{ "metadata": { "ParamSize": 325, "ParamBytes": 3631664128.0, "BitsPerParam": 3.617978559693305 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 211365888, "records": [ { "name": "lm_head.q_weight", "shape": [ 412, 128256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 211365888, "byteOffset": 0 } ], "md5sum": "62e5472e69bee32aeace72727f520aa6" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 1436, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "b4de61366df5af66ff855c1d935337ff" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 211365888, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 128256, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 211365888, "byteOffset": 0 } ], "md5sum": "3e45727898c14454774304cccd999ebe" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 26420736, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 128256, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 26420736, "byteOffset": 0 } ], "md5sum": "da547dd4e70f656eb8f40d6d8956af59" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 1436, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "8ffe47f63cd0e4f4d8c72c8cfc0ce194" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 412, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "55fccce6189d89b753ebbca86441afdc" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 32335360, "records": [ { "name": "lm_head.q_scale", "shape": [ 103, 128256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 26420736, "byteOffset": 0 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 26420736 }, { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 359, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 26428928 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29369856 }, { "name": "model.norm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29378048 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29386240 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 359, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 29394432 } ], "md5sum": "e0994d2bd03e708228da949ad5668378" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 1436, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "d14c325f8d6c2a79f6886b08cfcded67" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 412, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "e59935e3fcd3c44c66f18926edb6235a" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 103, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 412, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 103, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 412, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 103, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 359, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "e52bd3bf55192422adfdc7e30c5d5a87" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 1436, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "4b3cc59e1a117d246d328faf34848ffa" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 412, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "4a7b7a1876af3d6609655142dac341af" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 103, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 412, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 103, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 412, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 103, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 359, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "ee4a803440f79261ed413ce7cdc71d3f" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 1436, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "cf2697042348ba27193c5b4c590b7ff8" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 412, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "32819c19ef30c9dd4309ed4d565a7a92" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 103, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 412, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 103, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 412, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 103, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 359, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "b00447c145c40b1aa2d74a48ccfb97d8" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 1436, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "b08efba49c29ffb3b931dbd760e6013b" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 412, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "f8ed3bee314dc658074ddc8dea2971d2" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 103, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 412, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 103, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 412, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 103, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 359, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "5ac099a6955bad3d48648edaea642b4e" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 1436, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "2a093e5cf451bbe3413a5f068c618c29" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 412, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "a0af9a06fd629289b4532889cde7f26d" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 103, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 412, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 103, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 412, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 103, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 359, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "6370c79a235a239d15e3ce341bf6dd5a" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 1436, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "fd6796b8116ac5d5f4fdc507fb11b8a3" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 412, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "0848ecece56378e466d206c60ec5b6a1" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 103, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 412, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 103, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 412, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 103, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 359, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "be0c9b70eb822f00fc14ede2bf521df5" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 1436, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "af3b8ffc0edac321264c246f297d94f4" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 412, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "23a46bd048d7628ec32cc2777f65a989" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 103, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 412, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 103, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 412, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 103, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 359, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "f9eedd7c31e20a7d06b58298ddf8c9ad" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 1436, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "e5e19c87a70a4cba3f66da0447aa7e39" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 412, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "eb3609ad830eb0ddd06877eef16c9abe" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 103, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 412, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 103, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 412, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 103, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 359, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "9c0ea905b27a168d1b22f007f8cb862c" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 1436, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "e7c986e313a52e6a99994c6b5210800f" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 412, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "85fc8bdb777315a377aa9cb1bcb52110" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 103, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 412, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 103, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 412, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 103, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 359, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "18cd42517baff9178a5607d7e70101e5" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 1436, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "d37d4572aa9bd9dd354ce4eedc846945" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 412, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "84011eb43c00c3f66537db3e432ca2cd" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 103, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 412, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 103, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 412, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 103, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 359, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "5e133940a3da0ef749b4f5bd122e6f34" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 1436, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "e9c1baf38a897dfa8b24defe9fab0cc8" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 412, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "787fd6d32168c57a0a457af178028e31" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 103, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 412, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 103, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 412, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 103, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 359, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "1a299a6132feca7f55f75a3dc01b8331" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 1436, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "6c1eb849a76735afa20444e57dd13704" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 412, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "ae9e51bcc8f0e01e17ed29d6e72f5193" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 103, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 412, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 103, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 412, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 103, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 359, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "642bf414afeffcd79c7519dbef5cf6cf" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 1436, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "4259cfed6895513f67b2401c70d8c99c" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 412, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "595b24fcc796534cb7a6dc0f76794a8b" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 103, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 412, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 103, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 412, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 103, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 359, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "be054f0243f2465e86b73e3bfe6eee95" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 1436, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "1b9e879f243bc2ee651678eb398efc6b" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 412, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "543ea1f9a6167e532c18fc53acb8bc6d" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 103, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 412, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 103, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 412, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 103, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 359, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "1720361c9a2d9afe0a4f27214dcc3ea1" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 1436, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "c1d06b1b6fcd2b1b85593437e7e0497a" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 412, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "ea68bce14d0bd017851e3f47396b84cb" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 103, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 412, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 103, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 412, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 103, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 359, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "1962efe24df27d5eaa680840c515f440" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 1436, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "61c540fbf1559e869fdd6009aab0b41c" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 412, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "55f9fe5642104b703733d1fcebe89f1b" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 103, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 412, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 103, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 412, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 103, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 359, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "80c8691c575383f90dcfe1fffab279bf" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 1436, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "6171744acb53b9dd84c767690fdf1945" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 412, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "b7bfbfc22bc353a4ecc3695e32972412" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 103, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 412, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 103, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 412, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 103, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 359, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "a2fa4456f5a93a7e3028bc66e5aefca2" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 1436, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "0b45e7305905ba6b9af0a0527e73ffbd" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 412, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "3571113c5e1b7a42d86753f013607ae2" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 103, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.18.self_attn.qkv_proj.q_weight", "shape": [ 412, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 103, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 412, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 103, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 359, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "a8b7baf342c015d45a8f4a93b3976eee" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 412, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "5fc6345e44fc7c0f2dca9f8021f0cde6" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 30806016, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 103, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.19.self_attn.qkv_proj.q_weight", "shape": [ 412, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 103, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 412, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 103, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 103, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 24899584 } ], "md5sum": "66fe7c5156f73b4630faf9e1b3e63c37" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 1436, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "343bb813b27afcf20fa87023e581771f" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 412, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "5450498746324ec6bd572e7c236417b0" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.20.self_attn.qkv_proj.q_weight", "shape": [ 412, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 0 }, { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 103, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 10125312 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 412, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 11390976 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 103, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 18141184 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 18984960 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 359, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 18993152 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 103, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 21934080 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 27840512 } ], "md5sum": "7a41284df9a0526da27068bdcf47b5e2" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 1436, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "330ade4b5ecd0c230a26ecf51fd5cc7a" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 1436, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "f2353cdcd69b44aecae38e9215a12966" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 412, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "b38a6c741fa4d864faa92ba81fea8fe6" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 30806016, "records": [ { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 412, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 0 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 103, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 10125312 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 412, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 11390976 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 103, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 18141184 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 18984960 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 359, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 18993152 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21934080 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21942272 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 359, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 21950464 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 103, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 24891392 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 30797824 } ], "md5sum": "c33180cca206d3827ed07ded0a2228b1" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 1436, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "f045d53b3b0ad1809032b55e87310692" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 412, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "c911fec60491c949b7f56b764c041cd1" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.21.self_attn.qkv_proj.q_weight", "shape": [ 412, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 0 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 103, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 10125312 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 412, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 11390976 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 103, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 18141184 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 18984960 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 359, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 18993152 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 103, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 21934080 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 27840512 } ], "md5sum": "2fb232cfcf91ffd8f5536468706a6561" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 1436, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "ec95a225dfe638928037bd86dc54a341" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 412, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "b706f5791090a6ace9537da154545e49" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.22.self_attn.qkv_proj.q_weight", "shape": [ 412, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 0 }, { "name": "model.layers.22.self_attn.qkv_proj.q_scale", "shape": [ 103, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 10125312 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 412, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 11390976 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 103, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 18141184 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 18984960 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 359, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 18993152 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 103, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 21934080 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 27840512 } ], "md5sum": "5e24e8f957b88b28edb54fff7ff012d3" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 1436, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "b99fc6d5a1b8ab48e519369731e77a97" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 412, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "9b6f13b8cedbce7aa62da71228fbb989" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.23.self_attn.qkv_proj.q_weight", "shape": [ 412, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 0 }, { "name": "model.layers.23.self_attn.qkv_proj.q_scale", "shape": [ 103, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 10125312 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 412, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 11390976 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 103, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 18141184 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 18984960 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 359, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 18993152 }, { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 103, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 21934080 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 27840512 } ], "md5sum": "85df007be605424f30bed1c7ce84ee73" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 1436, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "87cb836bd192acc19c191d53b6b9b2e9" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 412, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "bd0ef2e819b0daffeee673d400079d93" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.24.self_attn.qkv_proj.q_weight", "shape": [ 412, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 0 }, { "name": "model.layers.24.self_attn.qkv_proj.q_scale", "shape": [ 103, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 10125312 }, { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 412, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 11390976 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 103, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 18141184 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 18984960 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 359, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 18993152 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 103, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 21934080 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 27840512 } ], "md5sum": "43095080db59fbffaed626269064c59d" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 1436, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "be1f0774af4f039047071b0c9362c901" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 412, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "68b054a5266f790814f5d2d73976fd40" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.25.self_attn.qkv_proj.q_weight", "shape": [ 412, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 0 }, { "name": "model.layers.25.self_attn.qkv_proj.q_scale", "shape": [ 103, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 10125312 }, { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 412, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 11390976 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 103, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 18141184 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 18984960 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 359, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 18993152 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 103, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 21934080 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 27840512 } ], "md5sum": "4464286aa257741919fcbfeef93330d5" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 1436, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "f4228ded1d68a969de6230b852a95f71" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 412, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "525aa4e83d854e56d6bb504bdba7af9e" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.26.self_attn.qkv_proj.q_weight", "shape": [ 412, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 0 }, { "name": "model.layers.26.self_attn.qkv_proj.q_scale", "shape": [ 103, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 10125312 }, { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 412, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 11390976 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 103, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 18141184 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 18984960 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 359, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 18993152 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 103, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 21934080 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 27840512 } ], "md5sum": "a163d7daa3c9c88e3c1ea6dd4593d929" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 1436, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "7f6455168ca488e7a3d74744ab81ae9e" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 412, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "fde4768ac40a750ff2214645b7f26ca5" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.27.self_attn.qkv_proj.q_weight", "shape": [ 412, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 0 }, { "name": "model.layers.27.self_attn.qkv_proj.q_scale", "shape": [ 103, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 10125312 }, { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 412, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 11390976 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 103, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 18141184 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 18984960 }, { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 359, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 18993152 }, { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 103, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 21934080 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 27840512 } ], "md5sum": "88544a71276cf11d6b1778ee0676e99c" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 1436, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "3c97489024f6da27ebf2de099db7e761" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 412, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "46908195854506543e28d875828d0943" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.28.self_attn.qkv_proj.q_weight", "shape": [ 412, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 0 }, { "name": "model.layers.28.self_attn.qkv_proj.q_scale", "shape": [ 103, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 10125312 }, { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 412, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 11390976 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 103, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 18141184 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 18984960 }, { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 359, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 18993152 }, { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 103, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 21934080 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 27840512 } ], "md5sum": "12f63b9d3807cf1d3f33f170342f8e85" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 1436, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "6b27786375edb1198e99e47b1a64243a" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 412, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "f4dd9c8135874f7e978ffb01f44a205f" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.29.self_attn.qkv_proj.q_weight", "shape": [ 412, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 0 }, { "name": "model.layers.29.self_attn.qkv_proj.q_scale", "shape": [ 103, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 10125312 }, { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 412, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 11390976 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 103, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 18141184 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 18984960 }, { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 359, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 18993152 }, { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 103, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 21934080 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 27840512 } ], "md5sum": "5a5096a85dbaae3719769af719899e4d" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 412, 28672 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "5b59f8b5966575591895edf25e59aeba" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 24891392, "records": [ { "name": "model.layers.30.self_attn.qkv_proj.q_weight", "shape": [ 412, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 0 }, { "name": "model.layers.30.self_attn.qkv_proj.q_scale", "shape": [ 103, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 10125312 }, { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 412, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 11390976 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 103, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 18141184 }, { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 103, 28672 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 18984960 } ], "md5sum": "a340b6b758358dea270454973ddc41ec" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 18984960, "records": [ { "name": "model.layers.31.self_attn.qkv_proj.q_weight", "shape": [ 412, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 0 }, { "name": "model.layers.31.self_attn.qkv_proj.q_scale", "shape": [ 103, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 10125312 }, { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 412, 4096 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 11390976 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 103, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 18141184 } ], "md5sum": "a52013119a84a104b1894ae65d12d133" } ] }