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": 3277594624.0, + "BitsPerParam": 3.6176423550341132 + }, + "records": [ + { + "dataPath": "params_shard_0.bin", + "format": "raw-shard", + "nbytes": 54001664, + "records": [ + { + "name": "lm_head.q_weight", + "shape": [ + 32768, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 54001664, + "byteOffset": 0 + } + ], + "md5sum": "122f33ee6ade904f4a82c963b4cd7eb6" + }, + { + "dataPath": "params_shard_1.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": "457b2d4ecec87d6dd48d116ab972c68c" + }, + { + "dataPath": "params_shard_2.bin", + "format": "raw-shard", + "nbytes": 33226752, + "records": [ + { + "name": "lm_head.q_scale", + "shape": [ + 32768, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 0 + }, + { + "name": "model.layers.22.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 6750208 + }, + { + "name": "model.layers.22.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 6758400 + }, + { + "name": "model.layers.22.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 30285824 + } + ], + "md5sum": "a02196763403ab5675d39d26e83a2de4" + }, + { + "dataPath": "params_shard_3.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": "dc7998f7968c6d3d0661789fb7505ba8" + }, + { + "dataPath": "params_shard_4.bin", + "format": "raw-shard", + "nbytes": 32391168, + "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.23.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5914624 + }, + { + "name": "model.layers.23.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 5922816 + }, + { + "name": "model.layers.23.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 29450240 + } + ], + "md5sum": "2e85b17486ceb440253f781767b2c58b" + }, + { + "dataPath": "params_shard_5.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": "248956079f00633c9ee6e0873f30a078" + }, + { + "dataPath": "params_shard_6.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": "183938cda8f5995c3b31da96f0baf4da" + }, + { + "dataPath": "params_shard_7.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": "e961b0578cecee5acf9618ee839a8258" + }, + { + "dataPath": "params_shard_8.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": "35566b2b53a99e8aea0abef836ee620b" + }, + { + "dataPath": "params_shard_9.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": "2077131b752bfe56e4f9f8b5c8025550" + }, + { + "dataPath": "params_shard_10.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": "5ddbea2b7566c8186d0cd729215c6a8b" + }, + { + "dataPath": "params_shard_11.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": "7a1f26d919d4fab135fc9d7bffec902b" + }, + { + "dataPath": "params_shard_12.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": "c684b02ea298fc50c7011ca3fd8a3219" + }, + { + "dataPath": "params_shard_13.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": "3a57d9584fb055287f1f462668d64d0b" + }, + { + "dataPath": "params_shard_14.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": "98a191fcb0fc7330a79e9ecd8117f9c5" + }, + { + "dataPath": "params_shard_15.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": "4a03fcf85f65b0032272e8dc836c3828" + }, + { + "dataPath": "params_shard_16.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": "e8750f8d6702420cabd616dd7630e29c" + }, + { + "dataPath": "params_shard_17.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": "87bf9ae04c1425787771405d929bf422" + }, + { + "dataPath": "params_shard_18.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": "9b481dd10faee1bff506c7db61fa4bd0" + }, + { + "dataPath": "params_shard_19.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": "c331d181d0843928946ecdccc45a53b7" + }, + { + "dataPath": "params_shard_20.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": "7943d8afbc9737e3487871921198480f" + }, + { + "dataPath": "params_shard_21.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": "f8998a9609f495b337a895e8b6ed11f0" + }, + { + "dataPath": "params_shard_22.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": "d879d8b307f8794696fd52ff62929590" + }, + { + "dataPath": "params_shard_23.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": "eb602602e6b8c44fd809b85e48d6af3b" + }, + { + "dataPath": "params_shard_24.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": "df9bca61d6e04ba1b5337ce24b70055f" + }, + { + "dataPath": "params_shard_25.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": "8ef7245223eced6afdcf1c83a20f382c" + }, + { + "dataPath": "params_shard_26.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": "7ac6438353ebacd6686d19fb6df4c7be" + }, + { + "dataPath": "params_shard_27.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": "2aa5b34137bb66670d44a8de9e9093ef" + }, + { + "dataPath": "params_shard_28.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.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.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": "603fdc8741bc74ded754ccdb667e8d1d" + }, + { + "dataPath": "params_shard_29.bin", + "format": "raw-shard", + "nbytes": 54001664, + "records": [ + { + "name": "model.embed_tokens.q_weight", + "shape": [ + 32768, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 54001664, + "byteOffset": 0 + } + ], + "md5sum": "39818e7ee373631ff8e360d2e27076ce" + }, + { + "dataPath": "params_shard_30.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": "92b259288fba53b4cc6dec95f4925f93" + }, + { + "dataPath": "params_shard_31.bin", + "format": "raw-shard", + "nbytes": 31666176, + "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.embed_tokens.q_scale", + "shape": [ + 32768, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 24907776 + }, + { + "name": "model.layers.0.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 31657984 + } + ], + "md5sum": "4807e5b3787217c5258f94c067dfe525" + }, + { + "dataPath": "params_shard_32.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": "e8fc122eb0c6c731e5a4c7214e95c7ac" + }, + { + "dataPath": "params_shard_33.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": "4a271ab3b530450b78af6a3a4367fe22" + }, + { + "dataPath": "params_shard_34.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": "5f8ee82031527423ecded72e32fbc9b7" + }, + { + "dataPath": "params_shard_35.bin", + "format": "raw-shard", + "nbytes": 30789632, + "records": [ + { + "name": "model.layers.0.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 0 + }, + { + "name": "model.layers.0.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 2940928 + }, + { + "name": "model.layers.0.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 8847360 + }, + { + "name": "model.layers.0.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 8855552 + }, + { + "name": "model.layers.0.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 18980864 + }, + { + "name": "model.layers.0.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 20246528 + }, + { + "name": "model.layers.0.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 26996736 + }, + { + "name": "model.layers.1.