{ "metadata": { "ParamSize": 325, "ParamBytes": 3279018496.0, "BitsPerParam": 2.609890907016264 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 54634496, "records": [ { "name": "lm_head.q_weight", "shape": [ 33152, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 54634496, "byteOffset": 0 } ], "md5sum": "32f214101f6bbbbb6da2311eef1fdb82" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "d02949b67064a64384f165419c381867" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 54634496, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 33152, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 54634496, "byteOffset": 0 } ], "md5sum": "9ca2f38d8ccb2331180900783bc2c91c" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "a0823322e5cebf970fccaa5b2924335d" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "038a58cfde57968065cb48f5f348b96d" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 28453376, "records": [ { "name": "lm_head.q_scale", "shape": [ 33152, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6829312, "byteOffset": 0 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 6829312 }, { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 6837504 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 12743936 }, { "name": "model.norm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 12752128 }, { "name": "model.embed_tokens.q_scale", "shape": [ 33152, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6829312, "byteOffset": 12760320 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 19589632 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 19597824 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 22538752 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 28445184 } ], "md5sum": "90c2ab8dc56d41fbdcc958f90777a624" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "1e58f89b555bbd95a26cfcaa4fa2b029" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "16b89fde1bd3b9f55b607820792ae179" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 10125312 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 11390976 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 18141184 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 18984960 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 18993152 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 21934080 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 27840512 } ], "md5sum": "2cc76cab2c1bd280007f069aa0be05c5" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 30375936, "records": [ { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 0 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 10125312 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 11390976 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 18141184 }, { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 18984960 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 29110272 } ], "md5sum": "32a592f95b75af1b487978854514cb32" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 31129600, "records": [ { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 0 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 6750208 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 7593984 }, { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 7602176 } ], "md5sum": "136df7853c36669d6057a3f5fa854fab" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "2896c6e49cd867382f8419e0b2cfa40f" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "49000346e8ae768ef39d4a1e679a4c9f" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "c6d5261b90be6321abf1edcce600f77b" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 30789632, "records": [ { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 0 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 2940928 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 8847360 }, { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 8855552 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 18980864 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 20246528 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 26996736 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 27840512 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 27848704 } ], "md5sum": "25eab09253a5ce263b48be94c1bed00a" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "e5675ec53e3edd8f53ff9fef8c5eb834" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "8cf3baf7bb0cc392cc133221647345cd" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "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": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "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": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "4fa1e59034e1fac65b1becd7d05b227d" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "5b0b3cb9ec95c355de39767d90d2cdee" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "d6939e18f1d4bde0cd6a5f391c71f091" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "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": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "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": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "018c0b56655aca2bdbc51a7202788507" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "aa73c6ccd80c7b6b3d5e0b3f1e1793c5" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "6d5bfa4816e9290c1cab4f815b0b7546" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "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": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "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": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "8403a25c00ec43724bac4f8d5100b2ce" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "840b9169d4ab0bc560ed5e2a4583163c" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "55464047ae5f5433cb7a1e69144f13b0" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "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": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "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": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "cef4f0d225ea402e8210832734b34477" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "8a30edd4b78af4084b1a42fbb694438e" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "ff7c1f4834ae43ea8d031d9b7fff274a" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "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": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "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": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "892d5aaba2bc820acd7bc435793ee420" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "b700dc5dd63113c66931edb40d3aba5a" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "5c1b10901599a060f4b6da2410fe18e1" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "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": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "27df1319522a3cce20bf87380ada5b6b" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "63b9ee08325b64b9de31930a1e7fc3af" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "4fafe9e95bb6e627e643de85688fd67f" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "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": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "f63bd8952da336819b481ff7554fbfa3" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "eceda7dbfbefcf27deb0ec3a870f15f2" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 32391168, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "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.11.