f80e9e92147d89dc" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "efa728d64f183cec8b2f83a037dc625c" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "650d42bfa2f582b982340c30d27a1c17" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "57e7832bbef80dd127e235fbb51b1fed" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "d9e2a13c12d89d6ef5ecc09326bc9c63" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "f269710f5babf8f04efe8dbf827ee082" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "d13e4c162d73aeecee70f1a62f8aed09" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "94afedf24f6d077eef986bb2ad91c92b" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "fc2544c4586587c783ace24ec781829d" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "6401e94f5f4c0ac321eff02ec97fe14a" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "daf857c38ab5d1f0ab67f3b77ec8c48c" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 26894336, "records": [ { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 19320832 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 23519232 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26877952 } ], "md5sum": "930bb85e3174a8d678884bf5624ae894" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "d830ceb2157c50116da72aa33b834f6a" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "feab837cd4cfb73b5c9583d835d6c10d" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "0c42176570667c3704f2ea1bc9f7a42c" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "7842cad3f4f49b46456586c34aa176ea" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "372ecee973005d4a230b1bc3a0096ce2" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "fb605ea6675082020946d0f784ef736a" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "58d82a884030cac5790ebeaf31d5f3d1" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "08c70d42936c77761336a666d233cfcd" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "ca70028a7941cd7a014c398086df7a7f" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.18.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "91ea3bb3e4b197ac16a017678ea50575" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "d5120a900df874716b0397bd4e710ef2" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.19.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "ba88d101cc3e9497e10c3ec2c582764d" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "f6bcdef729e9bad19bf890d16563657b" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "d73c2db4a6f3094f5b023ac3d7ab9866" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 26894336, "records": [ { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 19320832 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 23519232 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26877952 } ], "md5sum": "12ee46e31e385ad6ad6203f7056139f1" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "ca0bce1ef70a2e75db5e47a0a0f7508c" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "bf27128d35efb90f1855ab4dbf8fe289" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "65bf0625fb0cdc0307ee1a080c5acc74" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "129b90d9784e5c6fa2ca460c6a34f6d1" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "d66cc270cf1a705662834b0c740ed46f" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.20.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "f28a034fcc022f743c1df6d1ec92000c" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "d7572206dc51fb8fbad8bf7fecffb66c" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "f2025aba7b098f379978ecdb5eccb53e" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "2324c3e65f0e93d28ebee9a757229dff" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "5279aae3b14109636253fb876e2f2b50" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "328d613ad15f6305090a297e8bf5cb8b" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.21.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "19e818c2169d1d9e51ab7f3338d967f2" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "5d65bc637e47a447dcf932c48c6ba50e" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.22.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "4bc600d879433acf0aa682a6aa24c4f4" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "8dca92a08cbdc0199548c1a38d3bfb46" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 23535616, "records": [ { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.22.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 19320832 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23519232 } ], "md5sum": "1fe773d4e5af53b637877e5683d91a0a" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "754a49879dee3bfb8520b420e36cfef4" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "9b8ddced2b51f8fcdca6715cfa88f451" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "c9da3f7f32bae303eaf8c5f0559d2d1d" }, { "dataPath": "params_shard_112.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "71ba820fb19be7e797af4a2ebed49889" }, { "dataPath": "params_shard_113.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "766afbcadc8728be722325328c940f52" }, { "dataPath": "params_shard_114.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "439bec0dbdf61b19cc321109d0875f6e" }, { "dataPath": "params_shard_115.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "dd5ef4e7694dc243351744ef2cf76ffd" }, { "dataPath": "params_shard_116.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "055537838c2b103d9c606a01ef5cafcf" }, { "dataPath": "params_shard_117.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "4111db050e6e179280372997230f8d13" }, { "dataPath": "params_shard_118.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "ecd76238a9030db9067acde8a334c014" }, { "dataPath": "params_shard_119.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "cd39223800fdef75abfe696996b4861c" }, { "dataPath": "params_shard_120.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "71eb05482e08ad1bdf736f3bf58836db" }, { "dataPath": "params_shard_121.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "871ec80a5e11b9bc4e2cc64ac4662619" }, { "dataPath": "params_shard_122.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "b54682fe930aa632b1cf8a5207d0686c" }, { "dataPath": "params_shard_123.bin", "format": "raw-shard", "nbytes": 26894336, "records": [ { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 19320832 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 23519232 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26877952 } ], "md5sum": "bcc78ddf009d1cdbc44da4a25de3d465" }, { "dataPath": "params_shard_124.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "33a94cb95a1ff412049b2833e307fb12" }, { "dataPath": "params_shard_125.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "91c8e3b7e50147c3f537c9c28cfaf83a" }, { "dataPath": "params_shard_126.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "92029d004129d704e469d323f6c950fa" }, { "dataPath": "params_shard_127.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "804f38d717e9d7ef58098e6dc5d8469d" }, { "dataPath": "params_shard_128.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "5f7e54b6de7440d5d86a97068d9fe957" }, { "dataPath": "params_shard_129.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "c3a73498b65f535d3948cbf27a0f50be" }, { "dataPath": "params_shard_130.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.23.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "8e93e5c08aa0ba6bce5818a4db0d2066" }, { "dataPath": "params_shard_131.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "777446b3bd29196c2a81d2c465094410" }, { "dataPath": "params_shard_132.bin", "format": "raw-shard", "nbytes": 31100928, "records": [ { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 11763712 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15122432 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 15138816 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26886144 }, { "name": "model.layers.23.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 26902528 } ], "md5sum": "686e4f609187bd7decd0ce031fea45cd" }, { "dataPath": "params_shard_133.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "334e6ca01e2dfbda54fd02b819954a15" }, { "dataPath": "params_shard_134.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "130e2e8a2573532f98a7617a44a5265f" }, { "dataPath": "params_shard_135.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "954e0b66eeda2ee9c2e09f1c4aab9934" }, { "dataPath": "params_shard_136.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.24.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "0affead3aea9cd6fbcd0873ddfa385ef" }, { "dataPath": "params_shard_137.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "2e9d8ae95ab9f1b6fee22f92ca039e29" }, { "dataPath": "params_shard_138.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "52effd34fd5093b597bc5531f816c044" }, { "dataPath": "params_shard_139.bin", "format": "raw-shard", "nbytes": 22712320, "records": [ { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 3375104 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15122432 }, { "name": "model.layers.24.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 15138816 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 19337216 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 22695936 } ], "md5sum": "efa4e1ef5f1ba9b19c00e81b56db657f" }, { "dataPath": "params_shard_140.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "207c63f13a4c624fdfa5b72ad29a6815" }, { "dataPath": "params_shard_141.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "b690328ee63b2295445fa388b773ac54" }, { "dataPath": "params_shard_142.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.25.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "1bbc744687dd4466aa8c5b18f0bda0c8" }, { "dataPath": "params_shard_143.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "a5e0aaa6c1ff8659fb84c290171d1e10" }, { "dataPath": "params_shard_144.