diff --git "a/ndarray-cache.json" "b/ndarray-cache.json" new file mode 100644--- /dev/null +++ "b/ndarray-cache.json" @@ -0,0 +1,4311 @@ +{ + "metadata": { + "ParamSize": 325, + "ParamBytes": 3631664128.0, + "BitsPerParam": 2.6739310072364444 + }, + "records": [ + { + "dataPath": "params_shard_0.bin", + "format": "raw-shard", + "nbytes": 211365888, + "records": [ + { + "name": "lm_head.q_weight", + "shape": [ + 128256, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 211365888, + "byteOffset": 0 + } + ], + "md5sum": "a2f4a1dca6d2bd00daca338eec8bd3b5" + }, + { + "dataPath": "params_shard_1.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": "51f7103b5a18ff113d4f6db3ecf0b600" + }, + { + "dataPath": "params_shard_2.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": "d59b1d854d606d53b10a00871be3820c" + }, + { + "dataPath": "params_shard_3.bin", + "format": "raw-shard", + "nbytes": 29369856, + "records": [ + { + "name": "lm_head.q_scale", + "shape": [ + 128256, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 26420736, + "byteOffset": 0 + }, + { + "name": "model.layers.30.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 26420736 + }, + { + "name": "model.layers.30.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 26428928 + } + ], + "md5sum": "c23b750e59892fd21fa2f941ce1aabef" + }, + { + "dataPath": "params_shard_4.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": "92d37b1ee28a148a90022ccc361f3f4f" + }, + { + "dataPath": "params_shard_5.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": "1e434a65bd9e6cdb814e5bf1d2aa6f09" + }, + { + "dataPath": "params_shard_6.bin", + "format": "raw-shard", + "nbytes": 27848704, + "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.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 5914624 + }, + { + "name": "model.layers.30.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 12664832 + }, + { + "name": "model.layers.30.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 13508608 + }, + { + "name": "model.layers.30.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 23633920 + }, + { + "name": "model.layers.31.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24899584 + }, + { + "name": "model.layers.31.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 24907776 + } + ], + "md5sum": "7227205a804dd4cd99368443c5040cc8" + }, + { + "dataPath": "params_shard_7.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": "28cf331dee364ef28fd7e486b8787b11" + }, + { + "dataPath": "params_shard_8.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": "79a4d97e5e3f5397e32e86275d4a8f93" + }, + { + "dataPath": "params_shard_9.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": "b1bab467b46510d667c7a1a415c0e992" + }, + { + "dataPath": "params_shard_10.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": "94af387c6528ce84e1499eab9f330791" + }, + { + "dataPath": "params_shard_11.bin", + "format": "raw-shard", + "nbytes": 27856896, + "records": [ + { + "name": "model.layers.31.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 0 + }, + { + "name": "model.layers.31.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5906432 + }, + { + "name": "model.layers.31.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 5914624 + }, + { + "name": "model.layers.31.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 16039936 + }, + { + "name": "model.layers.31.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 17305600 + }, + { + "name": "model.layers.31.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 24055808 + }, + { + "name": "model.norm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24899584 + }, + { + "name": "model.layers.0.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24907776 + }, + { + "name": "model.layers.0.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 24915968 + } + ], + "md5sum": "205718aed28f62b588cf48f52e4ef2c0" + }, + { + "dataPath": "params_shard_12.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": "0e5990dcd25b5628c20f248535f919b8" + }, + { + "dataPath": "params_shard_13.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": "f800e318f876e4ffafd37a7f29c1b2da" + }, + { + "dataPath": "params_shard_14.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.0.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "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": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 5914624 + }, + { + "name": "model.layers.0.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 16039936 + }, + { + "name": "model.layers.0.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 17305600 + }, + { + "name": "model.layers.0.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "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": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 24907776 + } + ], + "md5sum": "7b1f4573c04188c9d5c3cb5bac01f894" + }, + { + "dataPath": "params_shard_15.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.2.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "a72784d454464bfb60b3b099e9c5adcc" + }, + { + "dataPath": "params_shard_16.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": "df35f2378bbd02b3dcd6404c9bbcf2f0" + }, + { + "dataPath": "params_shard_17.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.1.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "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": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 5914624 + }, + { + "name": "model.layers.1.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 16039936 + }, + { + "name": "model.layers.1.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 17305600 + }, + { + "name": "model.layers.1.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "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": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 24907776 + } + ], + "md5sum": "f585399bf7ebb5d83c71d9574d3bbfd5" + }, + { + "dataPath": "params_shard_18.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": "3783080bd764b42aff3294bb1209fbce" + }, + { + "dataPath": "params_shard_19.