{ "metadata": { "ParamSize": 805, "ParamBytes": 31776333224.0, "BitsPerParam": 3.0402330773461475 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 420686240, "records": [ { "name": "lm_head.q_weight", "shape": [ 128258, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 420686240, "byteOffset": 0 } ], "md5sum": "bc762f917caa677f7059317a47026d4f" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 52585780, "records": [ { "name": "lm_head.q_scale", "shape": [ 128258, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 52585780, "byteOffset": 0 } ], "md5sum": "bd692c097fbe81b9d09b7a35e6d6254d" }, { "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": "4f361b8bdd8cb00a92f6924621ed6b3f" }, { "dataPath": "params_shard_3.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": "5dc738735cc8778a9b6478a690ee7e15" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 23560192, "records": [ { "name": "model.layers.78.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 0 }, { "name": "model.layers.78.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 16384 }, { "name": "model.layers.78.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.79.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23543808 } ], "md5sum": "7a7367486baa0157e8febcac7a2a3d38" }, { "dataPath": "params_shard_5.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": "59d754dea1734cdf5350f834b191985f" }, { "dataPath": "params_shard_6.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": "4db98c5a3031b1f7c1e4a8349cd63d10" }, { "dataPath": "params_shard_7.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": "1efcdf8ef688b8dd93d25e0b38c7b7b2" }, { "dataPath": "params_shard_8.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": "61cc1033858c526540c55ea4c76d31d4" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 420686240, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 128258, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 420686240, "byteOffset": 0 } ], "md5sum": "ab0b603e89165b94f46d05ac53fe7ed1" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 52585780, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 128258, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 52585780, "byteOffset": 0 } ], "md5sum": "b8525b7d97e17a456ebba4b084b8ae47" }, { "dataPath": "params_shard_11.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": "15679a9ef043084787740e77a275212d" }, { "dataPath": "params_shard_12.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": "55705a5e048d4d50431019907269fba2" }, { "dataPath": "params_shard_13.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": "6df8ee6870532f510ff438bff20e0ee3" }, { "dataPath": "params_shard_14.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": "d8706a3b43225fe3d452a10e224be347" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 31117312, "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.layers.0.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19337216 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 19353600 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "d324a869f4c0d3fd122bfa66c6594dae" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "2f312bc6a64e630f8c0d9d0ea34efc2a" }, { "dataPath": "params_shard_17.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": "a5fe2df120b51bee4a5e3d3cfcfd53da" }, { "dataPath": "params_shard_18.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": "8be60a1931fb7d57d34193eabdc4a64d" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "3977def7e0af3b324d8a188b74193108" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 3358720 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 26869760 } ], "md5sum": "25869ee46ee9ece58e521f13c4216fed" }, { "dataPath": "params_shard_21.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": "9eb737f4dc6814bfb2183ee73fdbec43" }, { "dataPath": "params_shard_22.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": "81a201931b8f2b46373c6142da059880" }, { "dataPath": "params_shard_23.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": "88194e3e237659343aa3f5fb5aea47b9" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "853b00c08a32e6a42ac1ff3fdc1412ff" }, { "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": "e6d017e67c7393e4a9613a19e991a0a0" }, { "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": "48a063e6c628d62ada61e84d4fe6200d" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 31117312, "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.1.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 3375104 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15122432 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 15155200 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26902528 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 26918912 } ], "md5sum": "18e11beac5f285ab6d251b9c5620b253" }, { "dataPath": "params_shard_28.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": "3519b5be60e15a62800edf0a5a88c1dd" }, { "dataPath": "params_shard_29.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": "d0c6259d464f31270925139818f2154b" }, { "dataPath": "params_shard_30.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": "9a3ea58c39fd23ef310392402feaed67" }, { "dataPath": "params_shard_31.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": "b1f261b5093fc94eeea23c616cfec5df" }, { "dataPath": "params_shard_32.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": "c3d9dd25d2db2c3ef582074058ed5152" }, { "dataPath": "params_shard_33.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": "082ea30d09c235d6efc7f4b4264d52e6" }, { "dataPath": "params_shard_34.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": "89d0907a5b3c27deebe254c87de3d374" }, { "dataPath": "params_shard_35.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": "e7501a2c93daffd75695e266235222e6" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 30269440, "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.3.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 3375104 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15122432 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 15138816 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 19337216 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 22695936 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 26894336 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30253056 } ], "md5sum": "fcb2bbac9b52b90192f6cf6d35a63bb9" }, { "dataPath": "params_shard_37.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": "80b5987e40a41444c5a16006ac23cef3" }, { "dataPath": "params_shard_38.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": "3a1ac847813b4cc64bd1ffae9c401bce" }, { "dataPath": "params_shard_39.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": "92d0fb0b4c2ab0e64313a329f19bf04d" }, { "dataPath": "params_shard_40.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": "2ef2b36bebb1fe446c7cfa78d097375e" }, { "dataPath": "params_shard_41.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": "b40d76c01e983d877610f9a022f6a9c3" }, { "dataPath": "params_shard_42.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": "24ffb2c587e01f832bb0b704265653c3" }, { "dataPath": "params_shard_43.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": "b0ab50576f8d594572f406bcda87b55a" }, { "dataPath": "params_shard_44.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": "a367065586ccfe581ba95e1059c8bb0c" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 31100928, "records": [ { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19320832 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 19337216 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31084544 } ], "md5sum": "d4ff132576a5e83b8b2b2864f7a9b882" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "eda4218295050bcbfb7e73e88edf53e7" }, { "dataPath": "params_shard_47.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": "f30bb18f710612dee30c48886aa36e51" }, { "dataPath": "params_shard_48.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": "e51ff228ab503a953d49c8fcddf68b5c" }, { "dataPath": "params_shard_49.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": "773d78f0f376daf56c97ca81680d0590" }, { "dataPath": "params_shard_50.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": "776901a7357c4de90ed461e2ae9a6488" }, { "dataPath": "params_shard_51.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": "b8530bc75d5928c1f24b1caa46c997f6" }, { "dataPath": "params_shard_52.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": "13043823e077798847c2dcf57df1f85e" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 22712320, "records": [ { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 3358720 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 7557120 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 10915840 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 10932224 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 22679552 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 22695936 } ], "md5sum": "19a06a78b92b09f87dda120bebe96430" }, { "dataPath": "params_shard_54.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": "83e2258194360cd387c27c2e4b2983db" }, { "dataPath": "params_shard_55.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": "ceabed48e21b30f39ba3cfc54fdb2d87" }, { "dataPath": "params_shard_56.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": "7a72dc0a7c3d56abd9e8cac0c45a1ac0" }, { "dataPath": "params_shard_57.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": "d63312b049bd727eca98b6b704c70edc" }, { "dataPath": "params_shard_58.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": "43dc368ce08f643b1ced6c2a9f27756f" }, { "dataPath": "params_shard_59.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": "a6420c56829728c2c9c63bcb7bd4e133" }, { "dataPath": "params_shard_60.