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "68e8cddc3eb4f84eabad993d5a784f42" }, { "dataPath": "params_shard_145.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "f2ae3e7e52cac31ffbb80aee80b4f91d" }, { "dataPath": "params_shard_146.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "91e4e28516fc7365c618fa33cbbac396" }, { "dataPath": "params_shard_147.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.26.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "e6a6e6963edf92eda41f51b164657f33" }, { "dataPath": "params_shard_148.bin", "format": "raw-shard", "nbytes": 31100928, "records": [ { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.25.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19320832 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 19337216 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31084544 } ], "md5sum": "02bdaa972366817903be56909f98cbeb" }, { "dataPath": "params_shard_149.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.26.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "c587c25291a92f949bf84ef5b302f223" }, { "dataPath": "params_shard_150.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "e07420d32925e824eed73043c898ab2c" }, { "dataPath": "params_shard_151.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.27.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "d75f24bf4a655318b3e58c6045ddfeb2" }, { "dataPath": "params_shard_152.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "8440c6ab3af86c7a505e2e80779f5f78" }, { "dataPath": "params_shard_153.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 3358720 }, { "name": "model.layers.27.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 26869760 } ], "md5sum": "25d9e6e92c0797800e6b9f594ee84bc2" }, { "dataPath": "params_shard_154.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "1f333c90ee8b462ec1c62ca085eeeecb" }, { "dataPath": "params_shard_155.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "9f519131750d44d85a4a8c4a6673e4ca" }, { "dataPath": "params_shard_156.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "0db6997877548be87c78377445ea5f43" }, { "dataPath": "params_shard_157.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "a7eb372e0de2744cdce704927f57a7b5" }, { "dataPath": "params_shard_158.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.28.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "fac929a90e395e87e9e55c95a63da155" }, { "dataPath": "params_shard_159.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "7249414de4787542fb20aa07b0c77f37" }, { "dataPath": "params_shard_160.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 3375104 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15122432 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 15155200 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26902528 }, { "name": "model.layers.28.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 26918912 } ], "md5sum": "0d73d71e7b7914629ce2bcccb759104f" }, { "dataPath": "params_shard_161.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "09dcf66ef4685268bd2c24ba9bf84551" }, { "dataPath": "params_shard_162.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "3421732972049749cbbd5cc880a69900" }, { "dataPath": "params_shard_163.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "d628044f84f91ff39110c9b30f2a4a78" }, { "dataPath": "params_shard_164.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.29.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "90d44047c1bf880635d41018e9a7271f" }, { "dataPath": "params_shard_165.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "530a0f0e86f0c1ab02efe0e93e030a4b" }, { "dataPath": "params_shard_166.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "ac9930293511cc2d42ba209d9e394213" }, { "dataPath": "params_shard_167.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "c3048517f6c300529a64ffa5903ba8a9" }, { "dataPath": "params_shard_168.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.30.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "a8302c305f971e39be823a7bed4f5c5b" }, { "dataPath": "params_shard_169.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "21afb9c4c94485744695554c69112e79" }, { "dataPath": "params_shard_170.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "8022ee18bd4a98b5830b3f2dc82a155a" }, { "dataPath": "params_shard_171.bin", "format": "raw-shard", "nbytes": 30269440, "records": [ { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 3375104 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15122432 }, { "name": "model.layers.29.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 15138816 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 19337216 }, { "name": "model.layers.30.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 22695936 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 26894336 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30253056 } ], "md5sum": "9531831835909d81a52843287941a6ca" }, { "dataPath": "params_shard_172.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "dbe1a27e962524514462c2897b5d9214" }, { "dataPath": "params_shard_173.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "61f2e99ca963f1e89c2b5f3eb1af11f6" }, { "dataPath": "params_shard_174.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "30b565307481cf76c570abaaf7b0d4e4" }, { "dataPath": "params_shard_175.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.31.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "4adf97378fca2dcb613d370115bbe7e1" }, { "dataPath": "params_shard_176.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "24145b495d976177cbaaa080056d466c" }, { "dataPath": "params_shard_177.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.32.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "3836ad9b64153b8779e00392381d156e" }, { "dataPath": "params_shard_178.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.31.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 }, { "name": "model.layers.32.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "e399e3a115544f6757f5c0370349eb95" }, { "dataPath": "params_shard_179.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "a6a1148370bada862be8054c3fd57d3f" }, { "dataPath": "params_shard_180.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "272d5864487272ca9b65dc175f1df08c" }, { "dataPath": "params_shard_181.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.32.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "b887f2a856d92f47dd32715bb0ca9f66" }, { "dataPath": "params_shard_182.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.32.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "b4ba5e144ddd841f0dd46fbeac9f00c9" }, { "dataPath": "params_shard_183.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.33.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "a75ed6e295b9b93acc523153a37dafbb" }, { "dataPath": "params_shard_184.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.33.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "202970696df5ad438ff127ebf2d2dea7" }, { "dataPath": "params_shard_185.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.33.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "5b17f2853a34b55d52d91ce62343b49c" }, { "dataPath": "params_shard_186.bin", "format": "raw-shard", "nbytes": 26894336, "records": [ { "name": "model.layers.32.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.32.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.32.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.32.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.33.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 19320832 }, { "name": "model.layers.33.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 23519232 }, { "name": "model.layers.33.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26877952 } ], "md5sum": "1080b37b70815f10325a97b6431de5df" }, { "dataPath": "params_shard_187.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "ffdcc17f802a3f856c74c4fd1944d77e" }, { "dataPath": "params_shard_188.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "297628f914e097e0be21ab96293108c3" }, { "dataPath": "params_shard_189.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.34.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "c0f50aeea8aae660391e70625ba5e169" }, { "dataPath": "params_shard_190.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "62af18dc83ee1c501d776445e10116d5" }, { "dataPath": "params_shard_191.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "4012c7585b769eae728af0217a4d0835" }, { "dataPath": "params_shard_192.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.34.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "980349129845209b70e8e4444f87b9c5" }, { "dataPath": "params_shard_193.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.34.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "8752d8d24cf202f2aacbee2bbb921a15" }, { "dataPath": "params_shard_194.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.35.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "53072d7f0c5374a5a04cd7113cdba71f" }, { "dataPath": "params_shard_195.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.33.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.33.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.34.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.34.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.34.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.34.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.34.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 }, { "name": "model.layers.35.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "b1bbf8958b22d2893dfd196b2bcde3cf" }, { "dataPath": "params_shard_196.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "7131b0285b37c5418750932f398cc60b" }, { "dataPath": "params_shard_197.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "a44c1d390a150047c5c8ce01e40e1bd6" }, { "dataPath": "params_shard_198.