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": "f59df5a673caba346a01c559c81fbb91" + }, + { + "dataPath": "params_shard_20.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.2.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "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": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 5914624 + }, + { + "name": "model.layers.2.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 16039936 + }, + { + "name": "model.layers.2.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 17305600 + }, + { + "name": "model.layers.2.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "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": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 24907776 + } + ], + "md5sum": "331357a38e9132098d74dfad1cd1f8e2" + }, + { + "dataPath": "params_shard_21.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": "7cb34add108bd687b79fb13a8aa7dfd3" + }, + { + "dataPath": "params_shard_22.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": "0a3dc7fcbe9a907d022148cf147b3caa" + }, + { + "dataPath": "params_shard_23.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": "0f85629f4f2affb8697b3beeffcb87b8" + }, + { + "dataPath": "params_shard_24.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": "ba5eaa416b89316ff12268594eb950bc" + }, + { + "dataPath": "params_shard_25.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": "09b09f36dc859689aa81d256727a8a34" + }, + { + "dataPath": "params_shard_26.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": "cf9e818cc4d0de132aabdd70f0395436" + }, + { + "dataPath": "params_shard_27.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": "2fcc4fccabe707f87bf021249c4bb3db" + }, + { + "dataPath": "params_shard_28.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": "2e499d181571e3d9cb5525d5dc4239d8" + }, + { + "dataPath": "params_shard_29.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": "77548697978adb8544c686975e755a1d" + }, + { + "dataPath": "params_shard_30.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": "f795715d4a36f5c53742a4d6add6d26e" + }, + { + "dataPath": "params_shard_31.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": "48c239e997faf33d883d87126a66dbf1" + }, + { + "dataPath": "params_shard_32.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": "da6c748e8420b81207115a0cfe3e8ff8" + }, + { + "dataPath": "params_shard_33.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": "4b8873e124d72f6403e190fe194f567c" + }, + { + "dataPath": "params_shard_34.bin", + "format": "raw-shard", + "nbytes": 30806016, + "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.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 24899584 + } + ], + "md5sum": "2b23efd7f7a7aef50224d27ba5070c3c" + }, + { + "dataPath": "params_shard_35.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": "67d8041bc0104e03019c1f1a28968c25" + }, + { + "dataPath": "params_shard_36.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": "bfee7dde66d640017180fcac57717f16" + }, + { + "dataPath": "params_shard_37.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.8.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.8.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.8.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.8.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.10.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.10.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.10.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.10.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "0306438e964fe92e24248b04aa45f138" + }, + { + "dataPath": "params_shard_38.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.11.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "e7a99b86160968ec8ea7b30189dfce95" + }, + { + "dataPath": "params_shard_39.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": "1154890df18458a8e11078d65c312e23" + }, + { + "dataPath": "params_shard_40.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.10.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.10.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.10.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.10.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.11.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.11.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.11.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.11.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "09f3dbcb3f399564b8f7d3c1d9e30cab" + }, + { + "dataPath": "params_shard_41.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": "ba9118554463f2057c98f04f321af838" + }, + { + "dataPath": "params_shard_42.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": "a2575ffb81a31494071f4f7b3b1db992" + }, + { + "dataPath": "params_shard_43.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.11.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.11.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.11.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.11.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.12.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.12.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.12.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.12.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "e852ac4c95b4d3c658b5ee30d9c9ee25" + }, + { + "dataPath": "params_shard_44.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": "b7c2cfebee80b59ad48aed8d410d1fd6" + }, + { + "dataPath": "params_shard_45.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": "2a60e30c864f73f35393f5693f5dc99b" + }, + { + "dataPath": "params_shard_46.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.12.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.12.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.12.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.12.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.13.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.13.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.13.