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": "d7f1b9091b929efb0a4a619187faa973" }, { "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": "6ac4aba28ec4508eca057743eca4743e" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 31100928, "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.13.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 } ], "md5sum": "ad8bea5a90182134cbb6fff278c7f7c0" }, { "dataPath": "params_shard_63.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": "7c502add1d382fa45df3082664fb05b4" }, { "dataPath": "params_shard_64.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": "643cd1eeda6a9d50e771e2f482d3287f" }, { "dataPath": "params_shard_65.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": "ca130d4bb7ba3837083143e724bf71b7" }, { "dataPath": "params_shard_66.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": "0767a25a9675c400b65d7c302b99aab7" }, { "dataPath": "params_shard_67.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": "4d791d818eb7688b9e35f6ff02b44b4b" }, { "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": "f39e2f7777b867852881492e91b762c7" }, { "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": "5eb24419c7baa834185f0da4cd0b2639" }, { "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": "8722cc105f3f9fe46ba38315b55d9678" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11747328 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15945728 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19304448 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19320832 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19337216 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 19353600 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "054925aa30973a20c2ce5f7560491ef7" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "f98ce8562669cc6aa53f473e46a2fcd3" }, { "dataPath": "params_shard_73.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": "138e10613ce1f1a248883498042bcbb5" }, { "dataPath": "params_shard_74.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": "2b46986404fc363e120d53beac457345" }, { "dataPath": "params_shard_75.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": "e38dda4aca82aac6876d3e5880b36b3d" }, { "dataPath": "params_shard_76.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": "137ca3d02e0701591ade8cfb96f664c3" }, { "dataPath": "params_shard_77.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": "b0de07d5500add8f422949d896421cdb" }, { "dataPath": "params_shard_78.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": "eec1aa9de60fe2f3280030f5f260aac6" }, { "dataPath": "params_shard_79.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": "3834befb087aef3c0ddf0347fa85d2e2" }, { "dataPath": "params_shard_80.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": "a4bb493f7e019bf2a535d7d736806fa0" }, { "dataPath": "params_shard_81.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": "81579efdd2e92e008abb2b53eae503bc" }, { "dataPath": "params_shard_82.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": "4a589d23740c554f17d981578f8432e4" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 30269440, "records": [ { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 3375104 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15122432 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 15138816 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 19337216 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 22695936 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 26894336 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30253056 } ], "md5sum": "e2e954dbcddcaa51b27c73f6dc87d4a1" }, { "dataPath": "params_shard_84.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": "ce8b86021c818a5f0bf1e4265aa98479" }, { "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": "f1da63322adff3a6ed2f5f67a14e47e2" }, { "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": "020fb650aef3c6db6d24ddd631027893" }, { "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": "2bd63b6b4f5f0fbf02a7e83667328712" }, { "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": "09e92a2fe4e53627c62089a0bf7ff5c0" }, { "dataPath": "params_shard_89.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": "f4a6cc8b27e8e55629a48fbbb07838a8" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "32faa6091b15c9593f3a2eeae0ce9e90" }, { "dataPath": "params_shard_91.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": "328c759269f1a8e26e522fdba8017c79" }, { "dataPath": "params_shard_92.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": "310b952f7cd15f53a178937d2c0ba384" }, { "dataPath": "params_shard_93.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": "c632de30e2e4114502f7d7319a102396" }, { "dataPath": "params_shard_94.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": "407cd388f6a6639597b62b616de3053e" }, { "dataPath": "params_shard_95.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": "45a71b777dc455197f6ad254fcf2b6e0" }, { "dataPath": "params_shard_96.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": "764dd7ff68ad794d3e483cd2606700da" }, { "dataPath": "params_shard_97.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": "cd0760319a13378fcb38390829f14d15" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 26894336, "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.19.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 19320832 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 23519232 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26877952 } ], "md5sum": "3542b05824b8c7b7cebedde142ab9355" }, { "dataPath": "params_shard_99.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": "ccc8a7b26916caffdebd00b65a64e443" }, { "dataPath": "params_shard_100.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": "83f653706ede21ef97914bfd90aee6d6" }, { "dataPath": "params_shard_101.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": "8a91afca11183ac6f3550b0a2b5d6136" }, { "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": "536396a057034e0ab88aa02dcce802e7" }, { "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": "c525c93e53fac6349cbe429b85d78089" }, { "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": "dfa56fd9955456c39fb15774939b6bf0" }, { "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": "130320052a03c47d6976e83fffa37b9b" }, { "dataPath": "params_shard_106.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": "51377dd01471416f79e1b20056ee60c7" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 31100928, "records": [ { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 } ], "md5sum": "04b7aafce26b66baf431799ebb2a1efe" }, { "dataPath": "params_shard_108.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": "620d8b7d92a2636e35f405ab8b4cde67" }, { "dataPath": "params_shard_109.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": "af6f24b68a4a7cce1e59dbb10db472e8" }, { "dataPath": "params_shard_110.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": "6785cd221a68690ce46142dba13eb118" }, { "dataPath": "params_shard_111.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": "516de12648b1f1235f006c7d70d1eb06" }, { "dataPath": "params_shard_112.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": "56322d90d2c6f9fc5a648ec89e08bd6a" }, { "dataPath": "params_shard_113.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": "58406e5f2637845a3352ee42179b1d22" }, { "dataPath": "params_shard_114.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": "a633548686a09bee095ff93619e79bf1" }, { "dataPath": "params_shard_115.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": "ee997e398e941c9cf00fa1a5afba27f7" }, { "dataPath": "params_shard_116.bin", "format": "raw-shard", "nbytes": 31117312, "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.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11747328 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15945728 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19304448 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19320832 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19337216 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 19353600 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "127124bce95cbfc61f5f7b126c8f31bd" }, { "dataPath": "params_shard_117.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.23.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "b449802b6e76f7739216955ffb94f655" }, { "dataPath": "params_shard_118.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": "315d293d7176b18f98b9b21a1268ac03" }, { "dataPath": "params_shard_119.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": "d1fb66dda78f78a531707293c5a6a683" }, { "dataPath": "params_shard_120.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": "45d9ba0d64f0bf765220212deeb5e000" }, { "dataPath": "params_shard_121.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": "e0e01dcb88d9c10c154c209c5cd38f51" }, { "dataPath": "params_shard_122.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": "c458bcaacf0f854ea421b69152f9215b" }, { "dataPath": "params_shard_123.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": "7be937d4ec91fa7c9113b8310bc6e210" }, { "dataPath": "params_shard_124.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": "7d484bef3397394873e272d229dd2d88" }, { "dataPath": "params_shard_125.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": "9f88c6c2ddee5c79b11cbb4e9eaaee5c" }, { "dataPath": "params_shard_126.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": "2d0e89274b5b6715b3c5f2447a765ce0" }, { "dataPath": "params_shard_127.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": "98133617e2701c1d527b1f1ca97b4f0b" }, { "dataPath": "params_shard_128.bin", "format": "raw-shard", "nbytes": 30269440, "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.