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.35.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "44ad88765e243453d669c606509e9809" }, { "dataPath": "params_shard_199.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.35.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "3a673a9e732692cecd3011ffb035c01a" }, { "dataPath": "params_shard_200.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.36.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "5c19679518e291e690452023b32c7fc1" }, { "dataPath": "params_shard_201.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.36.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "d3cd2a0959bd3968e5131cb2e8f6847c" }, { "dataPath": "params_shard_202.bin", "format": "raw-shard", "nbytes": 23535616, "records": [ { "name": "model.layers.35.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.35.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.35.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.35.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.36.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 19320832 }, { "name": "model.layers.36.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23519232 } ], "md5sum": "8f2e41d246e63a55e495f9febc00aa5b" }, { "dataPath": "params_shard_203.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "6097317864ce1ae6a496d49fd8c58ae5" }, { "dataPath": "params_shard_204.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "08ba8ac27cee195f7baa7f180ae4938a" }, { "dataPath": "params_shard_205.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.36.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "daa9b6cae20e41edc935a9e034bd2629" }, { "dataPath": "params_shard_206.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.37.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "341cf32547b14941dd64a2ec9106cb4a" }, { "dataPath": "params_shard_207.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.37.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "8d9696c684143351efb9dc80186a6b7a" }, { "dataPath": "params_shard_208.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.37.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "7030adb919fe7900510a54a608976181" }, { "dataPath": "params_shard_209.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.37.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "10720e1492f920ec2bda959bccee8315" }, { "dataPath": "params_shard_210.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.37.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "8bc561a5618883e5b02951583ecfdda3" }, { "dataPath": "params_shard_211.bin", "format": "raw-shard", "nbytes": 31100928, "records": [ { "name": "model.layers.36.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.36.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.36.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 11763712 }, { "name": "model.layers.37.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15122432 }, { "name": "model.layers.37.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 15138816 }, { "name": "model.layers.37.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26886144 }, { "name": "model.layers.37.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 26902528 } ], "md5sum": "dfcea47031d57a91ae072f723d8c2e1d" }, { "dataPath": "params_shard_212.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.38.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "5cb1e3c48d13299234875b2359b93512" }, { "dataPath": "params_shard_213.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "cb3893b0023d39f14600f607688f3a60" }, { "dataPath": "params_shard_214.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "4888d97a3c4adbc9b2b26f74336e0e7f" }, { "dataPath": "params_shard_215.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.38.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "a5badae1844ecc64c9791456192762b6" }, { "dataPath": "params_shard_216.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.38.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "838685a3ef1290d8276769da3d3a8101" }, { "dataPath": "params_shard_217.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.39.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "589b8cf1a52bca20347be05975d36337" }, { "dataPath": "params_shard_218.bin", "format": "raw-shard", "nbytes": 22712320, "records": [ { "name": "model.layers.37.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.38.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.38.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 3375104 }, { "name": "model.layers.38.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15122432 }, { "name": "model.layers.38.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 15138816 }, { "name": "model.layers.38.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 19337216 }, { "name": "model.layers.39.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 22695936 } ], "md5sum": "33c36ba308ebaf52409e5b239bcaea98" }, { "dataPath": "params_shard_219.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.39.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "907267d236fd347bff7824a0361ad4a2" }, { "dataPath": "params_shard_220.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.39.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "6e15626b13d2e9d203c575e41c4f5d15" }, { "dataPath": "params_shard_221.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.39.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "993c6ab498283f75a5cbbeeeb047d5b9" }, { "dataPath": "params_shard_222.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.39.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "635650d866696fc4695850b904c92288" }, { "dataPath": "params_shard_223.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.40.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "965a2c348dbf8512784bedee108f6e92" }, { "dataPath": "params_shard_224.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.40.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "1f30e360bf6ce2ceb797adefcc9233e3" }, { "dataPath": "params_shard_225.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.40.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "a07c88dc5deb145f263ac25188df6cfb" }, { "dataPath": "params_shard_226.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.40.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "e49741efe9007ce6a470733aaf592878" }, { "dataPath": "params_shard_227.bin", "format": "raw-shard", "nbytes": 31100928, "records": [ { "name": "model.layers.39.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.39.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.39.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.39.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.40.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19320832 }, { "name": "model.layers.40.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 19337216 }, { "name": "model.layers.40.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31084544 } ], "md5sum": "c4930c633d058f6107e66903fd2588c6" }, { "dataPath": "params_shard_228.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.40.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.40.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "3a6f37873f17ec05f828341f203dcb80" }, { "dataPath": "params_shard_229.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.41.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "6de99d0123e4315ae6acb5335f195fbd" }, { "dataPath": "params_shard_230.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.41.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "e760f1d86e0ca4c061eef65ecfab766c" }, { "dataPath": "params_shard_231.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.41.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "31fc9d2ca22818f8cda38ca6fd63520c" }, { "dataPath": "params_shard_232.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.40.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.41.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 3358720 }, { "name": "model.layers.41.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 26869760 } ], "md5sum": "8152c0bb5224583e033a27fe135ddb81" }, { "dataPath": "params_shard_233.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.41.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "0c310455426910fe4ab291e54753c40c" }, { "dataPath": "params_shard_234.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.42.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "40b94db2c92b7cab4644f218eb98fe98" }, { "dataPath": "params_shard_235.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.42.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "cca2568cdcd8c02500362ebb5dbe9b48" }, { "dataPath": "params_shard_236.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.42.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "35c2aae32663f29fcd657a825654c0d1" }, { "dataPath": "params_shard_237.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.42.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "6b1867f6ec9d284a5606d83fde95a6f1" }, { "dataPath": "params_shard_238.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.42.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "52391b1a7b2474bafc5fc2366ab75410" }, { "dataPath": "params_shard_239.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.41.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.41.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.41.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 3375104 }, { "name": "model.layers.41.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15122432 }, { "name": "model.layers.42.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.42.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 15155200 }, { "name": "model.layers.42.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26902528 }, { "name": "model.layers.42.