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + }, + { + "name": "model.layers.1.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 27848704 + } + ], + "md5sum": "a73239df003d3bb630931cb8a2000b30" + }, + { + "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": "b83399c009b98b6995f396c9d8a37852" + }, + { + "dataPath": "params_shard_37.bin", + "format": "raw-shard", + "nbytes": 30806016, + "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.10.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 24899584 + } + ], + "md5sum": "431a52b5f50f19a5410d602d9817443c" + }, + { + "dataPath": "params_shard_38.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": "1b62f077f35104358012acf676243f18" + }, + { + "dataPath": "params_shard_39.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": "9f2b96282e524d6d901206dddb637bb0" + }, + { + "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.2.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.2.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.2.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.2.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "d89331394c3da72a4f57d141f4997781" + }, + { + "dataPath": "params_shard_41.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": "350adaba7863243622818aba81205832" + }, + { + "dataPath": "params_shard_42.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": "d19dd04e6ac848eaa0581b63e8a44f0c" + }, + { + "dataPath": "params_shard_43.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.2.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.2.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.2.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.2.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.3.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.3.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.3.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.3.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "a94f31aed478a6db2936dda13755a649" + }, + { + "dataPath": "params_shard_44.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": "076660aac9e7eb14278cdbd98ffefc63" + }, + { + "dataPath": "params_shard_45.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": "a8939b676b7dc03a3e8065776f2d72dd" + }, + { + "dataPath": "params_shard_46.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.3.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.3.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.3.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.3.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.4.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.4.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.4.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.4.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "b762de4d6c23badab59cc080e8779783" + }, + { + "dataPath": "params_shard_47.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": "3a225eff159b331810457421e04aed05" + }, + { + "dataPath": "params_shard_48.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": "d78e60e10597651c3abbdc60b278a446" + }, + { + "dataPath": "params_shard_49.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.4.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.4.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.4.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.4.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.5.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.5.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.5.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.5.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "2c53467a401201ae0a1da0eb9a81d17b" + }, + { + "dataPath": "params_shard_50.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": "849546a143464213a854ed38453ad7ab" + }, + { + "dataPath": "params_shard_51.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": "ed2608e9375aaf87961004ed411baa23" + }, + { + "dataPath": "params_shard_52.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.5.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.5.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.5.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.5.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.6.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.6.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.6.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.6.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "a37b0fe23d3b7feb34c5cbd1b3145a34" + }, + { + "dataPath": "params_shard_53.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": "aad42a07d29284c71a3adc3e37ce41ab" + }, + { + "dataPath": "params_shard_54.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": "ba8938264df2ff855ed5e9b4afc887ec" + }, + { + "dataPath": "params_shard_55.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.6.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.6.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.6.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.6.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.7.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.7.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.7.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.7.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "27cdb4da876e1eb696895b7f646b2dc9" + }, + { + "dataPath": "params_shard_56.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": "ef4775e2ae2a14e1f82d033d3edca4fb" + }, + { + "dataPath": "params_shard_57.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": "fb586bdba5d3659d98a3290145c6006f" + }, + { + "dataPath": "params_shard_58.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.7.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.7.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.7.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.7.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.8.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.8.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.8.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.8.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "2f87e4721ad1e021cc057fc6f0b7ac62" + }, + { + "dataPath": "params_shard_59.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": "b5bec6a0a3153276a1e3354ee9664f31" + }, + { + "dataPath": "params_shard_60.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": "1af06f23ed6c0629c3bfde3982f2e0d1" + }, + { + "dataPath": "params_shard_61.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.9.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.9.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.9.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.9.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "7865e89e1161b671ee2635dcbd6a33e8" + }, + { + "dataPath": "params_shard_62.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": "7ef60622195db580ff382599687e1910" + }, + { + "dataPath": "params_shard_63.