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 22695936 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 26894336 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30253056 } ], "md5sum": "aca079e4364548cf07fc1c58a836be13" }, { "dataPath": "params_shard_129.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": "2eac1827b2e3a724cbd5a2cb2ba75452" }, { "dataPath": "params_shard_130.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": "362092b2f7dfa09f1bc75450756499f7" }, { "dataPath": "params_shard_131.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": "36e05a60c7c7badf54d9154c02fa8f35" }, { "dataPath": "params_shard_132.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": "8cdd193b1a45ec2b84053f7d501c7b2c" }, { "dataPath": "params_shard_133.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "d3c2e97878c584a51133318b062c73e8" }, { "dataPath": "params_shard_134.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": "c605e86dffac5656b3bcb1185b2154e5" }, { "dataPath": "params_shard_135.bin", "format": "raw-shard", "nbytes": 31117312, "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.26.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.26.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "a2daaa4f241c963111bd6ea90230afb9" }, { "dataPath": "params_shard_136.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": "5e765cfae6294c0139ebc08169a50b92" }, { "dataPath": "params_shard_137.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "28a21d4bce4ccb5affe3d5be306f6017" }, { "dataPath": "params_shard_138.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": "ac81b65d5df2501cc08efabdb5b919e9" }, { "dataPath": "params_shard_139.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": "7305b60468494a27e29eabe2a7ad5928" }, { "dataPath": "params_shard_140.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": "fc84ee708a4db484c32c7f8976e102e7" }, { "dataPath": "params_shard_141.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": "94af189cf28f27dce2ac1eae3b284b41" }, { "dataPath": "params_shard_142.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": "282023558cc9a7597bf8b7207b2d1100" }, { "dataPath": "params_shard_143.bin", "format": "raw-shard", "nbytes": 26894336, "records": [ { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.27.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.28.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 19320832 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 23519232 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26877952 } ], "md5sum": "306c1bd34543561b373b2ed024955cb4" }, { "dataPath": "params_shard_144.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": "f5b3daa8c5634b3054e08ed68fe0cedd" }, { "dataPath": "params_shard_145.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": "59413ae9370395141fb09027957f2fb6" }, { "dataPath": "params_shard_146.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": "4074053a4f1829db17ca8c40858abda7" }, { "dataPath": "params_shard_147.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": "ffd16682cca448612c649faa88936875" }, { "dataPath": "params_shard_148.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": "c3b219e2fc1772153c692839faf456c4" }, { "dataPath": "params_shard_149.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": "8ad990bc08f82ffff4d974b22f5c30cd" }, { "dataPath": "params_shard_150.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": "4a33b10d2e29e1e0057837dcaeda4b35" }, { "dataPath": "params_shard_151.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": "e73c996c8048789487b16c9d4c2b7080" }, { "dataPath": "params_shard_152.bin", "format": "raw-shard", "nbytes": 31100928, "records": [ { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.29.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 } ], "md5sum": "8f3b43845cf7496a7570c1c6f632536b" }, { "dataPath": "params_shard_153.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": "e5484aece15134e1a473a77d8e7b9db2" }, { "dataPath": "params_shard_154.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": "9f37485bb53947d3108d040d81cfe81b" }, { "dataPath": "params_shard_155.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": "e1a38738778e3d069ee86849a7b05db1" }, { "dataPath": "params_shard_156.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": "d44538be26ff065a68b459c835a67168" }, { "dataPath": "params_shard_157.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": "5332be6429fbe78801ed50dbacc67707" }, { "dataPath": "params_shard_158.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": "1e9a8def91fe1dd95de3286ba2077f23" }, { "dataPath": "params_shard_159.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": "523e28d8752767a5a0d53c816be755c0" }, { "dataPath": "params_shard_160.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": "1eaf7ae7c5116bc9444fca41740ad39e" }, { "dataPath": "params_shard_161.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.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11747328 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15945728 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19304448 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19320832 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19337216 }, { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 19353600 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "b1a965c7a06794487b2038f255b779bc" }, { "dataPath": "params_shard_162.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.31.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "fcfb339a97b20147b602c022e871e453" }, { "dataPath": "params_shard_163.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": "44d1440eb089b124c1e0090a6810f772" }, { "dataPath": "params_shard_164.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": "95e5bc78950208152bdb37cc8892dbc9" }, { "dataPath": "params_shard_165.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": "4b245c0caaee51fba25b1edf6a20d636" }, { "dataPath": "params_shard_166.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": "7bb50665d1a04bbedf7cf883ec61cdc9" }, { "dataPath": "params_shard_167.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": "749f900aad626cbb8038b5e72f8eedb2" }, { "dataPath": "params_shard_168.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": "8ed57ced15437753032ac3ca18b4ee70" }, { "dataPath": "params_shard_169.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": "781d39efc731c3cdfbd1dd07d031626c" }, { "dataPath": "params_shard_170.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": "cec3923faeaddc804fd7643180a7091e" }, { "dataPath": "params_shard_171.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": "b08531e1c9a57c2518c546a4bcef7d0a" }, { "dataPath": "params_shard_172.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": "e0b14e33858ccaeaa582abdf7820edc0" }, { "dataPath": "params_shard_173.bin", "format": "raw-shard", "nbytes": 30269440, "records": [ { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.32.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.32.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 3375104 }, { "name": "model.layers.32.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15122432 }, { "name": "model.layers.32.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 15138816 }, { "name": "model.layers.32.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 19337216 }, { "name": "model.layers.33.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 22695936 }, { "name": "model.layers.33.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 26894336 }, { "name": "model.layers.33.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30253056 } ], "md5sum": "726e493ea35a18efbd9f485d45e03642" }, { "dataPath": "params_shard_174.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": "7c5839606b3b2b45e29233801e6c121a" }, { "dataPath": "params_shard_175.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": "21e6cc12e8673b97384d2b21da2b4403" }, { "dataPath": "params_shard_176.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": "5eb84b1ac8b692585913de23553f86e7" }, { "dataPath": "params_shard_177.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": "664bf93adc63d720052aebb12fa963fc" }, { "dataPath": "params_shard_178.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": "576d722a5ef108b1157dd847a5ef73c3" }, { "dataPath": "params_shard_179.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": "978a515e99d39482fe63def78f872018" }, { "dataPath": "params_shard_180.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": "1bcce58928bfcf277f9667939b30c407" }, { "dataPath": "params_shard_181.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": "b56c0f1ecf9202448453b1bb99072415" }, { "dataPath": "params_shard_182.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": "e389715baa6cdd0b2372114eaca2bf0b" }, { "dataPath": "params_shard_183.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": "2278241bcf50812da590b3d689a62dfb" }, { "dataPath": "params_shard_184.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": "bd99b2a15a7de786ddfdd2c7bfdef47f" }, { "dataPath": "params_shard_185.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": "0ef543d62cfdd52a2fc661fce0abecf0" }, { "dataPath": "params_shard_186.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": "6f71acd43862a65f39b895a50120eaac" }, { "dataPath": "params_shard_187.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": "4198944079f4c35088a53c489ec19a6c" }, { "dataPath": "params_shard_188.bin", "format": "raw-shard", "nbytes": 26894336, "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.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 23519232 }, { "name": "model.layers.36.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26877952 } ], "md5sum": "d0406892a753b21aa0da418309bc8e21" }, { "dataPath": "params_shard_189.