diff --git "a/ndarray-cache.json" "b/ndarray-cache.json" new file mode 100644--- /dev/null +++ "b/ndarray-cache.json" @@ -0,0 +1,4303 @@ +{ + "metadata": { + "ParamSize": 325, + "ParamBytes": 3274746880.0, + "BitsPerParam": 2.6089405710472406 + }, + "records": [ + { + "dataPath": "params_shard_0.bin", + "format": "raw-shard", + "nbytes": 52736000, + "records": [ + { + "name": "lm_head.q_weight", + "shape": [ + 32000, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 52736000, + "byteOffset": 0 + } + ], + "md5sum": "9057609f70a0099a30869c069330ef9e" + }, + { + "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": "ee0ffd4c6054fb4a859ef505a9132099" + }, + { + "dataPath": "params_shard_2.bin", + "format": "raw-shard", + "nbytes": 52736000, + "records": [ + { + "name": "model.embed_tokens.q_weight", + "shape": [ + 32000, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 52736000, + "byteOffset": 0 + } + ], + "md5sum": "7f39b21ea37fed3ac77551f92a538d52" + }, + { + "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": "e0168b6e23be0a9368f378e14e152814" + }, + { + "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": "ad901b3d4475388909789b9bdb66dce4" + }, + { + "dataPath": "params_shard_5.bin", + "format": "raw-shard", + "nbytes": 27978752, + "records": [ + { + "name": "lm_head.q_scale", + "shape": [ + 32000, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6592000, + "byteOffset": 0 + }, + { + "name": "model.layers.31.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 6592000 + }, + { + "name": "model.layers.31.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 6600192 + }, + { + "name": "model.layers.31.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 12506624 + }, + { + "name": "model.norm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 12514816 + }, + { + "name": "model.embed_tokens.q_scale", + "shape": [ + 32000, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6592000, + "byteOffset": 12523008 + }, + { + "name": "model.layers.0.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 19115008 + }, + { + "name": "model.layers.0.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 19123200 + }, + { + "name": "model.layers.0.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 22064128 + }, + { + "name": "model.layers.0.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27970560 + } + ], + "md5sum": "fdd46be1fd4accbd5b07011bb1864186" + }, + { + "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": "bbb10c267069fed6e8a52d2b394de97f" + }, + { + "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": "5afee6600f35d0f5421a3554c2db9825" + }, + { + "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": "a08553e9b35ca5d055c7fa6dea890a67" + }, + { + "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": "bd56131962b25a72156c510b9c11cafa" + }, + { + "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": "580d5d85e75634ff66a3569d26020dd1" + }, + { + "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": "aa07c7508cb72ad7970f791d12f92314" + }, + { + "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": "fb90e60b7fa73250b40b345f1bfff9d8" + }, + { + "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": "f609ac54844c6c1f256674a5b25033c0" + }, + { + "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": "3e8d7ba38fc1e47f826af55554c85a2c" + }, + { + "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": "95c0872fe8813cfc2245d58b3994eb59" + }, + { + "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": "8cab40dfd6ff7d959786a7650712a8a4" + }, + { + "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": "c61156505524b3aa1420f7a6b01a119a" + }, + { + "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": "7528184e3bd07e96de7f4ead656c879f" + }, + { + "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": "0f111350de7dffc253d8be35a054dc35" + }, + { + "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": "6d64602fd319dc023571ad5756e0c2c8" + }, + { + "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": "834640071f777b60b62a7bad1eea557b" + }, + { + "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": "508b16157d21a737f754e0bbf310f8cc" + }, + { + "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": "7ab1856541e653950c493a730023290e" + }, + { + "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": "db695f252da907e8500940f71f445c6a" + }, + { + "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": "4d97b04afe8385b9f1960b9806a4d3f1" + }, + { + "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": "f111edba0adcde8720364a6e5051d6c1" + }, + { + "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": "fa4b07c2c9dad3db5d07067786832f31" + }, + { + "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": "d42f0a6e00b60729d971341b9efcc810" + }, + { + "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": "5f278733495ab9cfdb57b592b2234216" + }, + { + "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": "9d2c9b256d4f8976187760c9f3170494" + }, + { + "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": "3ffb1ae2a5b05949c5ac1771a4d8c141" + }, + { + "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": "3526607e8e398f05953a37c2e59e2d29" + }, + { + "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": "2f5ce36f3abcefbabeefeb79b8fac09f" + }, + { + "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": "ee9a2d1939daa5a7c99da305c6376e8e" + }, + { + "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": "1c06fae5bf0964c92b6f869d90dee7ab" + }, + { + "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": "acb51379425b8e81c4a064b4cc968f5a" + }, + { + "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": "2ce455ecc1d60e3584c4d2a00cfc0f47" + }, + { + "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": "8f87d783a7ec919d255ed8998656fec2" + }, + { + "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": "fb0e110412f4ca39b536daa6e85d0265" + }, + { + "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