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 26918912 } ], "md5sum": "cc71e94850ac11f36e01a7f739851f16" }, { "dataPath": "params_shard_240.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.43.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "5e161f6e6d955845203e616a1f588512" }, { "dataPath": "params_shard_241.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.43.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "0d91bf7a7858807cff1da09af3e2449d" }, { "dataPath": "params_shard_242.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.43.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "79a2619ce647d39ef39346b270e00716" }, { "dataPath": "params_shard_243.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.43.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "750b7cf946fa0c50ed10250dd7c5a50c" }, { "dataPath": "params_shard_244.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.43.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "8945d43d20b8474849c4cb52c49d03f0" }, { "dataPath": "params_shard_245.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.44.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "f74f1006955fb8201512ce0f597022c1" }, { "dataPath": "params_shard_246.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.44.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "3f23797b9ff64bdaeae46053dbe028c1" }, { "dataPath": "params_shard_247.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.44.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "9bf925b8892342fc17f40f5b8810bbb7" }, { "dataPath": "params_shard_248.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.44.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "8d8f771e1bf64a69a3f35debdf7cbd95" }, { "dataPath": "params_shard_249.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.44.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "24b60d4cbc05dd0c31f39270d8d20106" }, { "dataPath": "params_shard_250.bin", "format": "raw-shard", "nbytes": 30269440, "records": [ { "name": "model.layers.42.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.43.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.43.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 3375104 }, { "name": "model.layers.43.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15122432 }, { "name": "model.layers.43.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 15138816 }, { "name": "model.layers.43.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 19337216 }, { "name": "model.layers.44.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 22695936 }, { "name": "model.layers.44.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 26894336 }, { "name": "model.layers.44.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30253056 } ], "md5sum": "ab750b664d07dad18407acf19515cbbe" }, { "dataPath": "params_shard_251.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.45.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "e0b9547a64de7503303b2a9d09c37d0b" }, { "dataPath": "params_shard_252.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.45.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "fd6cfe116248eb1027dd5fcc398788c7" }, { "dataPath": "params_shard_253.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.45.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "f2dc3285854e42253481c8490a418984" }, { "dataPath": "params_shard_254.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.45.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "95612034aeaddc8cadb3aad61fbf1f1a" }, { "dataPath": "params_shard_255.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.45.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "94406b14dc71974444ed4f25ea84ae98" }, { "dataPath": "params_shard_256.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.46.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "a5c778414bbb73f9c3c7d4c4be272209" }, { "dataPath": "params_shard_257.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.44.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.44.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.45.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.45.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.45.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.45.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.45.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 }, { "name": "model.layers.46.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "9aa3690c852bddd6eb0aa72a6fa4be5e" }, { "dataPath": "params_shard_258.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.46.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "f86cf29974fe347948a65f6b4f520983" }, { "dataPath": "params_shard_259.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.46.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "71cf720966a900313a23620ba8f92e88" }, { "dataPath": "params_shard_260.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.46.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "12e17f7739e771be020df18466cf1e1f" }, { "dataPath": "params_shard_261.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.46.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "d305c8583f96004cfa583f26971c4aac" }, { "dataPath": "params_shard_262.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.47.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "69ba6c414d64cc665dcd78c7e9fdb4d1" }, { "dataPath": "params_shard_263.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.47.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "8255a01d47fe211c567f770bbe9eae7e" }, { "dataPath": "params_shard_264.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.47.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "f84f76f1b9e24f055942cda649790fe0" }, { "dataPath": "params_shard_265.bin", "format": "raw-shard", "nbytes": 26894336, "records": [ { "name": "model.layers.46.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.46.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.46.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.46.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.47.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 19320832 }, { "name": "model.layers.47.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 23519232 }, { "name": "model.layers.47.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26877952 } ], "md5sum": "95f32f39f28d4cc984c2fce662f9a461" }, { "dataPath": "params_shard_266.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.47.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "345ed3e95efaa89fff5bc3c709d4c3f4" }, { "dataPath": "params_shard_267.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.47.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "5f4f987ea927124671352b744f9bf3f1" }, { "dataPath": "params_shard_268.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.48.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "20352270123ac802cee7163f5568c68f" }, { "dataPath": "params_shard_269.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.48.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "de1e5ab4b951b4ed059b6dad9b213baa" }, { "dataPath": "params_shard_270.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.48.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "0e4c27d4091a34061be80a1abc96012e" }, { "dataPath": "params_shard_271.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.48.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "1dcdc14790e6102f2df15d3ad75a95f5" }, { "dataPath": "params_shard_272.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.48.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "01f64f2b9253d2fc9260d8efcf351273" }, { "dataPath": "params_shard_273.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.49.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "4b872548b00db495506d71db75d43c0b" }, { "dataPath": "params_shard_274.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.47.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.47.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.48.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.48.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.48.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.48.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.48.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 }, { "name": "model.layers.49.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "b36c97b3b35f825b280833e07109eb8e" }, { "dataPath": "params_shard_275.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.49.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "5e16e01f9be6cc99d470c03da8765480" }, { "dataPath": "params_shard_276.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.49.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "859fbaee21690b1a656f2ff006978ce9" }, { "dataPath": "params_shard_277.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.49.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "65fd223e59ebc3b034d117d1a29f2357" }, { "dataPath": "params_shard_278.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.49.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "342a66607ae887a37480a412afa28fc7" }, { "dataPath": "params_shard_279.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.50.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "12ae64706593394209fc4399c1152a0e" }, { "dataPath": "params_shard_280.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "30189bf640ce8811f47dc3749985d4fa" }, { "dataPath": "params_shard_281.bin", "format": "raw-shard", "nbytes": 23535616, "records": [ { "name": "model.layers.49.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.49.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.49.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.49.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.50.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 19320832 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23519232 } ], "md5sum": "bc02116465674b4f4fbacfec169742e7" }, { "dataPath": "params_shard_282.