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": "1995b0f479f255e328b508ec12e052d9" }, { "dataPath": "params_shard_190.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": "52670801bfedccee6e9a53e030c10fab" }, { "dataPath": "params_shard_191.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": "6ed21e8b99e8227b4d86f246405f7119" }, { "dataPath": "params_shard_192.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": "3abe3466d8796aabbabf031be8d72b9b" }, { "dataPath": "params_shard_193.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": "688d0d28996d92c162f8f745fd5ee556" }, { "dataPath": "params_shard_194.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": "447543b2d827111a5c4edb78710f851e" }, { "dataPath": "params_shard_195.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": "302e52c5a0ef7bbc62537c3e9b64e5c3" }, { "dataPath": "params_shard_196.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": "99411ad511e5e6bc6f8e7114384f3b88" }, { "dataPath": "params_shard_197.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.37.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.37.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.37.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.37.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.37.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 } ], "md5sum": "e730780dfb7fd4e7342d39f8291b0aed" }, { "dataPath": "params_shard_198.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": "f00135ead4c92437db47ee8d13450802" }, { "dataPath": "params_shard_199.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": "1c89c04f03e4a8ec8947f8f51211ad32" }, { "dataPath": "params_shard_200.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": "a431e26dcd6be6eea436d61fcd0d3559" }, { "dataPath": "params_shard_201.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": "392cc11d87149b6c35c653fd029210a1" }, { "dataPath": "params_shard_202.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": "d4ce07649cdcc397cb5732cb9630fadd" }, { "dataPath": "params_shard_203.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": "0f8090f3b1dbcf65983fc736dad4a3b0" }, { "dataPath": "params_shard_204.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": "2a16378e3a5ac8e9edd1448351ed05d5" }, { "dataPath": "params_shard_205.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": "30e09e029e18b6eb3c260c9b0bc493a9" }, { "dataPath": "params_shard_206.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.38.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.38.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11747328 }, { "name": "model.layers.38.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15945728 }, { "name": "model.layers.38.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19304448 }, { "name": "model.layers.38.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19320832 }, { "name": "model.layers.39.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19337216 }, { "name": "model.layers.39.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 19353600 }, { "name": "model.layers.39.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "465b17fa9f83d1ff38f89223b9231286" }, { "dataPath": "params_shard_207.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.39.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.39.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "ab77f3e31f9a494d85d94b1f58042b0a" }, { "dataPath": "params_shard_208.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": "0209cc253046f90d252975c3242e786a" }, { "dataPath": "params_shard_209.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": "01ea18384cbae63efdb68124b6a93aec" }, { "dataPath": "params_shard_210.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": "e762869e74eb04027f633f36deae23d9" }, { "dataPath": "params_shard_211.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": "4a970b947c632c38abd74719a69af2e7" }, { "dataPath": "params_shard_212.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.40.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "c7532e2e19063098ada6204ca698f882" }, { "dataPath": "params_shard_213.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": "beddcd133cc3d70ccee3502032dab755" }, { "dataPath": "params_shard_214.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.41.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "04c569cd69cf802b55909ec6cc370832" }, { "dataPath": "params_shard_215.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": "ebb499464dcec54ef49a4b44bb4289e7" }, { "dataPath": "params_shard_216.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": "d7d12a0b0b45aac29db03e4f21567e9c" }, { "dataPath": "params_shard_217.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": "daaebd0588d9d2d9a6562262f4921232" }, { "dataPath": "params_shard_218.bin", "format": "raw-shard", "nbytes": 30269440, "records": [ { "name": "model.layers.39.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.40.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.40.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 3375104 }, { "name": "model.layers.40.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15122432 }, { "name": "model.layers.40.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 15138816 }, { "name": "model.layers.40.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 19337216 }, { "name": "model.layers.41.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 22695936 }, { "name": "model.layers.41.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 26894336 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30253056 } ], "md5sum": "e15e0293db6a5a1057d2745a7dcf5923" }, { "dataPath": "params_shard_219.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": "4dc96f8cec7c65784ce55bf5a9e85ad7" }, { "dataPath": "params_shard_220.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": "94e9112d33d9b2be39e93e4e47e30114" }, { "dataPath": "params_shard_221.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": "71ee31ba2f4db70ab5bca286cddbee9e" }, { "dataPath": "params_shard_222.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": "6b351d4e7f9695d9cca5f83dfa660bae" }, { "dataPath": "params_shard_223.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": "0e542b1dba2308ab7cef9119ec11ebc7" }, { "dataPath": "params_shard_224.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": "8d00a2d0d2e2a70c17b96f242fda23f9" }, { "dataPath": "params_shard_225.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": "4f9b4726b512e55cf88d49d176d080ca" }, { "dataPath": "params_shard_226.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": "badee10a4027be8032d5ae272822f101" }, { "dataPath": "params_shard_227.bin", "format": "raw-shard", "nbytes": 31100928, "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.5.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 } ], "md5sum": "5636dc56450085a5787821d967622bea" }, { "dataPath": "params_shard_228.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": "200a0028e6b6ac0cacbe14449b125402" }, { "dataPath": "params_shard_229.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": "f017f9fa621d9c1ac8632ddb2462b31f" }, { "dataPath": "params_shard_230.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": "81e28a7e153403573c8c94c1ad18880b" }, { "dataPath": "params_shard_231.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": "c83dc08e264249128bd41cb69a0c7a44" }, { "dataPath": "params_shard_232.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": "07de080a678ba78db82d1c2a0991349a" }, { "dataPath": "params_shard_233.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": "3e9efea95e528d1bc0c107b7cc0c1e31" }, { "dataPath": "params_shard_234.bin", "format": "raw-shard", "nbytes": 31100928, "records": [ { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11747328 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15945728 }, { "name": "model.layers.41.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19304448 }, { "name": "model.layers.41.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 19320832 }, { "name": "model.layers.41.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31068160 }, { "name": "model.layers.42.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31084544 } ], "md5sum": "03383cd3a12293acc492c92c61ae6314" }, { "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": "499b4aefd405bcf934af1eed177e2456" }, { "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": "7cc6d3064d111faa42be390c2ca00773" }, { "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": "1bdb6bb569afd589e1ff220b335bf3f3" }, { "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": "47883a7f45881ad604f7caa3b865236c" }, { "dataPath": "params_shard_239.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": "657ce5a85c4654e0f7bfc91a0846f203" }, { "dataPath": "params_shard_240.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": "a531403516dcccede15cce6854a9b0f7" }, { "dataPath": "params_shard_241.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": "9c134901cfa43209ead3463c28cf263b" }, { "dataPath": "params_shard_242.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": "afeb595aa1678220a5f36047b05f44d4" }, { "dataPath": "params_shard_243.bin", "format": "raw-shard", "nbytes": 31100928, "records": [ { "name": "model.layers.42.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.42.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.42.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.42.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.43.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19320832 }, { "name": "model.layers.43.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 19337216 }, { "name": "model.layers.43.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31084544 } ], "md5sum": "caf900a3c34bdfb077cc04a62ad00f9b" }, { "dataPath": "params_shard_244.