{ "metadata": { "ParamSize": 311, "ParamBytes": 703039744.0, "BitsPerParam": 3.1649068318507583 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 94808064, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 151936, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 94808064, "byteOffset": 0 } ], "md5sum": "cc27a0cd2dc5425cfb7dcb5f425a4417" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 33153280, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 151936, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11851008, "byteOffset": 0 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 11851008 }, { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 1536, 896 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5505024, "byteOffset": 11854080 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 1536, 224 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 688128, "byteOffset": 17359104 }, { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 17920, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 18047232 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 17920, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1397760, "byteOffset": 29229312 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 30627072 }, { "name": "model.layers.0.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 30630144 }, { "name": "model.layers.0.self_attn.c_attn.q_weight", "shape": [ 2048, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 30634240 }, { "name": "model.layers.0.self_attn.c_attn.q_scale", "shape": [ 2048, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 159744, "byteOffset": 31912192 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 1536, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 32071936 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 1536, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 119808, "byteOffset": 33030400 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 33150208 } ], "md5sum": "f6e96ec4fc7bc1e91df6873758efb15e" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 27492352, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 1536, 896 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5505024, "byteOffset": 0 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 1536, 224 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 688128, "byteOffset": 5505024 }, { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 17920, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 6193152 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 17920, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1397760, "byteOffset": 17375232 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 18772992 }, { "name": "model.layers.1.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18776064 }, { "name": "model.layers.1.self_attn.c_attn.q_weight", "shape": [ 2048, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 18780160 }, { "name": "model.layers.1.self_attn.c_attn.q_scale", "shape": [ 2048, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 159744, "byteOffset": 20058112 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 1536, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 20217856 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 1536, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 119808, "byteOffset": 21176320 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 21296128 }, { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 1536, 896 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5505024, "byteOffset": 21299200 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 1536, 224 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 688128, "byteOffset": 26804224 } ], "md5sum": "8edb400052a2d3779e034fb14d5ff96d" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 32481280, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 17920, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 0 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 17920, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1397760, "byteOffset": 11182080 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 12579840 }, { "name": "model.layers.10.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12582912 }, { "name": "model.layers.10.self_attn.c_attn.q_weight", "shape": [ 2048, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 12587008 }, { "name": "model.layers.10.self_attn.c_attn.q_scale", "shape": [ 2048, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 159744, "byteOffset": 13864960 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 1536, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 14024704 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 1536, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 119808, "byteOffset": 14983168 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 15102976 }, { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 1536, 896 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5505024, "byteOffset": 15106048 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 1536, 224 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 688128, "byteOffset": 20611072 }, { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 17920, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 21299200 } ], "md5sum": "b2042b3986ee8ab4047dbc6713ab10fc" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 31416320, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 17920, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1397760, "byteOffset": 0 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 1397760 }, { "name": "model.layers.11.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 1400832 }, { "name": "model.layers.11.self_attn.c_attn.q_weight", "shape": [ 2048, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 1404928 }, { "name": "model.layers.11.self_attn.c_attn.q_scale", "shape": [ 2048, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 159744, "byteOffset": 2682880 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 1536, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 2842624 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 1536, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 119808, "byteOffset": 3801088 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 3920896 }, { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 1536, 896 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5505024, "byteOffset": 3923968 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 1536, 224 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 688128, "byteOffset": 9428992 }, { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 17920, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 10117120 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 17920, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1397760, "byteOffset": 21299200 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 22696960 }, { "name": "model.layers.12.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22700032 }, { "name": "model.layers.12.self_attn.c_attn.q_weight", "shape": [ 2048, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 22704128 }, { "name": "model.layers.12.self_attn.c_attn.q_scale", "shape": [ 2048, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 159744, "byteOffset": 23982080 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 1536, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 24141824 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 1536, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 119808, "byteOffset": 25100288 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 25220096 }, { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 1536, 896 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5505024, "byteOffset": 25223168 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 1536, 224 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 688128, "byteOffset": 30728192 } ], "md5sum": "ad19b1dbad425df59bc28c5422a3654a" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 32481280, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 17920, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 0 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 17920, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1397760, "byteOffset": 11182080 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 12579840 }, { "name": "model.layers.13.