{ "metadata": { "ParamSize": 485, "ParamBytes": 18982125568.0, "BitsPerParam": 4.500270809152499 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "lm_head.q_weight", "shape": [ 32000, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "6a3961d8baf7dcc4f7f5ee3d7435792c" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.41.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "8af88fce638e42d26743cef41429396f" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.42.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "f3c6055d6a8a7d56f5d31b7eb36ec5ca" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 27705344, "records": [ { "name": "lm_head.q_scale", "shape": [ 32000, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 0 }, { "name": "model.layers.41.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 16384000 }, { "name": "model.layers.41.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 16400384 }, { "name": "model.layers.41.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 27672576 }, { "name": "model.layers.42.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 27688960 } ], "md5sum": "adc195bb33c3b575f9025a93d5149eab" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.42.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "b267a37c130bdb35b88f464a42e12855" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.42.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "9781c037099f489344aeb5f3b1a3f613" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.42.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "015425bb4105a727cf16bd44458eadaa" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.42.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "12aae4a498d7ff3666c7ea4f35b7ad9f" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.43.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "88894a5af7d6525eab0f9424d922fc17" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.43.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "676191fcabd48a73d613b984bdf769ca" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.43.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "754cbeabfa806fe79966226fc4e4d2ff" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.43.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "e8d1712a4aa91eedf9e6da9efb196247" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 32030720, "records": [ { "name": "model.layers.42.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.42.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.42.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 11288576 }, { "name": "model.layers.42.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 16531456 }, { "name": "model.layers.43.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.43.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 20742144 }, { "name": "model.layers.43.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 32014336 } ], "md5sum": "b473d049da41459ca82e12b5a70f60f7" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.43.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "b00151cf327487c2f01c3d953dfe0106" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.44.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "51082b052869ee1381fc6abf4ed101f4" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.44.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "c5714086a28566338eda3c8531a6178e" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.44.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "79294efbe7fe994be6276576288cce1c" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.44.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "0f040a277d2eae183e790861f9e3469a" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.44.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "5b35f7dea56aaf679f4bab1840b1488a" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.45.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "99dd8dbd87b3d045ac55f0d6c8038d0f" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 30195712, "records": [ { "name": "model.layers.43.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.43.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.44.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.44.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 9453568 }, { "name": "model.layers.44.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.44.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 20742144 }, { "name": "model.layers.44.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 25985024 }, { "name": "model.layers.45.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30179328 } ], "md5sum": "f68fddd5b25217f193688cd6f39f3812" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.45.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "322358a85ae2f8be894b23809b4be7fa" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.45.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "b94d3b73e1c75e9b8340c936d9ea0393" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.45.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "2ccaae95988367f74ed173ee685a743c" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.45.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "17976e14b99e7672077022e649a3bdbe" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.46.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "9741d2fd77698c6f3ed854817202e277" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.46.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "306276897839d1c6dcaa4e99bb8dbb46" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.46.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "3ef80fc8b2e72ff1a28af8c5e6ad96eb" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.46.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "ee34644a9fca35aabf77ccf315b027cc" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 32030720, "records": [ { "name": "model.layers.45.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.45.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.45.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 11288576 }, { "name": "model.layers.45.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 16531456 }, { "name": "model.layers.46.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.46.