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.43.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.43.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "175759bb098416063dd7767f23002b54" }, { "dataPath": "params_shard_245.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": "388c1e212cbcc093e1e40557ef3f1110" }, { "dataPath": "params_shard_246.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": "60495d6d2e896653192c6a5e79707546" }, { "dataPath": "params_shard_247.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": "91dd051257147280c71f973a005670de" }, { "dataPath": "params_shard_248.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": "747c62c5a75dec1c5c009c7440fe3fbc" }, { "dataPath": "params_shard_249.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": "3abeb8750d6f4215f3644fcbad1e6a94" }, { "dataPath": "params_shard_250.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": "21c5ba81dbe66a419dc3a8c47441f251" }, { "dataPath": "params_shard_251.bin", "format": "raw-shard", "nbytes": 22712320, "records": [ { "name": "model.layers.43.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.44.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 3358720 }, { "name": "model.layers.44.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 7557120 }, { "name": "model.layers.44.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 10915840 }, { "name": "model.layers.44.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 10932224 }, { "name": "model.layers.44.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 22679552 }, { "name": "model.layers.45.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 22695936 } ], "md5sum": "f077024bd0b90839ef4b4caaed409117" }, { "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": "e9df750d57e3967d611481f9c7ea0f67" }, { "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": "e84ff05b2dcebc9d3ae129bc1df6fb9c" }, { "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": "56c3a85a1d6e1fb1371030bfc35a802f" }, { "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": "2fd55d360aafe01994e3cb6d5a1a5ac3" }, { "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": "d75f74ab75f29d66bd95fa65b5624f5a" }, { "dataPath": "params_shard_257.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": "8d7cdbf324de1301678ffea1c962d890" }, { "dataPath": "params_shard_258.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": "ae46111c6be3a0ed870c441e0ca85926" }, { "dataPath": "params_shard_259.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": "bf17ff363c43d575d6832433bb5d7ff3" }, { "dataPath": "params_shard_260.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.45.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.45.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.45.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.45.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.46.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 19320832 } ], "md5sum": "ea1ba4718548bd8aea096d66dc2516b9" }, { "dataPath": "params_shard_261.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.46.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.46.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "66bcafe9b8cec7cd2a6eb5ccebe49fe1" }, { "dataPath": "params_shard_262.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": "c769a0cbb116da48ba9891d276d36c5d" }, { "dataPath": "params_shard_263.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": "366b7ab909e3b8d2ec56d60a02b2d445" }, { "dataPath": "params_shard_264.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": "9e4ef4a81fc6ed0e714c1a443685eda1" }, { "dataPath": "params_shard_265.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": "f579d44f751de22070dc0147e6e70702" }, { "dataPath": "params_shard_266.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": "5055f45b90d515b4c4da16f3fe45220e" }, { "dataPath": "params_shard_267.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": "086eb29c8a020c57cc4d995e5baaeb7c" }, { "dataPath": "params_shard_268.bin", "format": "raw-shard", "nbytes": 22745088, "records": [ { "name": "model.layers.46.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.46.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.46.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3375104 }, { "name": "model.layers.47.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3391488 }, { "name": "model.layers.47.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 3407872 }, { "name": "model.layers.47.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15155200 }, { "name": "model.layers.47.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 15171584 }, { "name": "model.layers.47.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 19369984 }, { "name": "model.layers.48.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 22728704 } ], "md5sum": "53fe58a590b30f9da46a497621b0da11" }, { "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": "9fa521582f9867d278c82142857d9cd2" }, { "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": "20f782ed036ff7987a75117ffe5424a6" }, { "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": "ae13a64f8f7112ed6d602ac371276abe" }, { "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": "f46651c99ca5fbe5d6f922fc1af4a1a7" }, { "dataPath": "params_shard_273.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": "80c3642803ed200e1b3afcec401b3a6b" }, { "dataPath": "params_shard_274.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": "5af9212563a460070c9d146fb925cb6a" }, { "dataPath": "params_shard_275.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": "6b1cb4049e98998e88d4e3256e9d52a9" }, { "dataPath": "params_shard_276.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": "d171b2d5d7385066dda4837d5e62a557" }, { "dataPath": "params_shard_277.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": "2b587ca49747d3bfc62531af88520f65" }, { "dataPath": "params_shard_278.bin", "format": "raw-shard", "nbytes": 26894336, "records": [ { "name": "model.layers.48.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.48.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.48.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.48.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.49.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 19320832 }, { "name": "model.layers.49.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 23519232 }, { "name": "model.layers.49.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26877952 } ], "md5sum": "5c257c472c90a6c3efc5f2fcf112ac3b" }, { "dataPath": "params_shard_279.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": "b256642d36cf4d718d95a1a1f25fcead" }, { "dataPath": "params_shard_280.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": "148c23d9ab9d0486186e160db27b656f" }, { "dataPath": "params_shard_281.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": "05ac1f14ad0734cce561c8d90aab9d65" }, { "dataPath": "params_shard_282.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": "e8bea2969657ed501bfde55e059ee861" }, { "dataPath": "params_shard_283.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": "b1644410449ce9c46bb0dd4f35094cef" }, { "dataPath": "params_shard_284.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": "60c11c53033661ee451f976ae9ffa029" }, { "dataPath": "params_shard_285.bin", "format": "raw-shard", "nbytes": 31117312, "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.50.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.50.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.50.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.50.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.50.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 }, { "name": "model.layers.51.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "ba61002d646cdf758a87b0f82f5d8039" }, { "dataPath": "params_shard_286.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": "81260aa921b351ce9e5f5915f322abf4" }, { "dataPath": "params_shard_287.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": "6063de71cf170b06217be93a2cdb5465" }, { "dataPath": "params_shard_288.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": "06726630c222eb8a45391da0a48a3ef9" }, { "dataPath": "params_shard_289.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": "09cbff2383a7df9cec0acdbc8b04baf1" }, { "dataPath": "params_shard_290.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": "f0300490f1bfc76207eb29ab8e7bb52c" }, { "dataPath": "params_shard_291.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": "120f046a9c9a91cdaf5c59ca720b8a21" }, { "dataPath": "params_shard_292.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": "75a9ea9d3baae7b2327acde9fc6c41d5" }, { "dataPath": "params_shard_293.bin", "format": "raw-shard", "nbytes": 26894336, "records": [ { "name": "model.layers.51.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.51.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.51.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.51.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.52.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 19320832 }, { "name": "model.layers.52.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 23519232 }, { "name": "model.layers.52.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26877952 } ], "md5sum": "90a5c47f6e9961e508abd2104693e4e4" }, { "dataPath": "params_shard_294.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": "2b0a24ff3b15ba74305accb1132abb25" }, { "dataPath": "params_shard_295.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": "e8acb332abac6983c96035061b7e943f" }, { "dataPath": "params_shard_296.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": "f36aafb8957af32328e7d0d126537760" }, { "dataPath": "params_shard_297.