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "cc124dfcddfbc0e7dd7048a0753a9139" }, { "dataPath": "params_shard_283.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "7c6751d7115a5b77ca01e1c624e146f1" }, { "dataPath": "params_shard_284.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "c174d16f7fa393e7a65712f61cc89e58" }, { "dataPath": "params_shard_285.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "2199cb2d0dcc5915f447286206473a5a" }, { "dataPath": "params_shard_286.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "16bfee3107217844cb5a97cf1c747065" }, { "dataPath": "params_shard_287.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "335112f57e2f294f3ba13677e4bf1552" }, { "dataPath": "params_shard_288.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "db91f532b4d8c999d927778fc9f811e7" }, { "dataPath": "params_shard_289.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "efa7a8ed33671e845899c691388c65f2" }, { "dataPath": "params_shard_290.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "2b2faae95af751f02118e0d3c00a7832" }, { "dataPath": "params_shard_291.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "542bd28b06011f669b6d9b424f52e810" }, { "dataPath": "params_shard_292.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "a76b971897197df0dfa634602cb70539" }, { "dataPath": "params_shard_293.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "8134868d7e88b941503e8aa9d663f47c" }, { "dataPath": "params_shard_294.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "b0d69178555a74c88c5d7589ea9ad29e" }, { "dataPath": "params_shard_295.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "7eaa39b4346eddadda09e8d5647aef2c" }, { "dataPath": "params_shard_296.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.50.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "ce3a8253cca6c409d481ad88baf791f6" }, { "dataPath": "params_shard_297.bin", "format": "raw-shard", "nbytes": 23535616, "records": [ { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 19320832 }, { "name": "model.layers.50.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23519232 } ], "md5sum": "94f620f9902e779082a945f2a6163b09" }, { "dataPath": "params_shard_298.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.50.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "591dc57e6d1fae0a990389582752bbf0" }, { "dataPath": "params_shard_299.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.50.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "bb5c9b2dd4a54a84b764a7de382cb40d" }, { "dataPath": "params_shard_300.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.50.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "f6a718cd4b7cf7685b059d7626e061e2" }, { "dataPath": "params_shard_301.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.51.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "425a2400688b7184b118f9db10b8dd85" }, { "dataPath": "params_shard_302.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.51.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "62860dd8d467ec516913c208a2a7d037" }, { "dataPath": "params_shard_303.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.51.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "ca3244b188eecc08faba4b72fa1d86b9" }, { "dataPath": "params_shard_304.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.51.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "24e121e1fc534479e6b4e9e385f897e3" }, { "dataPath": "params_shard_305.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.51.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "0562b938943ffdde178c0b0c69b9dd57" }, { "dataPath": "params_shard_306.bin", "format": "raw-shard", "nbytes": 31100928, "records": [ { "name": "model.layers.50.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.50.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.50.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 11763712 }, { "name": "model.layers.51.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15122432 }, { "name": "model.layers.51.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 15138816 }, { "name": "model.layers.51.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26886144 }, { "name": "model.layers.51.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 26902528 } ], "md5sum": "04c05a59341453d9cd02a0427857d39d" }, { "dataPath": "params_shard_307.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.52.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "a64c7aca746042562af5a030c452eb1b" }, { "dataPath": "params_shard_308.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.52.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "4a09878d5f2e6a4ef3f657ea9fe8a6a9" }, { "dataPath": "params_shard_309.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.52.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "098618175a2d72bdf1acd9e412df9725" }, { "dataPath": "params_shard_310.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.52.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "92323b598f7bfaa20c39b238bcf4195c" }, { "dataPath": "params_shard_311.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.52.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "14360ae5531c043d50f90f5ce7bfb85f" }, { "dataPath": "params_shard_312.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.53.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "61c262b05b74300268d8e944e4546cdd" }, { "dataPath": "params_shard_313.bin", "format": "raw-shard", "nbytes": 22712320, "records": [ { "name": "model.layers.51.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.52.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.52.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 3375104 }, { "name": "model.layers.52.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15122432 }, { "name": "model.layers.52.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 15138816 }, { "name": "model.layers.52.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 19337216 }, { "name": "model.layers.53.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 22695936 } ], "md5sum": "b4fd232cf394c978b254ccb44915af54" }, { "dataPath": "params_shard_314.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.53.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "7b5f8e9805c7ca506e18ae327adeb4d7" }, { "dataPath": "params_shard_315.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.53.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "32c6f2328b4c798f5f860484889b9877" }, { "dataPath": "params_shard_316.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.53.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "c7cd5d0a12ce8a99cd2b9acc8ebf1fce" }, { "dataPath": "params_shard_317.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.53.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "1cd03ce94509546f4e4a77a50c32122a" }, { "dataPath": "params_shard_318.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.54.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "8cf7605ee0d9c9a41b48b44045193052" }, { "dataPath": "params_shard_319.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.54.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "38a3dd8511152797a3a08dd752d75109" }, { "dataPath": "params_shard_320.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.54.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "56d0bf4fc0ed93309635e49f160905bf" }, { "dataPath": "params_shard_321.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.54.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "ceaa00867ae4e1eb55d5dc775b88e979" }, { "dataPath": "params_shard_322.bin", "format": "raw-shard", "nbytes": 31100928, "records": [ { "name": "model.layers.53.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.53.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.53.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.53.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.54.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19320832 }, { "name": "model.layers.54.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 19337216 }, { "name": "model.layers.54.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31084544 } ], "md5sum": "2f40526ae0f386e13918ac8ac2f98e97" }, { "dataPath": "params_shard_323.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.54.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.54.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "656bb6351da9b4100ed1a825f6ec5b67" }, { "dataPath": "params_shard_324.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.55.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "791fe39f3aa7157ecb884cd2de449e5f" }, { "dataPath": "params_shard_325.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.55.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "0a8ccefb72573ba68bf629fdc49db92f" }, { "dataPath": "params_shard_326.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.55.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "692864d3de4d6b44f370e81da30a7186" }, { "dataPath": "params_shard_327.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.54.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.55.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 3358720 }, { "name": "model.layers.55.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 26869760 } ], "md5sum": "3394f09afd2432c508de527f45d84fd4" }, { "dataPath": "params_shard_328.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.55.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "24c23df10a217a6db682073768b145d3" }, { "dataPath": "params_shard_329.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.56.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "bfef43dffeb9c8d67acd799fc8817064" }, { "dataPath": "params_shard_330.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.56.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "f537a135ff3d1313676d69eba6574de6" }, { "dataPath": "params_shard_331.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.56.