": "ee8bd9c064ca0fbd560fb6177beb138e" + }, + { + "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": "c7b0aff176f580eb3064985a77fdb08f" + }, + { + "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": "02f1dc4beb3d73dc21f3ae5a00f04377" + }, + { + "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": "0c3f9dd284879da4a57a8f947cd9cb6c" + }, + { + "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": "2af54b0728f6c33b2da185830b89375a" + }, + { + "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": "85fc52ebdff5410b5c73573251d74205" + }, + { + "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": "ca408e6c0ef24261b5e79a441b946f61" + }, + { + "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": "dbc9a54a5bdb6c5c0d9d4f50fd45cf3f" + }, + { + "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": "8958d54bc27201e837f7d0bcad94a1dc" + }, + { + "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": "c77f10e9db8b8d7f22c0783d3e26d6fd" + }, + { + "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": "3751d326d3d9ef1138d7ed994bfc937d" + }, + { + "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": "fc2f90f9c05de3a90ca2c0fe0057093c" + }, + { + "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": "73957bf137395b856413384684000216" + }, + { + "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": "76548ed45a268dbfcc02c7d82fb07fef" + }, + { + "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": "9a33b50cd924cacc8f5e286ea575082f" + }, + { + "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": "f6f193b948f8fbdf5d4e42aff2d94722" + }, + { + "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": "95d43784dda688b45db1b5d4b9cd4f18" + }, + { + "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": "d4263ba2322874343eb437b269b8939b" + }, + { + "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": "d7cdb6337ea6d3a845e54196750faef0" + }, + { + "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": "65d2cee0ebc8d84f8ef96e28c744ed3f" + }, + { + "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": "b6b23c7b4ca811cc602d157e48ec694e" + }, + { + "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": "f1c7436472f49a53157ad31cf4f2ef1b" + }, + { + "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": "c721541da9d9381083d9320d3427490b" + }, + { + "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": "2d493546c5bda3c5b816b13765d34834" + }, + { + "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": "714e0db31f3140a9b19ba9c03595db90" + }, + { + "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": "c7199ebd92a762a18faee23b2ac27381" + }, + { + "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": "8601d3d565487b0618f429ad93308f58" + }, + { + "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": "3fb6493df5626c2ead902b17f1bf2101" + }, + { + "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": "a89b916fa913363d3e91d8c1b60e04f7" + }, + { + "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": "10884d48367657ef94a4c594cc54f977" + }, + { + "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": "b27b65953e4af92aeb8471ef442f6cbe" + }, + { + "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": "4b2111f8e288d6e947875d965cb772d8" + }, + { + "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": "4de4b09717532ff5d38ab48ba4c8742d" + }, + { + "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": "3be038c7678181c9a7a3ad9c7a46f287" + }, + { + "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": "bd2015ce71fb7e22682a6392e61259c7" + }, + { + "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": "781f8880e19ae122aeb904d945f5f902" + }, + { + "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": "c0db4e4ed996b755a6288b3da31fa4ed" + }, + { + "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": "4ef9e28bc557473053b5e90e413494cc" + }, + { + "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": "53db2a80e6fb9c8207417a4fbaebeb0b" + }, + { + "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": "247b7d6f55aa8cda04f54674b54fad3d" + }, + { + "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": "10176217e528b48004c3dba841bff0ff" + }, + { + "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": "1ff0ed64522f1c940303d2b6a38f79cb" + }, + { + "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": "d629c1418c581f2d722725ea6dcb4b11" + }, + { + "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": "db0c570faa0e26cff9a83fddb1b4e8e8" + }, + { + "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": "3ebe3f682253623ef2b2cb1d3f2582ce" + }, + { + "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": "4394267b1df39656093f414dac8bf500" + }, + { + "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": "4524ebb49b4168f881f8047013dfa70e" + }, + { + "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": "b2108408bcabc86ed0ffbeb80009ead3" + }, + { + "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": "a92636787e54af0c51324a36241448d5" + }, + { + "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": "7d1d9552c124fefceb422aba6974b77d" + }, + { + "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": "53d3af38ec5f799fc6cefba51d6df116" + }, + { + "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": "a9aaf3ca88f0c54b7fbe36f82809e4d8" + }, + { + "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": "f1bec15df95f8016ec05a00aa5757e17" + }, + { + "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": "90d6619835fdc714fe255d6acecdb525" + }, + { + "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": "5cf34bb88eb08d784176c578855abaaa" + }, + { + "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": "faf662a6ac436baba56dde8f8c78fc8c" + }, + { + "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": "041e0080627f03977d1dca4d4445abcd" + }, + { + "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": "111dd04d6854fdf8574c72f346457f5a" + } + ] +} \ No newline at end of file