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5914624 }, { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 5922816 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 29450240 } ], "md5sum": "b2e76bbe1fa8c9fa26c0073cad9d2f42" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "68fd3783f5cc3ab1a4ba1b64fffa617b" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "48b5c28221c59c36f3b7ebaff9a0a324" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "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": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "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": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "7577ee810ff264980d18dbe513d0a617" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "03dcecee5104ba7b7db1ce2b57b59f89" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "76009a597cf83869a77b3241da494b0b" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "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": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "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": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "511d33c390a417c05cf0799e83d84cdc" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "71b507138794e51da742bf3a9eb06591" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "adedf93ad9e3b5e1bda5e939bf1ad36d" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "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": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "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": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "324271acdf8e7f537a0989941f4d56c6" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "556bf13b4fdcad30af4503f93e09bc62" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "8a1069755b393515e0d2f2caac6a31f1" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "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": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "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": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "0345f4ff508712789d5f2ab1ddcd0cd8" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "e05fb51b5ebcdcbb06616ed7bed8da69" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "fddc1787b7e02081e846850d2da73078" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "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": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "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": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "ec0c4781e255fbe991681ecc26cbdf75" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "f50d29d68071ea0ae9f5c5306ba42217" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "5420b6d97a0c5d3c2c055cc92d41db49" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "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": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "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": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "b61ecd2731c6ec27d1549b5927f892fc" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "1fb18bdc1a5bde01b7b82997b63b91c8" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "3866277b9b6084ff70992a94edbcc196" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "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": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "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": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "b3a2669529605cf740a41658773562d0" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "1d5b257309d9423e9c1988d42753f03f" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "4ed25475d80029cb24aafca145794428" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "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": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "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": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "07c31825b3c743ce42359633e6e531f2" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "17cca9ded84c549540e80b994d40ab49" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "367bdb2b587a56f8937f67633c10c526" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "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": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "5560252799890005a1e8b664cd20bbc2" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 24899584, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.20.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 } ], "md5sum": "412b9df855a58de79ff566e4beef857a" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "ac7da3f2944514e935f0fffaddf432a5" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "1fb41a07ea5797d7acd88ae379c4bd7a" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "4919399e21829914b0ed7d1164b00a25" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "88fde9826bb27b232db1e86885e07a5a" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 30797824, "records": [ { "name": "model.layers.21.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 0 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 10125312 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 11390976 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 11399168 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 14340096 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 20246528 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 20254720 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 27004928 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 27848704 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 27856896 } ], "md5sum": "4c40b6806620e7e19720afc4885c9e08" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "ce3636c33f964ac4b8dfd27f176afdbe" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "34eb4da10e3555861c09a96440d7bc3a" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.22.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.22.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "1cb5a7a14587f3dfc1357ac84708f439" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "00a79d89360774a4157a15ca863a8a68" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "fc675131895ee1ad47024c4f49813ab3" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.23.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.23.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "46ee535e4fecead8d3ff2b9bcf2466f7" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "602a5a737d3b3f63d754a29507a709e5" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "43956bfd191fb9dad4dae794053c14ca" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.24.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.24.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "f3b6ac40c97b75ebba7a2adcc2ffa958" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "1d2fc934c8a30260954b3aba3f280fff" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "964772f76995279ff708da6f8f4274fc" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.25.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.25.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "43a7ec74a18af64c07026ca2ac42b0c9" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "f08c327f09d9ab5cd9cb957bace8066c" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "67c74722a4362185fb99d9db0d44a51c" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.26.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.26.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "bb09d570433c9e220ac88bcc8b069708" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "839bd0b1f8ad7310032b9f3dddca64fa" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "4bc0155c917622ad2a91cc4dac0e09f1" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.27.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.27.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "b037967e647bee2de82340144acc3ae9" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "a9e9255540512aba5a97ba12f4ae3d9a" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "3e31c0acf8ace4b53054b6c68a9ab333" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.28.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.28.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "07bd38faa73e3c09823579443c838ff9" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "c6649cd07704512a8bc5cf55a86be4ea" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "1a7d138d22acf81a7bafb4de847d1c1f" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.29.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.29.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "846baf9ca7f740c95c2c7569050edaac" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "add39d675937f4fa65d9a6bc51899de7" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 27840512, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.30.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.30.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24899584 } ], "md5sum": "e3cc034143368901c9309bc845b8f070" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 18984960, "records": [ { "name": "model.layers.31.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 0 }, { "name": "model.layers.31.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 10125312 }, { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 11390976 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 18141184 } ], "md5sum": "ae1700a480cb88a67f4f3b7f9a7bd82f" } ] }