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 20742144 }, { "name": "model.layers.46.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 32014336 } ], "md5sum": "02870401aae4ef127f7dc3060d995a49" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.46.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "8b6638fa17e99581a8a80d5bfe817cc4" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.47.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "4d60a0116324eef7e64fa3f5d48f763f" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.47.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "43ea4194d21438f66f37e46f2cd7c178" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.47.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "f57f0c60699a52a38aba7b9798f1c6f1" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.47.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "bba85265331613befd966594d2912d7d" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.47.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "5c0f4482a7bd3a549fa580765ae6982d" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 32000, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "648c929032c00b32893d19a3fff1464d" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 30195712, "records": [ { "name": "model.layers.46.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.46.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.47.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.47.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 9453568 }, { "name": "model.layers.47.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.47.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 20742144 }, { "name": "model.layers.47.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 25985024 }, { "name": "model.norm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30179328 } ], "md5sum": "5375e8ab051c22529af04bde47d3d084" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "ca4e4c73317c2b353cbd2d21a49d31f1" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "1035f3dd6c4dffdb0ff63de527d2e739" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "af801dfa23c7cf3b68659c24842a797c" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "d89fcc634d61a65df262ad9a8e366fe0" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "0d550d91d9e4bcd1f0e21118dd0ebdd4" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 32931840, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 32000, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 0 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 16384000 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 16400384 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 27672576 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 27688960 } ], "md5sum": "8887cb83dcb6a6e8141d81e2c3356831" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "97375e980f3cb0785da86b02f2d06014" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "85488011862effe4d65c27ce953d0961" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "20f03534d81d19cc07d3449c8bd46850" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "cb6e74f610f2661784cc7c161e39e8bc" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c0197e3dc97592bc913d6fe34f597e1b" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "f6d850bc0769a83c92d12b074c056c88" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 24952832, "records": [ { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 4210688 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15482880 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 15499264 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 20742144 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24936448 } ], "md5sum": "669f9b2d21e6c518b250bc31cc6305fa" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "9ed53535e0d944c80caf2b01604a7e68" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "58f7ef888092aaf7f58594ffb7d9bf2d" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "c4ef6e85016a4453cae499ddd51b8117" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "6d84a2db4f93000151fe23030ef0f73c" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "f359cf65adb95ed6720617e06374cb9d" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "f0c94f7618f7354448258c71c200844f" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "b9637f75314e3b3cd2e01f48866bb4d6" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "599cac37a3de05f5f94bd8cd26beb933" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 32030720, "records": [ { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 11288576 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 16531456 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 20742144 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 32014336 } ], "md5sum": "1c839c82129b4dbb517fcf09abb77dab" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c3a57ac8b609106f406e77ffd2284e09" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "f383eee03bed97ae42c8521d604c31ef" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "8118e5853d01cc3b56ed18bb37a4f3d3" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "d365cce3b4c909994431148e358b016f" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "eb92c32f9f99dbde94f72c69a87490f5" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "38dc7181d0052abc3fac11c18fe17349" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "52243b0cd3247b2dc26469a54efbfe29" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 30195712, "records": [ { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 9453568 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 20742144 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 25985024 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30179328 } ], "md5sum": "3ad5224af9135bfebc85c0e9a39f71ac" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "fb30cb367f01f4479bc71b3a6b5f2661" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "07355555777016484c6576ec6a45b8a4" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "c2401c533fab8148a8f05de543672358" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "596d8ec9292c319acfb7cf950f3ede6d" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "98e94912349893804301a7a2479188a4" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "d9d1237918c880dcfcb87daa007c6614" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "1eaa25f83f993a7e62a1ed97a23c21e7" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "0b8a74862caa75d3ea33c37a2d2d5747" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "469a8a164dba98e8d3d6959bf9d64618" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 