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": "ac204f4895b8da12e92796c45e9b58f1" }, { "dataPath": "params_shard_298.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": "7a0c5a78e10f4b1aec89eb453fa594f2" }, { "dataPath": "params_shard_299.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": "35eaca277cfb9bb38f4010a39840e66e" }, { "dataPath": "params_shard_300.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": "cc5ac78882f870def1d228149679d9a8" }, { "dataPath": "params_shard_301.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": "ea1373973ebe7603ec652b3b78ccabe7" }, { "dataPath": "params_shard_302.bin", "format": "raw-shard", "nbytes": 31100928, "records": [ { "name": "model.layers.52.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.52.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.53.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.53.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.53.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.53.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.53.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 } ], "md5sum": "2ab531f53cd53df63bd3a4e6471e5a99" }, { "dataPath": "params_shard_303.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": "adab5a5ec41e42a2c9bf7326954623b6" }, { "dataPath": "params_shard_304.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": "e27697e76fa83475a92f2656b6c0a63d" }, { "dataPath": "params_shard_305.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": "0d8d6a45af45e05c5e4b5b956f4cd8bd" }, { "dataPath": "params_shard_306.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.54.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "99ebc6696f429fe43b9e7cff778f7efb" }, { "dataPath": "params_shard_307.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": "19e25202ed8fbbb2c3f92a01fa902aac" }, { "dataPath": "params_shard_308.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": "91d3ef1bd1a5cb263b2c5b4c1aa4cc34" }, { "dataPath": "params_shard_309.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.55.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "34f16f9eb0050af03f3902f3f366fe87" }, { "dataPath": "params_shard_310.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": "d6c1923f46441dd7faff3e86d8a3d548" }, { "dataPath": "params_shard_311.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.54.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.54.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11747328 }, { "name": "model.layers.54.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15945728 }, { "name": "model.layers.54.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19304448 }, { "name": "model.layers.54.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19320832 }, { "name": "model.layers.55.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19337216 }, { "name": "model.layers.55.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 19353600 }, { "name": "model.layers.55.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "9ce62ec0210d69495ec4eac8c5826e1e" }, { "dataPath": "params_shard_312.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.55.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.55.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "05db2a596af3105a31e95b147443e52b" }, { "dataPath": "params_shard_313.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": "29423230e7096d0ea5fdcda5c9aecd0a" }, { "dataPath": "params_shard_314.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": "f92ac9f474a8cfe964c1f04be986eee1" }, { "dataPath": "params_shard_315.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": "1b790d6b24278b26d91926a9698b24a3" }, { "dataPath": "params_shard_316.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": "cf959e787b60c875bd73ce4f6b59bfc3" }, { "dataPath": "params_shard_317.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": "d22d846bf1b306cb861b5d80a61e9dee" }, { "dataPath": "params_shard_318.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": "d1f3ccbdcb16049a73b9778981b4da9e" }, { "dataPath": "params_shard_319.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": "e7478c72209ce4fe73a786af5061ce03" }, { "dataPath": "params_shard_320.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": "71351414b52a0c7ed2b91be926a71c4a" }, { "dataPath": "params_shard_321.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": "6696786a14896fe20a0e5fc0afacf1f7" }, { "dataPath": "params_shard_322.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": "51aa78be9b25fd900744f00533c6bbb6" }, { "dataPath": "params_shard_323.bin", "format": "raw-shard", "nbytes": 30269440, "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.56.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.56.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 3375104 }, { "name": "model.layers.56.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15122432 }, { "name": "model.layers.56.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 15138816 }, { "name": "model.layers.56.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 19337216 }, { "name": "model.layers.57.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 22695936 }, { "name": "model.layers.57.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 26894336 }, { "name": "model.layers.57.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30253056 } ], "md5sum": "4d782f0a4f6f6e73f058adb0f3aad65b" }, { "dataPath": "params_shard_324.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": "46986c73339d40a3d19fa44353fd026f" }, { "dataPath": "params_shard_325.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": "a19d8c2b8d26022dfe959a3a28b8d811" }, { "dataPath": "params_shard_326.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": "0c5d2c0e028bf51cb438b8388e1d4a85" }, { "dataPath": "params_shard_327.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": "1ea8a5637a076017e872365d590bd82f" }, { "dataPath": "params_shard_328.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": "9d4a8670fc189e3b77c920ccb44d5b91" }, { "dataPath": "params_shard_329.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": "153c75f7ccadd113942049fd0177e006" }, { "dataPath": "params_shard_330.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.57.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.57.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.58.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.58.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.58.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.58.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.58.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 }, { "name": "model.layers.59.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "0bea2ec93e7b5efc2730d898e7214645" }, { "dataPath": "params_shard_331.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": "fa7851811ce96e36e510658f0018f78d" }, { "dataPath": "params_shard_332.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": "de595d37097fdc149db31ecf138cc3f5" }, { "dataPath": "params_shard_333.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": "07c618d932b914a38855d363fb7fef62" }, { "dataPath": "params_shard_334.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": "f392c33e9ff24093d167856d8ac1635a" }, { "dataPath": "params_shard_335.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": "077b0eecb1a2a4663c05772c647429f0" }, { "dataPath": "params_shard_336.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": "448d165aeebe31736ffee1307306f0d0" }, { "dataPath": "params_shard_337.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": "d9da996c11d107bdf6635ed036a6065e" }, { "dataPath": "params_shard_338.bin", "format": "raw-shard", "nbytes": 26927104, "records": [ { "name": "model.layers.59.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.59.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.59.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.59.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.60.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 19320832 }, { "name": "model.layers.60.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 23519232 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26877952 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26894336 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26910720 } ], "md5sum": "ec39345d3b9b069fa6c353a7344240c9" }, { "dataPath": "params_shard_339.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": "ce59321517bc3e90084aed8776b142fc" }, { "dataPath": "params_shard_340.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": "a2be9b0aeba4d6b99324521e7f98743b" }, { "dataPath": "params_shard_341.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": "d92152051df9077058e36c1ec335cde7" }, { "dataPath": "params_shard_342.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": "61d953abafa6938ab886dffdb8f8cba7" }, { "dataPath": "params_shard_343.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": "d8ab2593e9408a65a1967aa8747c70bd" }, { "dataPath": "params_shard_344.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": "88700c6c3c2fff85c2dd449baf0e772d" }, { "dataPath": "params_shard_345.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": "bf34da0a91e16a89604a3aa702608232" }, { "dataPath": "params_shard_346.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": "968bfcb021a9e3d7f374a4ee62a5f922" }, { "dataPath": "params_shard_347.bin", "format": "raw-shard", "nbytes": 31100928, "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.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19320832 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 19337216 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31084544 } ], "md5sum": "aec739376b3e78407f14fd1365bebdac" }, { "dataPath": "params_shard_348.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "a22309c77e1f364eef93a41ed058f92d" }, { "dataPath": "params_shard_349.