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.13.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "07a9037aec1729deb7f9b050cf848348" + }, + { + "dataPath": "params_shard_47.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": "94bb9d68abc3b3452de60671fa58d538" + }, + { + "dataPath": "params_shard_48.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": "99bab9465c34abd4222c3748303eb3d9" + }, + { + "dataPath": "params_shard_49.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.13.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.13.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.13.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.13.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.14.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.14.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.14.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.14.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "80782d9f92885121dd6b68c479cc3fab" + }, + { + "dataPath": "params_shard_50.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": "1cc2415580f6ad461441f8281d025877" + }, + { + "dataPath": "params_shard_51.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": "61b21853328547e4218710d76ec81483" + }, + { + "dataPath": "params_shard_52.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.14.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.14.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.14.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.14.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.15.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.15.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.15.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.15.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "4f1ccced80f97eef4f47acbd7eeb09b1" + }, + { + "dataPath": "params_shard_53.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": "21e2479f0511fdfeeda40ef1ca205daa" + }, + { + "dataPath": "params_shard_54.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": "b7f79d2c7f64d5c9b93918486b5c5e44" + }, + { + "dataPath": "params_shard_55.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.15.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.15.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.15.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.15.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.16.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.16.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.16.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.16.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "18eb132fe2ace5f2090732120043984d" + }, + { + "dataPath": "params_shard_56.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": "615819eef39952a0fa4ef14d096a20bd" + }, + { + "dataPath": "params_shard_57.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": "72c40fc0b8f79ec4292693185c5bd61e" + }, + { + "dataPath": "params_shard_58.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.16.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.16.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.16.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.16.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.17.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.17.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.17.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.17.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "50ecf9292cc000afcbea564c75b2f2ce" + }, + { + "dataPath": "params_shard_59.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": "db6c6fa19c3ff212fa88c5e4388fe62b" + }, + { + "dataPath": "params_shard_60.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": "517e6dcc55fb73f394a1dfd880890651" + }, + { + "dataPath": "params_shard_61.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.17.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.17.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.17.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.17.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.18.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.18.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.18.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.18.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "a7275375ec39852d0ad419efd702c1e0" + }, + { + "dataPath": "params_shard_62.bin", + "format": "raw-shard", + "nbytes": 30375936, + "records": [ + { + "name": "model.layers.18.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.18.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.18.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.18.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.19.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 18984960 + }, + { + "name": "model.layers.19.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 29110272 + } + ], + "md5sum": "cffb8a2d667d43c815dea09615d3d57e" + }, + { + "dataPath": "params_shard_63.bin", + "format": "raw-shard", + "nbytes": 31129600, + "records": [ + { + "name": "model.layers.19.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 0 + }, + { + "name": "model.layers.19.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 6750208 + }, + { + "name": "model.layers.8.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 7593984 + }, + { + "name": "model.layers.8.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 7602176 + } + ], + "md5sum": "2c59f674dd983c9d1533cbfcc32e4d50" + }, + { + "dataPath": "params_shard_64.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": "a96e9bbcd47c8dff882d5aa43211936a" + }, + { + "dataPath": "params_shard_65.bin", + "format": "raw-shard", + "nbytes": 29425664, + "records": [ + { + "name": "model.layers.8.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 0 + }, + { + "name": "model.layers.8.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 2940928 + }, + { + "name": "model.layers.9.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 2949120 + }, + { + "name": "model.layers.9.