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12582912 }, { "name": "model.layers.13.self_attn.c_attn.q_weight", "shape": [ 2048, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 12587008 }, { "name": "model.layers.13.self_attn.c_attn.q_scale", "shape": [ 2048, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 159744, "byteOffset": 13864960 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 1536, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 14024704 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 1536, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 119808, "byteOffset": 14983168 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 15102976 }, { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 1536, 896 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5505024, "byteOffset": 15106048 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 1536, 224 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 688128, "byteOffset": 20611072 }, { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 17920, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 21299200 } ], "md5sum": "9053fb38c6481237888d15b128ba7cfa" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 31416320, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 17920, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1397760, "byteOffset": 0 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 1397760 }, { "name": "model.layers.14.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 1400832 }, { "name": "model.layers.14.self_attn.c_attn.q_weight", "shape": [ 2048, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 1404928 }, { "name": "model.layers.14.self_attn.c_attn.q_scale", "shape": [ 2048, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 159744, "byteOffset": 2682880 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 1536, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 2842624 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 1536, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 119808, "byteOffset": 3801088 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 3920896 }, { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 1536, 896 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5505024, "byteOffset": 3923968 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 1536, 224 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 688128, "byteOffset": 9428992 }, { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 17920, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 10117120 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 17920, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1397760, "byteOffset": 21299200 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 22696960 }, { "name": "model.layers.15.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22700032 }, { "name": "model.layers.15.self_attn.c_attn.q_weight", "shape": [ 2048, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 22704128 }, { "name": "model.layers.15.self_attn.c_attn.q_scale", "shape": [ 2048, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 159744, "byteOffset": 23982080 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 1536, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 24141824 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 1536, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 119808, "byteOffset": 25100288 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 25220096 }, { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 1536, 896 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5505024, "byteOffset": 25223168 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 1536, 224 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 688128, "byteOffset": 30728192 } ], "md5sum": "747eaab3e4f8f43f1c332532d31f26be" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 32481280, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 17920, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 0 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 17920, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1397760, "byteOffset": 11182080 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 12579840 }, { "name": "model.layers.16.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12582912 }, { "name": "model.layers.16.self_attn.c_attn.q_weight", "shape": [ 2048, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 12587008 }, { "name": "model.layers.16.self_attn.c_attn.q_scale", "shape": [ 2048, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 159744, "byteOffset": 13864960 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 1536, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 14024704 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 1536, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 119808, "byteOffset": 14983168 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 15102976 }, { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 1536, 896 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5505024, "byteOffset": 15106048 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 1536, 224 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 688128, "byteOffset": 20611072 }, { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 17920, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 21299200 } ], "md5sum": "359905d0d75dbaf8cee73383397eeef4" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 31416320, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 17920, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1397760, "byteOffset": 0 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 1397760 }, { "name": "model.layers.17.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 1400832 }, { "name": "model.layers.17.self_attn.c_attn.q_weight", "shape": [ 2048, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 1404928 }, { "name": "model.layers.17.self_attn.c_attn.q_scale", "shape": [ 2048, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 159744, "byteOffset": 2682880 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 1536, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 2842624 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 1536, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 119808, "byteOffset": 3801088 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 3920896 }, { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 1536, 896 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5505024, "byteOffset": 3923968 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 1536, 224 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 688128, "byteOffset": 9428992 }, { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 17920, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 10117120 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 17920, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1397760, "byteOffset": 21299200 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 22696960 }, { "name": "model.layers.18.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22700032 }, { "name": "model.layers.18.self_attn.c_attn.q_weight", "shape": [ 2048, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 22704128 }, { "name": "model.layers.18.self_attn.c_attn.q_scale", "shape": [ 2048, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 159744, "byteOffset": 23982080 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 1536, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 24141824 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 1536, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 119808, "byteOffset": 25100288 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 25220096 }, { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 1536, 896 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5505024, "byteOffset": 25223168 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 1536, 224 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 688128, "byteOffset": 30728192 } ], "md5sum": "01e3a2b7ad48303d790bc077a0885233" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 32481280, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 17920, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 0 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 17920, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1397760, "byteOffset": 11182080 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 12579840 }, { "name": "model.layers.19.