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": "04f04004b73e616037234c8f8c1ca59e" }, { "dataPath": "params_shard_350.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": "4d586e3e439550624017fc5b151f9423" }, { "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": "807acf1a814479a9256bcbb79c558052" }, { "dataPath": "params_shard_352.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": "8b9975f4d5a23282cc35f82387971548" }, { "dataPath": "params_shard_353.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": "e9242f46d4212b7908b6dfd01cea8143" }, { "dataPath": "params_shard_354.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": "911a0a674fa066baaa6d1bd958efc6b0" }, { "dataPath": "params_shard_355.bin", "format": "raw-shard", "nbytes": 22712320, "records": [ { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 3358720 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 7557120 }, { "name": "model.layers.60.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 10915840 }, { "name": "model.layers.60.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 10932224 }, { "name": "model.layers.60.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 22679552 }, { "name": "model.layers.61.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 22695936 } ], "md5sum": "3ecd705db7a1fc488bf68a386d5e6b44" }, { "dataPath": "params_shard_356.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": "5f871929e245efc51400f3207bb91175" }, { "dataPath": "params_shard_357.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": "dd66f354f1bc5f4cfe267a0e354368b8" }, { "dataPath": "params_shard_358.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": "752ad52af5627c946ee2df1420eb12de" }, { "dataPath": "params_shard_359.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": "635f969dcaea4eca91c2406521c16ad2" }, { "dataPath": "params_shard_360.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": "4a76f9e4e2ff743e2f86c0e40ab2d992" }, { "dataPath": "params_shard_361.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": "0af1fdada31a7445c192238fca7cdb8b" }, { "dataPath": "params_shard_362.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": "1b7db26996a4872ab568f77a52ddddae" }, { "dataPath": "params_shard_363.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": "660a1843db14afe808ff24842cbff1a0" }, { "dataPath": "params_shard_364.bin", "format": "raw-shard", "nbytes": 31068160, "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.61.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.61.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.62.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 19320832 } ], "md5sum": "3a2a50d3d81979197f168e2c7b0a52cb" }, { "dataPath": "params_shard_365.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.62.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.62.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "acc30fa02207ca2edd077b86d55aa3b5" }, { "dataPath": "params_shard_366.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": "69cd036b317a8011971985773cb564b3" }, { "dataPath": "params_shard_367.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": "a0acc94e64f9cbe59f66d4dd476cb854" }, { "dataPath": "params_shard_368.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": "1c15e2f3d5702508800e0a83caf70d51" }, { "dataPath": "params_shard_369.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": "58a5e30fd819d27d939d385680d33cad" }, { "dataPath": "params_shard_370.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": "7c2fe13a6d863d08f384d2d7684aa942" }, { "dataPath": "params_shard_371.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": "ac28d04c3f89df0afba4614629563d2b" }, { "dataPath": "params_shard_372.bin", "format": "raw-shard", "nbytes": 22745088, "records": [ { "name": "model.layers.62.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.62.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.62.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3375104 }, { "name": "model.layers.63.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3391488 }, { "name": "model.layers.63.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 3407872 }, { "name": "model.layers.63.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15155200 }, { "name": "model.layers.63.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 15171584 }, { "name": "model.layers.63.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 19369984 }, { "name": "model.layers.64.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 22728704 } ], "md5sum": "f2887ef767ef87a3fd2699fc1916cd8f" }, { "dataPath": "params_shard_373.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": "035306d3463c9e760d7fcf25a42889b0" }, { "dataPath": "params_shard_374.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": "c32331faa4cf6bbc44fbf6ec41c89e17" }, { "dataPath": "params_shard_375.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": "14cb770c329bab26cca50305f8e28d65" }, { "dataPath": "params_shard_376.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": "077d671ce7a988a2a64d9e6c9c5760fa" }, { "dataPath": "params_shard_377.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": "5bf4e2b4f4a479571320344e202b2dde" }, { "dataPath": "params_shard_378.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": "abe3071284c505e082dc2680c4c07212" }, { "dataPath": "params_shard_379.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": "65d3569de76ff928f39ff38705dc57ac" }, { "dataPath": "params_shard_380.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": "8beb5dc2577cb102687717b248ca1a69" }, { "dataPath": "params_shard_381.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": "682afccc232f65116298ec7e20cf56e5" }, { "dataPath": "params_shard_382.bin", "format": "raw-shard", "nbytes": 26894336, "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.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.64.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.65.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 19320832 }, { "name": "model.layers.65.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 23519232 }, { "name": "model.layers.65.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26877952 } ], "md5sum": "ef888c44853fdc573436f7888e20f72a" }, { "dataPath": "params_shard_383.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": "85d4f2b8200f1ba9b8139155f5c2ea9d" }, { "dataPath": "params_shard_384.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": "621860dda4d94f22da97ad562a07d64a" }, { "dataPath": "params_shard_385.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": "792b037204b9a83668e8ef1079d14e1e" }, { "dataPath": "params_shard_386.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": "f636b261bfb3e28b31cde450137b3ecb" }, { "dataPath": "params_shard_387.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": "4a0ccedc09d5a69898d686b7cde08de5" }, { "dataPath": "params_shard_388.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": "f4bdf89a1dc87b04e3f7035cf45fef52" }, { "dataPath": "params_shard_389.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.65.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.65.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.66.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.66.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.66.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.66.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.66.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 }, { "name": "model.layers.67.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "5502dc7239a148c160641fa66098a101" }, { "dataPath": "params_shard_390.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": "5331300daa219434f37eabad4b5f70c7" }, { "dataPath": "params_shard_391.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": "bc71df7f886175f31945a53b30ad9a0a" }, { "dataPath": "params_shard_392.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": "8fb527578a08bc5d6889252934f1fa86" }, { "dataPath": "params_shard_393.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": "2078c0c7e761d7bfe14a020c14287203" }, { "dataPath": "params_shard_394.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": "9254d3c93f5a725e7d7f271c70979c07" }, { "dataPath": "params_shard_395.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.68.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "8b3158173dda201d9a9a995ad1d57fc5" }, { "dataPath": "params_shard_396.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": "ae0542f809cb7ea7d9c0095df594f6bf" }, { "dataPath": "params_shard_397.bin", "format": "raw-shard", "nbytes": 26894336, "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.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 19320832 }, { "name": "model.layers.68.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 23519232 }, { "name": "model.layers.68.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26877952 } ], "md5sum": "27964a477cb1d39431d86c826c58b9a7" }, { "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": "57075372ab8388d4b2049957a04dbee0" }, { "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": "9128e459ec244dacb702bf303915e905" }, { "dataPath": "params_shard_400.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": "ad529c1b445dcd86c2dd7ed74b3fec9b" }, { "dataPath": "params_shard_401.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": "829621a79985438e68c5ac87ad5707e9" }, { "dataPath": "params_shard_402.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.69.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "06455636a29b22267947f0f2fe23c209" }, { "dataPath": "params_shard_403.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": "d33c79698ddb54811ebb60c6c8cfbc4f" }, { "dataPath": "params_shard_404.