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 2957312 + }, + { + "name": "model.layers.9.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 26484736 + } + ], + "md5sum": "20d2dbb2b8ab819fe61746088d5f01c1" + }, + { + "dataPath": "params_shard_66.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": "cbcc787b0b0412b6642fd267b43f94ed" + }, + { + "dataPath": "params_shard_67.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": "5be09de7ea738457bd055beca83341e8" + }, + { + "dataPath": "params_shard_68.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.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": "8cd832c21887584b37af2d2cd697c3b0" + }, + { + "dataPath": "params_shard_69.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": "4baf15c3a2eaba63c0eefada95545f1d" + }, + { + "dataPath": "params_shard_70.bin", + "format": "raw-shard", + "nbytes": 32391168, + "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.20.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5914624 + }, + { + "name": "model.layers.20.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 5922816 + }, + { + "name": "model.layers.20.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 29450240 + } + ], + "md5sum": "2cc0caa71eed5e335ec694657638b708" + }, + { + "dataPath": "params_shard_71.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": "1ff92003b3be1fbe36d8219c266666cf" + }, + { + "dataPath": "params_shard_72.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": "dc3662adc2e845dec606a633432f2b77" + }, + { + "dataPath": "params_shard_73.bin", + "format": "raw-shard", + "nbytes": 27848704, + "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 + }, + { + "name": "model.layers.21.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24899584 + }, + { + "name": "model.layers.21.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 24907776 + } + ], + "md5sum": "a6db154eeacaffef4b99e28e12544f16" + }, + { + "dataPath": "params_shard_74.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": "ce3f7363937c9aa6d113725226b225f6" + }, + { + "dataPath": "params_shard_75.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": "ec523f769e4947e7e725538b5f7e70d7" + }, + { + "dataPath": "params_shard_76.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.21.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 0 + }, + { + "name": "model.layers.21.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5906432 + }, + { + "name": "model.layers.21.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 5914624 + }, + { + "name": "model.layers.21.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 16039936 + }, + { + "name": "model.layers.21.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 17305600 + }, + { + "name": "model.layers.21.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 24055808 + }, + { + "name": "model.layers.22.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24899584 + }, + { + "name": "model.layers.22.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 24907776 + } + ], + "md5sum": "0d7e580b3c788afa93c13b3533c07fe8" + }, + { + "dataPath": "params_shard_77.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": "b7bf07ce90741ca84c60afa884337c66" + }, + { + "dataPath": "params_shard_78.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": "b2f60749ddb9a91c196d898964407bcc" + }, + { + "dataPath": "params_shard_79.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": "f5f81a833fc8e85c551d3bc3adf2ae08" + }, + { + "dataPath": "params_shard_80.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": "2c4b37f5686d1f57bf52ac317e7fe5e9" + }, + { + "dataPath": "params_shard_81.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": "85aaf04d5dbd1dd2c14e824e0306188c" + }, + { + "dataPath": "params_shard_82.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": "5b28cf0b19e78fc3c3c9529b9cb5031f" + }, + { + "dataPath": "params_shard_83.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": "8f2ec97c3e4f4d06743fadf8a856fa58" + }, + { + "dataPath": "params_shard_84.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": "c13b2161949a40134be3bf0b7c811992" + }, + { + "dataPath": "params_shard_85.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": "ba25e23e65542c71a919409c54254360" + }, + { + "dataPath": "params_shard_86.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": "596be593622cd0dd86a28cd7c05245d0" + }, + { + "dataPath": "params_shard_87.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": "a82d0763946e5d6d88fbacce038fa269" + }, + { + "dataPath": "params_shard_88.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": "2f77e99d504c5be4d3d0c1731e524c31" + }, + { + "dataPath": "params_shard_89.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": "1a729a32192effad6d3016d7949d2506" + }, + { + "dataPath": "params_shard_90.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": "4d30e7501deca8bcfdfd504681c12b8a" + }, + { + "dataPath": "params_shard_91.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": "ecb67c97573974575ae668ab358603ac" + }, + { + "dataPath": "params_shard_92.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": "9be8fd54f6f90461bb4b5b3b56084506" + }, + { + "dataPath": "params_shard_93.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": "0c6fb9d16b110108708a985c2369c175" + }, + { + "dataPath": "params_shard_94.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": "9864f906ac7ef98fd06dc3a948f1d6c7" + }, + { + "dataPath": "params_shard_95.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": "8ff05a95c5afda3189a7a7f0d3e7f3b7" + }, + { + "dataPath": "params_shard_96.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": "1f3a3ef7957bfecf3905c50b91b259ba" + }, + { + "dataPath": "params_shard_97.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": "63ef83ada012b3a00f663ae8fd0aa29e" + }, + { + "dataPath": "params_shard_98.bin", + "format": "raw-shard", + "nbytes": 24899584, + "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 + } + ], + "md5sum": "c2507489f8bb0b8ffe566ee22befb4ac" + } + ] +} \ No newline at end of file