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12582912 }, { "name": "model.layers.19.self_attn.c_attn.q_weight", "shape": [ 2048, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 12587008 }, { "name": "model.layers.19.self_attn.c_attn.q_scale", "shape": [ 2048, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 159744, "byteOffset": 13864960 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 1536, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 14024704 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 1536, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 119808, "byteOffset": 14983168 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 15102976 }, { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 1536, 896 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5505024, "byteOffset": 15106048 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 1536, 224 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 688128, "byteOffset": 20611072 }, { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 17920, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 21299200 } ], "md5sum": "4908df5a4a0f62bac148482dc753446d" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 31416320, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 17920, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1397760, "byteOffset": 0 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 1397760 }, { "name": "model.layers.2.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 1400832 }, { "name": "model.layers.2.self_attn.c_attn.q_weight", "shape": [ 2048, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 1404928 }, { "name": "model.layers.2.self_attn.c_attn.q_scale", "shape": [ 2048, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 159744, "byteOffset": 2682880 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 1536, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 2842624 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 1536, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 119808, "byteOffset": 3801088 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 3920896 }, { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 1536, 896 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5505024, "byteOffset": 3923968 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 1536, 224 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 688128, "byteOffset": 9428992 }, { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 17920, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 10117120 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 17920, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1397760, "byteOffset": 21299200 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 22696960 }, { "name": "model.layers.20.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22700032 }, { "name": "model.layers.20.self_attn.c_attn.q_weight", "shape": [ 2048, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 22704128 }, { "name": "model.layers.20.self_attn.c_attn.q_scale", "shape": [ 2048, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 159744, "byteOffset": 23982080 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 1536, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 24141824 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 1536, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 119808, "byteOffset": 25100288 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 25220096 }, { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 1536, 896 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5505024, "byteOffset": 25223168 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 1536, 224 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 688128, "byteOffset": 30728192 } ], "md5sum": "fce3d559b170686d288c758b8910375c" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 32481280, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 17920, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 0 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 17920, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1397760, "byteOffset": 11182080 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 12579840 }, { "name": "model.layers.21.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12582912 }, { "name": "model.layers.21.self_attn.c_attn.q_weight", "shape": [ 2048, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 12587008 }, { "name": "model.layers.21.self_attn.c_attn.q_scale", "shape": [ 2048, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 159744, "byteOffset": 13864960 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 1536, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 14024704 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 1536, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 119808, "byteOffset": 14983168 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 15102976 }, { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 1536, 896 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5505024, "byteOffset": 15106048 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 1536, 224 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 688128, "byteOffset": 20611072 }, { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 17920, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 21299200 } ], "md5sum": "79e7736f957deacee569fc9edc982042" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 31416320, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 17920, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1397760, "byteOffset": 0 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 1397760 }, { "name": "model.layers.22.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 1400832 }, { "name": "model.layers.22.self_attn.c_attn.q_weight", "shape": [ 2048, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 1404928 }, { "name": "model.layers.22.self_attn.c_attn.q_scale", "shape": [ 2048, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 159744, "byteOffset": 2682880 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 1536, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 2842624 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 1536, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 119808, "byteOffset": 3801088 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 3920896 }, { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 1536, 896 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5505024, "byteOffset": 3923968 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 1536, 224 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 688128, "byteOffset": 9428992 }, { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 17920, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 10117120 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 17920, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1397760, "byteOffset": 21299200 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 22696960 }, { "name": "model.layers.23.