30179328, "records": [ { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 11288576 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 16531456 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 20725760 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 25968640 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30162944 } ], "md5sum": "1c47c473188fffad68209c82708012c6" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "aae3b1628d9ee0215a60eaecbf98670c" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "aa327366ecc6a08ea4656fd14dae2e20" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "573476cd329ae9c55de3d8d5000d56d4" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "fb4f1cb0ebb50cd83f00f6fd79a34293" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "221ef8cb435444d17313f21121fd518e" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "6b0d3df782bf0dd779a0b936816c90e0" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "fdb34b5da3cff12d2493c7260dc3ef7c" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "028d804d35668acb7aafad77e858a90b" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 32030720, "records": [ { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 11288576 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 16531456 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 20742144 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 32014336 } ], "md5sum": "a31e075e88aaccadf926663c173e10a2" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "e70f0eab6897a0b02960a40c58344f16" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "9736d556bd9bdf4a33f303affff087e0" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "33b6d3aa697c1d6a7a57770899981aa0" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "a4a93aa3fd6115431629bc1fcdc9b3c9" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "203cb46ee11bcca5172ed29fe4f63643" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "53179922287b2adba1dcc83a87fb0ed0" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "6c2d24a3cf6cd9af96a77cc2e27fb363" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "b8733b1c600f296f958b766409d37740" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "7b4ced24515f880b5354c25a9fa77e2e" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 30179328, "records": [ { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 9453568 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 20742144 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 25985024 } ], "md5sum": "1afdbc533906e4da1273ac6a10d5e039" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "6f26090ad4956c1a3528fc39386360be" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "5b42216438719543f67e93897c0a6afd" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "57285402de1338b5d1d7ebf34748fd6d" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "2dc8eef0256bf48acfe0acc8d0fb78e6" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "97ad6a56ec7ae08d00e56b2f459dcef0" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "8f28e494e32bef598871b4182b66c8be" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 32047104, "records": [ { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 9453568 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20742144 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 20758528 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 32030720 } ], "md5sum": "464a9f5e89af900c15f3beef33b3e460" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "dfbc2f467d6faac10a7e195fa15c6552" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "74e84654da47c33e61102988c9658725" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "c33f24c57319f87046141b81d07ae2d2" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "b004d65ad7ecbda5a6941ae49ab62e50" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "9f87d43d9534975f11858ab5b0537e50" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "fcb4362a9cfccd775436dfc218348038" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "5c43ad2ede3fe307136949cbe43b1801" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 30195712, "records": [ { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 9453568 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 20742144 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 25985024 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30179328 } ], "md5sum": "fa412234d0eb0657cc3f8a55ce9b0cc2" }, { "dataPath": "params_shard_112.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "d35706626d7779edffd63a8e6a2ec9d7" }, { "dataPath": "params_shard_113.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "1440f6ac87cfe78ad5e13d7e8e0544d2" }, { "dataPath": "params_shard_114.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "a826e15b187e8de738b08e94ff45bbb7" }, { "dataPath": "params_shard_115.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "066d1f29133ec6a22876c4050766d20a" }, { "dataPath": "params_shard_116.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "490957454e590e3511e5a831ef4ca440" }, { "dataPath": "params_shard_117.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "f7380f7e8e0fb2c1b7ff363d3b6048e1" }, { "dataPath": "params_shard_118.bin", "format": "raw-shard", "nbytes": 32047104, "records": [ { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 11288576 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 16531456 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 20742144 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 32014336 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 32030720 } ], "md5sum": "2ac754e37310e7e22a79369272f6f040" }, { "dataPath": "params_shard_119.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "07cd15ffe7a388c53d1e54b8fb123c47" }, { "dataPath": "params_shard_120.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "e4672afc365aa7ac279a5c173f81792d" }, { "dataPath": "params_shard_121.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "4a607515437238780de566d9d1a8c625" }, { "dataPath": "params_shard_122.