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": "17f5e1a2ace9b6c835574afcd4ba3d15" + }, + { + "dataPath": "params_shard_64.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": "a105a4d396c5fcf889e2f4e81b55ac39" + }, + { + "dataPath": "params_shard_65.bin", + "format": "raw-shard", + "nbytes": 30806016, + "records": [ + { + "name": "model.layers.9.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.9.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.9.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.9.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.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21934080 + }, + { + "name": "model.layers.11.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21942272 + }, + { + "name": "model.layers.11.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 21950464 + }, + { + "name": "model.layers.11.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 24891392 + }, + { + "name": "model.layers.11.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 30797824 + } + ], + "md5sum": "4c773a05e45174f2f6e43f2ee7677b88" + }, + { + "dataPath": "params_shard_66.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": "9111827c3a8388b2f35daadce0f2dc01" + }, + { + "dataPath": "params_shard_67.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": "c5d446bd49ad9d31d2ad1e43dad85202" + }, + { + "dataPath": "params_shard_68.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": "b2ea589338ceb0113f1639b53fcf884b" + }, + { + "dataPath": "params_shard_69.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": "5ecf63d56c145868dd41629746a46f1b" + }, + { + "dataPath": "params_shard_70.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": "5224e02bcdd0c3b21b5950e1561b785f" + }, + { + "dataPath": "params_shard_71.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": "8a201e160733267ccde68aba05382afa" + }, + { + "dataPath": "params_shard_72.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": "daf7a54bf37ffeac4ed70492a7fc5306" + }, + { + "dataPath": "params_shard_73.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": "74c80091daee7fa500d58017b53913e5" + }, + { + "dataPath": "params_shard_74.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": "dcac29d93a75f264d730292b5ee9bb79" + }, + { + "dataPath": "params_shard_75.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": "c6c9ee1f54ea0051855d5063225fdda1" + }, + { + "dataPath": "params_shard_76.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": "a92bda71aa96c69f7e43fd2abb463da3" + }, + { + "dataPath": "params_shard_77.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": "48fcfadb87f826d3b00a2da5ad9b6119" + }, + { + "dataPath": "params_shard_78.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": "6465f65a6e154c22a3605628278bedbf" + }, + { + "dataPath": "params_shard_79.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": "f0167392b57604862d126d00f3e0d425" + }, + { + "dataPath": "params_shard_80.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": "4031e9c96945a01b789f686ffc4f21e4" + }, + { + "dataPath": "params_shard_81.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": "84c082ea5b0a9f829a89fb3318fc41f6" + }, + { + "dataPath": "params_shard_82.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": "f0fd0b2d5a2dbf3c435d0abc485042f4" + }, + { + "dataPath": "params_shard_83.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": "0951eee7cfb8bd2ff82da99111df52e8" + }, + { + "dataPath": "params_shard_84.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": "cf59e3fd536d53b8ff6eb207fe93a26f" + }, + { + "dataPath": "params_shard_85.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": "24e95dcc422606e49cf67a7812bb25d8" + }, + { + "dataPath": "params_shard_86.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": "e3f1d879e1c7e47625fb435065b93bdb" + }, + { + "dataPath": "params_shard_87.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": "b77af82ba2ebe3d740e7b60df1ec7a32" + }, + { + "dataPath": "params_shard_88.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": "6511559a7ddeabccd91f39fecdbbcbd9" + }, + { + "dataPath": "params_shard_89.bin", + "format": "raw-shard", + "nbytes": 27848704, + "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.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.19.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.19.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.19.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "a4c8551276e80995af1ed62840464b9f" + }, + { + "dataPath": "params_shard_90.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": "ef2cf9fd5b18612f2349d985b982c43e" + }, + { + "dataPath": "params_shard_91.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": "39165608ca2ad37543f764539bf9a168" + }, + { + "dataPath": "params_shard_92.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.19.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.19.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.19.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.19.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.20.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.20.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.20.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.20.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "c1472b45fbb7a42c9f2e77c7d137226f" + }, + { + "dataPath": "params_shard_93.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": "de2108b3810014ff200b367b791ea9df" + }, + { + "dataPath": "params_shard_94.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": "cddbb914b92713df17b8891709abfd56" + }, + { + "dataPath": "params_shard_95.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.20.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.20.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.20.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.20.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.21.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.21.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.21.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.21.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "6a1b7a4044cec715db37d3a9ec396458" + }, + { + "dataPath": "params_shard_96.bin", + "format": "raw-shard", + "nbytes": 30375936, + "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.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.21.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.22.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 18984960 + }, + { + "name": "model.layers.22.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 29110272 + } + ], + "md5sum": "4a8081c15e364f8393973cc815178c36" + }, + { + "dataPath": "params_shard_97.bin", + "format": "raw-shard", + "nbytes": 7593984, + "records": [ + { + "name": "model.layers.22.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 0 + }, + { + "name": "model.layers.22.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 6750208 + } + ], + "md5sum": "b5e2036f08b550acb20f39f7dc6cb6bf" + } + ] +} \ No newline at end of file