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22700032 }, { "name": "model.layers.23.self_attn.c_attn.q_weight", "shape": [ 2048, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 22704128 }, { "name": "model.layers.23.self_attn.c_attn.q_scale", "shape": [ 2048, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 159744, "byteOffset": 23982080 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 1536, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 24141824 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 1536, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 119808, "byteOffset": 25100288 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 25220096 }, { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 1536, 896 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5505024, "byteOffset": 25223168 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 1536, 224 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 688128, "byteOffset": 30728192 } ], "md5sum": "3c99a8a276ea9d96c914f997c0131191" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 32481280, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 17920, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 0 }, { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 17920, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1397760, "byteOffset": 11182080 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 12579840 }, { "name": "model.layers.24.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12582912 }, { "name": "model.layers.24.self_attn.c_attn.q_weight", "shape": [ 2048, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 12587008 }, { "name": "model.layers.24.self_attn.c_attn.q_scale", "shape": [ 2048, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 159744, "byteOffset": 13864960 }, { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 1536, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 14024704 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 1536, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 119808, "byteOffset": 14983168 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 15102976 }, { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 1536, 896 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5505024, "byteOffset": 15106048 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 1536, 224 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 688128, "byteOffset": 20611072 }, { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 17920, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 21299200 } ], "md5sum": "ab555859333aad5f92db0b6e46ac3663" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 31416320, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 17920, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1397760, "byteOffset": 0 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 1397760 }, { "name": "model.layers.25.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 1400832 }, { "name": "model.layers.25.self_attn.c_attn.q_weight", "shape": [ 2048, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 1404928 }, { "name": "model.layers.25.self_attn.c_attn.q_scale", "shape": [ 2048, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 159744, "byteOffset": 2682880 }, { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 1536, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 2842624 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 1536, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 119808, "byteOffset": 3801088 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 3920896 }, { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 1536, 896 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5505024, "byteOffset": 3923968 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 1536, 224 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 688128, "byteOffset": 9428992 }, { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 17920, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 10117120 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 17920, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1397760, "byteOffset": 21299200 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 22696960 }, { "name": "model.layers.26.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22700032 }, { "name": "model.layers.26.self_attn.c_attn.q_weight", "shape": [ 2048, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 22704128 }, { "name": "model.layers.26.self_attn.c_attn.q_scale", "shape": [ 2048, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 159744, "byteOffset": 23982080 }, { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 1536, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 24141824 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 1536, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 119808, "byteOffset": 25100288 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 25220096 }, { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 1536, 896 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5505024, "byteOffset": 25223168 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 1536, 224 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 688128, "byteOffset": 30728192 } ], "md5sum": "c1eb2a3a19b3c33f7ab75f115f6ffbfd" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 32481280, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 17920, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 0 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 17920, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1397760, "byteOffset": 11182080 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 12579840 }, { "name": "model.layers.27.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12582912 }, { "name": "model.layers.27.self_attn.c_attn.q_weight", "shape": [ 2048, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 12587008 }, { "name": "model.layers.27.self_attn.c_attn.q_scale", "shape": [ 2048, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 159744, "byteOffset": 13864960 }, { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 1536, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 14024704 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 1536, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 119808, "byteOffset": 14983168 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 15102976 }, { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 1536, 896 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5505024, "byteOffset": 15106048 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 1536, 224 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 688128, "byteOffset": 20611072 }, { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 17920, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 21299200 } ], "md5sum": "ced3a5c648f96de3fa77d9a0b294aed7" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 31416320, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 17920, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1397760, "byteOffset": 0 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 1397760 }, { "name": "model.layers.3.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 1400832 }, { "name": "model.layers.3.self_attn.c_attn.q_weight", "shape": [ 2048, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 1404928 }, { "name": "model.layers.3.self_attn.c_attn.q_scale", "shape": [ 2048, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 159744, "byteOffset": 2682880 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 1536, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 2842624 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 1536, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 119808, "byteOffset": 3801088 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 3920896 }, { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 1536, 896 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5505024, "byteOffset": 3923968 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 1536, 224 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 688128, "byteOffset": 9428992 }, { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 17920, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 10117120 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 17920, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1397760, "byteOffset": 21299200 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 22696960 }, { "name": "model.layers.4.