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "8287b8b82b32dbe917b0a01c4f6a6580" }, { "dataPath": "params_shard_123.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "643eed3d286b21477265988b0b385cc7" }, { "dataPath": "params_shard_124.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "27608c8512ffed8f3e89a631c31544af" }, { "dataPath": "params_shard_125.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "07bbc56832942f8d81a795b1c376c51a" }, { "dataPath": "params_shard_126.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "6164012d838e0950267cc9659be4604f" }, { "dataPath": "params_shard_127.bin", "format": "raw-shard", "nbytes": 32030720, "records": [ { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 11288576 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 16531456 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 20742144 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 32014336 } ], "md5sum": "e36cd1afc3c9b77362a5b02d17bdde66" }, { "dataPath": "params_shard_128.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "5c846fd80ac96bed133dca569a2c72a0" }, { "dataPath": "params_shard_129.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "6436e97c88ed4361242bda3a2ff841c1" }, { "dataPath": "params_shard_130.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "0d21a265391dc35014f99380ce0cd80e" }, { "dataPath": "params_shard_131.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "6648e465eb974b72dee1a5e79a5a9c1a" }, { "dataPath": "params_shard_132.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "94f8e27af3b4151c44ae4443ec1cb7aa" }, { "dataPath": "params_shard_133.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "a0e17a216eeb99a45e3bff561ce1f558" }, { "dataPath": "params_shard_134.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "36747f14fb60bd15a2acc9b013f680b3" }, { "dataPath": "params_shard_135.bin", "format": "raw-shard", "nbytes": 30195712, "records": [ { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 9453568 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 20742144 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 25985024 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30179328 } ], "md5sum": "646e9b2d1b7c1cd8efabe7082b36b1c8" }, { "dataPath": "params_shard_136.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "01e218c86e081e85514abbf3fa14202a" }, { "dataPath": "params_shard_137.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "fe6a693d7883a6229ae8d849232c4b52" }, { "dataPath": "params_shard_138.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "46fe669eff45287515a83e9a09b585a1" }, { "dataPath": "params_shard_139.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c353fd32ef4c28b95446b40ea7108b24" }, { "dataPath": "params_shard_140.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "be387268c96eff2e7e12a53abd611af9" }, { "dataPath": "params_shard_141.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "f649f66e527075c2375ff1623ccfab23" }, { "dataPath": "params_shard_142.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "84199583d381c8a22417e17b3824e319" }, { "dataPath": "params_shard_143.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.18.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "95bda682007dfb78356fa835124d6f80" }, { "dataPath": "params_shard_144.bin", "format": "raw-shard", "nbytes": 32030720, "records": [ { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 11288576 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 16531456 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 20742144 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 32014336 } ], "md5sum": "75929d3ee4642763ac5e7f78a77d4e41" }, { "dataPath": "params_shard_145.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "6ec0344fa2863b208a38085c72fbe59a" }, { "dataPath": "params_shard_146.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "cc6e1b65fc0ab84635d7e750bf9f4667" }, { "dataPath": "params_shard_147.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "08d1f691e6f8d25e11c2a89a5c82cd18" }, { "dataPath": "params_shard_148.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "d9bfc6e87943c5b1131310a5a6378035" }, { "dataPath": "params_shard_149.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.19.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "237cf26aa0e782322686162accb9276b" }, { "dataPath": "params_shard_150.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "bb99da95ad995c1b256ccd8bb0eb2730" }, { "dataPath": "params_shard_151.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "e8ca24a2508007c7fafef654d65650b8" }, { "dataPath": "params_shard_152.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "51e1ad06a1783bf2e4c8614e612eb380" }, { "dataPath": "params_shard_153.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.20.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "92c40c6ccca6b03d9e6f72167d00d8cb" }, { "dataPath": "params_shard_154.bin", "format": "raw-shard", "nbytes": 30179328, "records": [ { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 9453568 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 20742144 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 25985024 } ], "md5sum": "9a99367969bad6fd48990f8d096ab74a" }, { "dataPath": "params_shard_155.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c8707636ea31399faa2aedee54da573c" }, { "dataPath": "params_shard_156.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "89f241392de9950d0893cbe87574aa09" }, { "dataPath": "params_shard_157.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "260413341b21774f49712de5b23a75ef" }, { "dataPath": "params_shard_158.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "00ea4438dcb333bb6f9e651a1c25b21f" }, { "dataPath": "params_shard_159.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "36ad8d5a924753db0c8e1277b1cf2c71" }, { "dataPath": "params_shard_160.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.21.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "f7983c26028f8873e4d5608b3d4f7421" }, { "dataPath": "params_shard_161.bin", "format": "raw-shard", "nbytes": 32047104, "records": [ { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 9453568 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20742144 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 20758528 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 32030720 } ], "md5sum": "3207e51d78ba7333ed07de75fe288c3f" }, { "dataPath": "params_shard_162.