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "f2279c45a7764720c08dc1af94b587e8" }, { "dataPath": "params_shard_332.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.56.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "0f6cf649ba1ff501fb70d456e8de96e5" }, { "dataPath": "params_shard_333.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.56.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "b32f52a01c4f662c2b9062d77d4aef57" }, { "dataPath": "params_shard_334.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.55.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.55.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.55.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 3375104 }, { "name": "model.layers.55.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15122432 }, { "name": "model.layers.56.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.56.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 15155200 }, { "name": "model.layers.56.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26902528 }, { "name": "model.layers.56.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 26918912 } ], "md5sum": "5984fa93b7477409652cb6940f28dc45" }, { "dataPath": "params_shard_335.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.57.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "1e892c648a8cdf536ba6e301aad91384" }, { "dataPath": "params_shard_336.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.57.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "a1674b6e979d9c84a9d06925f631919f" }, { "dataPath": "params_shard_337.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.57.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "53c7fef8ac176c548a25a07d9fb0ccb8" }, { "dataPath": "params_shard_338.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.57.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "bb91ba0c0fc01477cf3358130df3f077" }, { "dataPath": "params_shard_339.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.57.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "d25581a073b4e30d19220e7733a7355a" }, { "dataPath": "params_shard_340.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.58.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "abebbffb40688ce70ddc7c2b8e2e3da9" }, { "dataPath": "params_shard_341.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.58.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "f54934416a7dfef3ad9a8045a3b01358" }, { "dataPath": "params_shard_342.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.58.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "882b4bb025cafec8cf867ad8fa6a1f6f" }, { "dataPath": "params_shard_343.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.58.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "3a0a7d5d76aeef33a459658edbb68131" }, { "dataPath": "params_shard_344.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.58.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "815d4c338d176ce6331692c8cd6cfee2" }, { "dataPath": "params_shard_345.bin", "format": "raw-shard", "nbytes": 30269440, "records": [ { "name": "model.layers.56.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.57.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.57.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 3375104 }, { "name": "model.layers.57.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15122432 }, { "name": "model.layers.57.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 15138816 }, { "name": "model.layers.57.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 19337216 }, { "name": "model.layers.58.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 22695936 }, { "name": "model.layers.58.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 26894336 }, { "name": "model.layers.58.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30253056 } ], "md5sum": "f93c358ca0ffeef22ed6474b764d1004" }, { "dataPath": "params_shard_346.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.59.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "29c67dba213a4da5dfefd10f34568f6d" }, { "dataPath": "params_shard_347.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.59.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "4437dd777a1753c7fbff969e015b32b1" }, { "dataPath": "params_shard_348.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.59.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "ba04c6a5282e8db4d747e3608fddac65" }, { "dataPath": "params_shard_349.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.59.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "42e160b460c7ce9e62ddf73d5432ce31" }, { "dataPath": "params_shard_350.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.59.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "723e73eaad3bc2c94db73a239b9daf25" }, { "dataPath": "params_shard_351.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.60.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "0514ce293aaf4bb9f4485b08405a07cc" }, { "dataPath": "params_shard_352.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.58.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.58.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.59.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.59.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.59.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.59.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.59.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 }, { "name": "model.layers.60.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "a238b7849897569fee95d81f0b506bc7" }, { "dataPath": "params_shard_353.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.60.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "7c124858c6a4e2941c08686e9e211f1e" }, { "dataPath": "params_shard_354.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.60.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "fc01af296221b4fabd429bc627feeff4" }, { "dataPath": "params_shard_355.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.60.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "8154513708a5fa8ba3f4f2b0fd674978" }, { "dataPath": "params_shard_356.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.60.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "5eb0ccb775f06e6443e9dadb0177edc5" }, { "dataPath": "params_shard_357.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.61.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "eacdeb28f44775d5c168c3adef5b6360" }, { "dataPath": "params_shard_358.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.61.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "c7a01475adfcb499bff7632b49ab1b5c" }, { "dataPath": "params_shard_359.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.61.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "490006412bd1a492a72be7acfa55ded2" }, { "dataPath": "params_shard_360.bin", "format": "raw-shard", "nbytes": 26894336, "records": [ { "name": "model.layers.60.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.60.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.60.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.60.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.61.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 19320832 }, { "name": "model.layers.61.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 23519232 }, { "name": "model.layers.61.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26877952 } ], "md5sum": "d489258bdf6e9091c25f4d5908095245" }, { "dataPath": "params_shard_361.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.61.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "e653f6199616d2ecfc61c361c43578b5" }, { "dataPath": "params_shard_362.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.61.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "63701cfa807dc4f56337f486d90f2798" }, { "dataPath": "params_shard_363.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.62.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "91c29cd7adeebc2a510ab2f0f5cbe8f8" }, { "dataPath": "params_shard_364.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.62.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "e10df218ec9a00568f000203bafe13b3" }, { "dataPath": "params_shard_365.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.62.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "93986ecb9e26b772f05220f0b84c844d" }, { "dataPath": "params_shard_366.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.62.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "5ac90a0cfefbf484c5628185c7e7a333" }, { "dataPath": "params_shard_367.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.62.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "130b748ffca73451d3fc37981c3f42b0" }, { "dataPath": "params_shard_368.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.63.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "15f617babbef3ca36337ed20decd8f65" }, { "dataPath": "params_shard_369.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.61.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.61.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.62.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.62.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.62.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.62.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.62.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 }, { "name": "model.layers.63.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "21fa2ca00e7cc0e7a113fc052c1f1b93" }, { "dataPath": "params_shard_370.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.63.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "c539fa81fe4c1ffe7a7ad9f37d3a409d" }, { "dataPath": "params_shard_371.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.63.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "1378c0c1bdd2cc0da0715957ad5a0681" }, { "dataPath": "params_shard_372.