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22700032 }, { "name": "model.layers.4.self_attn.c_attn.q_weight", "shape": [ 2048, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 22704128 }, { "name": "model.layers.4.self_attn.c_attn.q_scale", "shape": [ 2048, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 159744, "byteOffset": 23982080 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 1536, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 24141824 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 1536, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 119808, "byteOffset": 25100288 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 25220096 }, { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 1536, 896 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5505024, "byteOffset": 25223168 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 1536, 224 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 688128, "byteOffset": 30728192 } ], "md5sum": "97cdd79091ea4637619dcce065a4080f" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 32481280, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 17920, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 0 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 17920, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1397760, "byteOffset": 11182080 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 12579840 }, { "name": "model.layers.5.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12582912 }, { "name": "model.layers.5.self_attn.c_attn.q_weight", "shape": [ 2048, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 12587008 }, { "name": "model.layers.5.self_attn.c_attn.q_scale", "shape": [ 2048, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 159744, "byteOffset": 13864960 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 1536, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 14024704 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 1536, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 119808, "byteOffset": 14983168 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 15102976 }, { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 1536, 896 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5505024, "byteOffset": 15106048 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 1536, 224 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 688128, "byteOffset": 20611072 }, { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 17920, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 21299200 } ], "md5sum": "d9c4ba941c7feda6646d56b7e19ab10e" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 31416320, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 17920, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1397760, "byteOffset": 0 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 1397760 }, { "name": "model.layers.6.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 1400832 }, { "name": "model.layers.6.self_attn.c_attn.q_weight", "shape": [ 2048, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 1404928 }, { "name": "model.layers.6.self_attn.c_attn.q_scale", "shape": [ 2048, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 159744, "byteOffset": 2682880 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 1536, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 2842624 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 1536, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 119808, "byteOffset": 3801088 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 3920896 }, { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 1536, 896 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5505024, "byteOffset": 3923968 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 1536, 224 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 688128, "byteOffset": 9428992 }, { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 17920, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 10117120 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 17920, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1397760, "byteOffset": 21299200 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 22696960 }, { "name": "model.layers.7.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22700032 }, { "name": "model.layers.7.self_attn.c_attn.q_weight", "shape": [ 2048, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 22704128 }, { "name": "model.layers.7.self_attn.c_attn.q_scale", "shape": [ 2048, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 159744, "byteOffset": 23982080 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 1536, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 24141824 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 1536, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 119808, "byteOffset": 25100288 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 25220096 }, { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 1536, 896 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5505024, "byteOffset": 25223168 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 1536, 224 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 688128, "byteOffset": 30728192 } ], "md5sum": "19e03ea01610e8409aac9a1e0edd0ce0" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 32481280, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 17920, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 0 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 17920, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1397760, "byteOffset": 11182080 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 12579840 }, { "name": "model.layers.8.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12582912 }, { "name": "model.layers.8.self_attn.c_attn.q_weight", "shape": [ 2048, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 12587008 }, { "name": "model.layers.8.self_attn.c_attn.q_scale", "shape": [ 2048, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 159744, "byteOffset": 13864960 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 1536, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 14024704 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 1536, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 119808, "byteOffset": 14983168 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 15102976 }, { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 1536, 896 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5505024, "byteOffset": 15106048 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 1536, 224 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 688128, "byteOffset": 20611072 }, { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 17920, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11182080, "byteOffset": 21299200 } ], "md5sum": "432f2c9cd94c5ce796f4299fd8bbee01" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 3923968, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 17920, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1397760, "byteOffset": 0 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 1397760 }, { "name": "model.layers.9.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 1400832 }, { "name": "model.layers.9.self_attn.c_attn.q_weight", "shape": [ 2048, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1277952, "byteOffset": 1404928 }, { "name": "model.layers.9.self_attn.c_attn.q_scale", "shape": [ 2048, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 159744, "byteOffset": 2682880 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 1536, 156 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 958464, "byteOffset": 2842624 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 1536, 39 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 119808, "byteOffset": 3801088 }, { "name": "model.norm.weight", "shape": [ 1536 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3072, "byteOffset": 3920896 } ], "md5sum": "228f5bbe20a6faf40d77b53cdc5466d0" } ] }