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "717dba9912b3be5a448f445e76e3ad03" }, { "dataPath": "params_shard_163.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "c026c6bd9052f0b8ba8f524d3dfd6016" }, { "dataPath": "params_shard_164.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "925e87e94c9961f5be25060606c0e9f1" }, { "dataPath": "params_shard_165.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "2af785e79601b27a8318986520e6d6b2" }, { "dataPath": "params_shard_166.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.22.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "fc51decdb8ccec292c15c89ac61cc651" }, { "dataPath": "params_shard_167.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c1b74fbfafff745c8cd042f46b0c5348" }, { "dataPath": "params_shard_168.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "14d7b4896981714e90c8cb2f05d26c7d" }, { "dataPath": "params_shard_169.bin", "format": "raw-shard", "nbytes": 30195712, "records": [ { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 9453568 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.22.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 20742144 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 25985024 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30179328 } ], "md5sum": "296529dc9d5f50ecb704f025b0d6f253" }, { "dataPath": "params_shard_170.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "63f58bd69cfd1d3609626e9db4c7d994" }, { "dataPath": "params_shard_171.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "0e0c60cdde5fe341f5d89e284a67a278" }, { "dataPath": "params_shard_172.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.23.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "673868628e2e054c58828c02f1d6d027" }, { "dataPath": "params_shard_173.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "258404dc3abf12215bc3a1c29869f0f1" }, { "dataPath": "params_shard_174.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "79ba4ab8ebf4c6921d69b46ea9459b8a" }, { "dataPath": "params_shard_175.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "f035ef7a23566e1cf84b492a533be958" }, { "dataPath": "params_shard_176.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "c85e676f462fcfb197850c15cfad3042" }, { "dataPath": "params_shard_177.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.24.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "dc3d028dc04f3adf14a0615d59bd0f58" }, { "dataPath": "params_shard_178.bin", "format": "raw-shard", "nbytes": 32030720, "records": [ { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.23.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 11288576 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 16531456 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 20742144 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 32014336 } ], "md5sum": "ca192b03c3777722b55944174ae5e82e" }, { "dataPath": "params_shard_179.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "dcc20711c60061d184113b78ab18a2fd" }, { "dataPath": "params_shard_180.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "d8816f2cc9ca897886f43f4109a459a2" }, { "dataPath": "params_shard_181.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "5a2a0f8db7e6de709eed90c8b9706610" }, { "dataPath": "params_shard_182.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "34bb14d467730a038c561902caf0a571" }, { "dataPath": "params_shard_183.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.25.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "9f33dc3daa41252713f1364065494768" }, { "dataPath": "params_shard_184.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "10c1bf707ee51ce966169375174d8b47" }, { "dataPath": "params_shard_185.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "e17d51a66e17ee1b1ea95570d0fdb7b6" }, { "dataPath": "params_shard_186.bin", "format": "raw-shard", "nbytes": 30195712, "records": [ { "name": "model.layers.24.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 9453568 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.25.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 20742144 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 25985024 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30179328 } ], "md5sum": "5d359606121c22b738ccb19130e2404c" }, { "dataPath": "params_shard_187.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "13496e9396c00cac7870a0756919fc4f" }, { "dataPath": "params_shard_188.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "89d00563f42e1214a6bfdbc314ff7c19" }, { "dataPath": "params_shard_189.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.26.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "30cb9797efae48faa834880fbb6976ca" }, { "dataPath": "params_shard_190.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "ecdbc980feb7d8433b4fe88714e059b6" }, { "dataPath": "params_shard_191.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "7086f6b6d50f75c6c21dbd22592289f0" }, { "dataPath": "params_shard_192.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "ae2a45845712b212e84dbd7d8ac73ef3" }, { "dataPath": "params_shard_193.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.27.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "c99839536d190e99c109acd4b4500ded" }, { "dataPath": "params_shard_194.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "e335f69ee6410dd832b65d0131d07f11" }, { "dataPath": "params_shard_195.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "0ab86bd1b46433a686c281e86f44c8ce" }, { "dataPath": "params_shard_196.bin", "format": "raw-shard", "nbytes": 30179328, "records": [ { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.26.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 11288576 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 16531456 }, { "name": "model.layers.27.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 20725760 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 25968640 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30162944 } ], "md5sum": "aca54b5a9c515bc09e22329c469539ab" }, { "dataPath": "params_shard_197.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "a052cdd5773644f155e6d4f6f5541298" }, { "dataPath": "params_shard_198.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "27ad354545444531c225a84c98de9ec5" }, { "dataPath": "params_shard_199.