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.63.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "b26c2c8388ea56340b8eebd9724f1cbc" }, { "dataPath": "params_shard_373.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.63.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "ce85c62dbb2557b72101acf228616975" }, { "dataPath": "params_shard_374.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.64.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "b62335700b2c1f820f86be6b8c07271c" }, { "dataPath": "params_shard_375.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.64.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "8afe6216978488830a6d8f18904bd84f" }, { "dataPath": "params_shard_376.bin", "format": "raw-shard", "nbytes": 23535616, "records": [ { "name": "model.layers.63.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.63.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.63.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.63.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.64.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 19320832 }, { "name": "model.layers.64.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23519232 } ], "md5sum": "35976e151a410e2166a2aac5203e1169" }, { "dataPath": "params_shard_377.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.64.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "02c7979a9396b93198d9fcdc04bc153e" }, { "dataPath": "params_shard_378.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.64.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "ee3ecd776e097df13771ee89ba55e589" }, { "dataPath": "params_shard_379.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.64.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "4da5c35d6611ee2838035763d7072f5d" }, { "dataPath": "params_shard_380.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.65.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "7a9ff3dae8dbdc6b05f76364ee3ae6e2" }, { "dataPath": "params_shard_381.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.65.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "07faaa97005208bc91826b1616d54bc7" }, { "dataPath": "params_shard_382.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.65.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "cba0036f398df01301e5770878d805c1" }, { "dataPath": "params_shard_383.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.65.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "aef348c05710f23ba58272cd173025b0" }, { "dataPath": "params_shard_384.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.65.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "0964255a76d5b06e35d3479ba53bee15" }, { "dataPath": "params_shard_385.bin", "format": "raw-shard", "nbytes": 31100928, "records": [ { "name": "model.layers.64.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.64.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.64.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 11763712 }, { "name": "model.layers.65.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15122432 }, { "name": "model.layers.65.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 15138816 }, { "name": "model.layers.65.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26886144 }, { "name": "model.layers.65.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 26902528 } ], "md5sum": "164f0f21b6f19852357088dcf2301928" }, { "dataPath": "params_shard_386.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.66.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "c9e38a6af835f101464c05e66ba18cef" }, { "dataPath": "params_shard_387.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.66.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "e131f0885dda0c08d91d1140b1506091" }, { "dataPath": "params_shard_388.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.66.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "ccb05b64d862760659e3132731f6de01" }, { "dataPath": "params_shard_389.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.66.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "8a3d1c111c7e6a41e6fb9b3a3dd3d838" }, { "dataPath": "params_shard_390.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.66.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "88327fac0beeb710cfe19a2168e1f8e8" }, { "dataPath": "params_shard_391.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.67.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "e3fc84b9e56cd9451ab8ff6947f265a9" }, { "dataPath": "params_shard_392.bin", "format": "raw-shard", "nbytes": 22712320, "records": [ { "name": "model.layers.65.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.66.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.66.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 3375104 }, { "name": "model.layers.66.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15122432 }, { "name": "model.layers.66.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 15138816 }, { "name": "model.layers.66.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 19337216 }, { "name": "model.layers.67.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 22695936 } ], "md5sum": "e78f37016c6f48dffb749447cfc7870b" }, { "dataPath": "params_shard_393.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.67.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "ba40fac07faa1926bf8450c5245fcb3c" }, { "dataPath": "params_shard_394.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.67.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "b0eb648edc384e297375cb2bc391f2e9" }, { "dataPath": "params_shard_395.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.67.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "9604e98716dc1cf3142cdaa560adf2f6" }, { "dataPath": "params_shard_396.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.67.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "cf4b78e3a83da4409e2f16317bb61a23" }, { "dataPath": "params_shard_397.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.68.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "8412877cbcd2f93d34bb5807ae8dd6db" }, { "dataPath": "params_shard_398.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.68.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "8bd206d71a1c1c4323fbbb13c07d5fa3" }, { "dataPath": "params_shard_399.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.68.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "6637ac64e7dc0319143ec5c38c6f69bb" }, { "dataPath": "params_shard_400.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.68.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "9022d10a948eecf1547401ef1ebf0ef0" }, { "dataPath": "params_shard_401.bin", "format": "raw-shard", "nbytes": 31100928, "records": [ { "name": "model.layers.67.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.67.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.67.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.67.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.68.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19320832 }, { "name": "model.layers.68.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 19337216 }, { "name": "model.layers.68.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31084544 } ], "md5sum": "d72f21125474d957313589d51f9eb635" }, { "dataPath": "params_shard_402.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.68.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.68.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "9ca1f3557a706a949e533da847c1702b" }, { "dataPath": "params_shard_403.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.69.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "09a68e37082c21f07c7783896f370fa6" }, { "dataPath": "params_shard_404.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.69.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "dcf18112b2b93a801f78a14e46cdb558" }, { "dataPath": "params_shard_405.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.69.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "4abedcd27abe15d3e4bfb483f3951774" }, { "dataPath": "params_shard_406.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.68.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.69.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 3358720 }, { "name": "model.layers.69.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 26869760 } ], "md5sum": "fbcbba0477f32137672a37f246a69f83" }, { "dataPath": "params_shard_407.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.69.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "c5b01a3df05a42c59f295c6adc341f80" }, { "dataPath": "params_shard_408.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.70.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "d5ab95eac51195df6f6009c56a43e0c5" }, { "dataPath": "params_shard_409.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.70.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "e719a03d35bfb780f7ec5ddccf9f1669" }, { "dataPath": "params_shard_410.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.70.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "4a5367fee7fcd2633135777892ce6850" }, { "dataPath": "params_shard_411.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.70.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "a69c19ed7f0b49ee9695e1d6e07a29a0" }, { "dataPath": "params_shard_412.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.70.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "5d5c91df10e7a808657d4b35cb22f9d1" }, { "dataPath": "params_shard_413.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.69.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.69.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.69.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 3375104 }, { "name": "model.layers.69.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15122432 }, { "name": "model.layers.70.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.70.