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": "bf368e1ab957eb67c596824bd3c40540" }, { "dataPath": "params_shard_405.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": "53bfaeef0ba03908513c791c9aa3a0e5" }, { "dataPath": "params_shard_406.bin", "format": "raw-shard", "nbytes": 31100928, "records": [ { "name": "model.layers.68.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.68.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.69.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.69.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.69.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.69.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.69.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 } ], "md5sum": "e345e55128e0f4073e91690c6a8ce65d" }, { "dataPath": "params_shard_407.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": "f4fb46e9bdc5af2c20029057e9933710" }, { "dataPath": "params_shard_408.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": "40c24089c7f6bbabdc79ce4b13f59380" }, { "dataPath": "params_shard_409.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": "203da03f724fa7503cc3f410bd0ddbda" }, { "dataPath": "params_shard_410.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": "a5e44d418ce4fa3b4f298fd5f2dd185f" }, { "dataPath": "params_shard_411.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": "3a6b00056bae6c27270e7bcfffe07edd" }, { "dataPath": "params_shard_412.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": "b31086a340df987406a5cb12208f5f2c" }, { "dataPath": "params_shard_413.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": "0aba4520993729b0a1f47b94f58d1f33" }, { "dataPath": "params_shard_414.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": "03a7975758444095f8749d36eb47a01e" }, { "dataPath": "params_shard_415.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.70.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.70.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11747328 }, { "name": "model.layers.70.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15945728 }, { "name": "model.layers.70.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19304448 }, { "name": "model.layers.70.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19320832 }, { "name": "model.layers.71.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19337216 }, { "name": "model.layers.71.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 19353600 }, { "name": "model.layers.71.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "ce4124a10e298884d4daedb972296d33" }, { "dataPath": "params_shard_416.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.71.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.71.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "111548560736d13d0e3720cab024d18e" }, { "dataPath": "params_shard_417.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": "f6beb38da37785a3044aa3a8846ea514" }, { "dataPath": "params_shard_418.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": "6a55e50b945fcd4e827ad8036532bf31" }, { "dataPath": "params_shard_419.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": "0396275908fb65d179b9e2fb216b21aa" }, { "dataPath": "params_shard_420.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": "55215b652302831155d38cd87e9f6057" }, { "dataPath": "params_shard_421.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": "67d931863e7f7683d60eb5e3685abd00" }, { "dataPath": "params_shard_422.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": "b83da4e6f9beef1ab6667d6e25b9922c" }, { "dataPath": "params_shard_423.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": "cf64e0a5136d1200c231fc4a3b82ff85" }, { "dataPath": "params_shard_424.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": "2754c95125e7ad4fb610f920bf5a3d36" }, { "dataPath": "params_shard_425.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": "e264eedc15fd7f2d3e1f88c9c4ea89f8" }, { "dataPath": "params_shard_426.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": "2c5d27ce7819ff132e701bbb6cd3e3ca" }, { "dataPath": "params_shard_427.bin", "format": "raw-shard", "nbytes": 30269440, "records": [ { "name": "model.layers.71.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.72.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.72.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 3375104 }, { "name": "model.layers.72.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15122432 }, { "name": "model.layers.72.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 15138816 }, { "name": "model.layers.72.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 19337216 }, { "name": "model.layers.73.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 22695936 }, { "name": "model.layers.73.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 26894336 }, { "name": "model.layers.73.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30253056 } ], "md5sum": "0dfad8daf671eba4db6998879a767568" }, { "dataPath": "params_shard_428.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": "b676feff6bbaac1d9a5aa6455d1439bc" }, { "dataPath": "params_shard_429.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": "d490b17347a7ea30716a5a7ef84e682b" }, { "dataPath": "params_shard_430.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": "e85a2c8d52e2cedfc5582f255ac3d352" }, { "dataPath": "params_shard_431.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": "21ec1e529d2fc44ca67392f3afd8fe55" }, { "dataPath": "params_shard_432.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": "0b3c1bc9b62f1c1d240f337aeb83d932" }, { "dataPath": "params_shard_433.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": "e17642ef384d6f556e82dd9e1e968730" }, { "dataPath": "params_shard_434.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.73.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.73.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.74.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.74.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.74.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.74.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.74.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 }, { "name": "model.layers.75.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "dfbb6b7cdae8bbbcb433a7e8185a90ea" }, { "dataPath": "params_shard_435.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": "8960f2beafeb521973086f4180bf23f6" }, { "dataPath": "params_shard_436.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": "ba989e2a73ccd5e680f3afb910901ae0" }, { "dataPath": "params_shard_437.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": "4b0142f42590e100fa3f5f5c986a166c" }, { "dataPath": "params_shard_438.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": "8f941ce4e89b8d52b3436034157f888f" }, { "dataPath": "params_shard_439.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": "7ba68a700ccfcf3adee8de37a6274abd" }, { "dataPath": "params_shard_440.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": "b950c712977ec9d6fa5cfc33f76d7d25" }, { "dataPath": "params_shard_441.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": "260e5610e2ba9ff5f355fe53b4642d05" }, { "dataPath": "params_shard_442.bin", "format": "raw-shard", "nbytes": 26894336, "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.75.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.75.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.76.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 19320832 }, { "name": "model.layers.76.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 23519232 }, { "name": "model.layers.76.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26877952 } ], "md5sum": "828e2253ac0149c33c261c1f68dac4af" }, { "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": "a7eab7d92aff3ceb7c1405e54bf82d9d" }, { "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": "ed508680a44fea4790b7648835c11cb6" }, { "dataPath": "params_shard_445.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": "4fbe3527143b13d4066b6eb6348c0e49" }, { "dataPath": "params_shard_446.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": "cd48502d235750fd3ce5b21532dd3bfc" }, { "dataPath": "params_shard_447.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": "05d48fadce681cb6e8c01854a355c0a9" }, { "dataPath": "params_shard_448.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": "eeb9acee62ddcee43efefaa9fc254851" }, { "dataPath": "params_shard_449.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": "bffb5e4693d3e466a75e1fed664d1187" }, { "dataPath": "params_shard_450.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": "26d2bb33896cd1bfc1d090fd5ebfcc7a" }, { "dataPath": "params_shard_451.bin", "format": "raw-shard", "nbytes": 31100928, "records": [ { "name": "model.layers.76.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.76.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.77.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.77.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.77.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.77.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.77.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 } ], "md5sum": "e76cf9b4973cd4545011ca8633a59f0e" }, { "dataPath": "params_shard_452.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": "16e2a5df399cf92ae34fbf1a57a9c057" }, { "dataPath": "params_shard_453.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": "47f7be82e32a822d0ce8da7223c955b4" }, { "dataPath": "params_shard_454.bin", "format": "raw-shard", "nbytes": 19304448, "records": [ { "name": "model.layers.78.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.78.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11747328 }, { "name": "model.layers.78.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15945728 } ], "md5sum": "70c2e745b3cc80fc2c504de28395cdd1" } ] }