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 15155200 }, { "name": "model.layers.70.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26902528 }, { "name": "model.layers.70.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 26918912 } ], "md5sum": "6aefe980f4d400d0e898ad6bbdd72c6b" }, { "dataPath": "params_shard_414.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.71.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "63a8d9688db3502b7da8b850b6792917" }, { "dataPath": "params_shard_415.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.71.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "5f4b1e608420b0e2690b3cf2f47dc3e9" }, { "dataPath": "params_shard_416.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.71.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "a391aeb8322d7b1fef29d3321a49f681" }, { "dataPath": "params_shard_417.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.71.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "7690c86876fbd2bd8d06983dde90b3a1" }, { "dataPath": "params_shard_418.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.71.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "6e8ab411c20b944d642a908006304d98" }, { "dataPath": "params_shard_419.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.72.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "ae027964c532b25385d9bee669a27aa9" }, { "dataPath": "params_shard_420.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.72.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "f4a1ed69f3d610d5c36cbfcefbfcc163" }, { "dataPath": "params_shard_421.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.72.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "6199cd0b094ebc37e7cd55d3d4568c35" }, { "dataPath": "params_shard_422.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.72.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "0b8ba3be9aebf61b1e2307d5201c67d7" }, { "dataPath": "params_shard_423.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.72.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "46c093a24c0a025999356683a11b5474" }, { "dataPath": "params_shard_424.bin", "format": "raw-shard", "nbytes": 30269440, "records": [ { "name": "model.layers.70.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.71.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.71.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 3375104 }, { "name": "model.layers.71.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15122432 }, { "name": "model.layers.71.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 15138816 }, { "name": "model.layers.71.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 19337216 }, { "name": "model.layers.72.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 22695936 }, { "name": "model.layers.72.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 26894336 }, { "name": "model.layers.72.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30253056 } ], "md5sum": "97f5fd3359c65f8532a696abc6abb81a" }, { "dataPath": "params_shard_425.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.73.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "9cbaf8e4378b1a3e35bd4a4785832480" }, { "dataPath": "params_shard_426.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.73.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "4a8351d2690bfadcf33e5876cc8701a6" }, { "dataPath": "params_shard_427.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.73.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "d29d4b7995144f2ecb0fd99d8f1f1bf4" }, { "dataPath": "params_shard_428.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.73.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "38b833f788a04afff17428c5030df7f7" }, { "dataPath": "params_shard_429.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.73.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "c86b0fe399b92607e73a1f48efa5b408" }, { "dataPath": "params_shard_430.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.74.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "f35582ae422db4a9795356bb120565d5" }, { "dataPath": "params_shard_431.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.72.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.72.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.73.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.73.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.73.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.73.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.73.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 }, { "name": "model.layers.74.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "216545ed37800417b94950b6bcece275" }, { "dataPath": "params_shard_432.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.74.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "7e00b08fd779967945b1b4cdf0eba6e8" }, { "dataPath": "params_shard_433.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.74.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "8f7dc045286f29000d28d4629eaedd99" }, { "dataPath": "params_shard_434.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.74.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "01598d17c6f0b619ec7fd26005bb86a1" }, { "dataPath": "params_shard_435.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.74.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "c1a2ca65d9064316804531cd9fb03834" }, { "dataPath": "params_shard_436.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.75.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "3626802b1294c78d66dc09ccc40feadf" }, { "dataPath": "params_shard_437.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.75.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "c68e1634edef08cf8e64ffe73923458e" }, { "dataPath": "params_shard_438.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.75.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "439fb373ce93098913b617bfef609202" }, { "dataPath": "params_shard_439.bin", "format": "raw-shard", "nbytes": 26894336, "records": [ { "name": "model.layers.74.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.74.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.74.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.74.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.75.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 19320832 }, { "name": "model.layers.75.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 23519232 }, { "name": "model.layers.75.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26877952 } ], "md5sum": "f8969659467e325a89a60efdf32fc048" }, { "dataPath": "params_shard_440.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.75.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "087a459916bda0a58e80ab11ca6565ae" }, { "dataPath": "params_shard_441.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.75.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "f199f4ea0d3b176458c5984e0c552f89" }, { "dataPath": "params_shard_442.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.76.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "b8146e7f9bd8b2d8a9e5eb8e3e94afa5" }, { "dataPath": "params_shard_443.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.76.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "af96f27429da40f412362377f4e4fce2" }, { "dataPath": "params_shard_444.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.76.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "2c989f3a731f4692b2a5060e3ecf72ba" }, { "dataPath": "params_shard_445.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.76.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "e890e58b7a49b753b9e6166b533f4b74" }, { "dataPath": "params_shard_446.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.76.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "dac3baa4f8c901ae8739eb8dd5b956ae" }, { "dataPath": "params_shard_447.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.77.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "da9f0c945a6bbc185486830a4e4c9e18" }, { "dataPath": "params_shard_448.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.75.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.75.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.76.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.76.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.76.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.76.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.76.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 }, { "name": "model.layers.77.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "b4282651139f97cbbc05a77acf120325" }, { "dataPath": "params_shard_449.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.77.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "11e5dfa6015cf039a4a3206aaf393031" }, { "dataPath": "params_shard_450.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.77.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "03e495dac4d9befbdaba44316cfb1d15" }, { "dataPath": "params_shard_451.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.77.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "b9cb080f048c45a88f88b271266f7dd0" }, { "dataPath": "params_shard_452.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.77.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "8b21d86bcec7661052388690f7d12876" }, { "dataPath": "params_shard_453.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.78.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "b9cbe9eb2992cd51fe89792ee9a09031" }, { "dataPath": "params_shard_454.bin", "format": "raw-shard", "nbytes": 23519232, "records": [ { "name": "model.layers.77.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.77.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.77.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.77.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.78.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 19320832 } ], "md5sum": "958483c3745523d61f6973c51df92efb" } ] }