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "bdd8d03b4224b103e78fde7756303dd2" }, { "dataPath": "params_shard_200.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.28.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "fc3bcce18ce42ed5d26c44d485eb7343" }, { "dataPath": "params_shard_201.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "ba8e00f30c6bed3e7d624fef03e694bc" }, { "dataPath": "params_shard_202.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "3232f905f75942e9009097e026731aee" }, { "dataPath": "params_shard_203.bin", "format": "raw-shard", "nbytes": 32047104, "records": [ { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11288576 }, { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 11304960 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 22577152 }, { "name": "model.layers.28.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 22593536 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 27836416 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 32030720 } ], "md5sum": "66869013450de32de17345a81fae4fdc" }, { "dataPath": "params_shard_204.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "093ad11b82c59c66d85977e4672bf43e" }, { "dataPath": "params_shard_205.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "289f6735490a5227ad9a46d19e7107da" }, { "dataPath": "params_shard_206.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.29.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "46a037203c323fa7f101d2af20292871" }, { "dataPath": "params_shard_207.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "a7ff0c9d8945f06e43126d79a494b9b6" }, { "dataPath": "params_shard_208.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "451504a15bc75b6a3a02b1d71093a111" }, { "dataPath": "params_shard_209.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "a04e6ee6d0f10e4d06b6c3e6f5c2c0d1" }, { "dataPath": "params_shard_210.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "6faa64910619e0ea87b0c7929c862d56" }, { "dataPath": "params_shard_211.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.30.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "2ce7a7dcaf91e85216dfee0555699d6d" }, { "dataPath": "params_shard_212.bin", "format": "raw-shard", "nbytes": 32030720, "records": [ { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.29.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 11288576 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 16531456 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 20742144 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 32014336 } ], "md5sum": "5cb04990ae097af6077e197165376014" }, { "dataPath": "params_shard_213.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "346bddc4b24e5dd9666a90b95ad831be" }, { "dataPath": "params_shard_214.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "e29adf0e9418d695decb617d611779b6" }, { "dataPath": "params_shard_215.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "fcad225335683da2b4d6c7dd1c42ba7a" }, { "dataPath": "params_shard_216.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "13727110ccc57c1e505cddd7522aa2dd" }, { "dataPath": "params_shard_217.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.31.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "a54223f15861a18622f0bf1b3f69e282" }, { "dataPath": "params_shard_218.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c33da83826a9f7f7921b62f9703a276d" }, { "dataPath": "params_shard_219.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.32.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "201f1d4fd28f39609ca18a725983f28c" }, { "dataPath": "params_shard_220.bin", "format": "raw-shard", "nbytes": 30195712, "records": [ { "name": "model.layers.30.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 9453568 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.31.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 20742144 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 25985024 }, { "name": "model.layers.32.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30179328 } ], "md5sum": "10e5bea8724a2ac40c48a3d95fcd02ee" }, { "dataPath": "params_shard_221.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "77106f5fda37e026412ade45e1ce2b32" }, { "dataPath": "params_shard_222.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "942afbf7e580a6ca7bf4f4127a7aed00" }, { "dataPath": "params_shard_223.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.32.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "5fe8fa24b469803d295e122c01d06677" }, { "dataPath": "params_shard_224.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.32.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "7afe25613ecee06d40c2df3c61eef8af" }, { "dataPath": "params_shard_225.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.33.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "b1f14f9cd823ec94b9fef79f51de5536" }, { "dataPath": "params_shard_226.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "cd61f3bbd1e08bfd19ab732374d9689c" }, { "dataPath": "params_shard_227.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "89138fb91540d6925b79b304e52c322a" }, { "dataPath": "params_shard_228.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.33.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "f07fd3fbcb798dd7ed9c969f02ce6eff" }, { "dataPath": "params_shard_229.bin", "format": "raw-shard", "nbytes": 32030720, "records": [ { "name": "model.layers.32.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.32.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.32.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 11288576 }, { "name": "model.layers.32.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 16531456 }, { "name": "model.layers.33.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.33.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 20742144 }, { "name": "model.layers.33.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 32014336 } ], "md5sum": "8762c621750c4c3637248b1251cd913e" }, { "dataPath": "params_shard_230.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.33.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "1986a51602ff4ed09925e9fa7d680942" }, { "dataPath": "params_shard_231.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "47e49a8c8f335e00334cac37fa0a7195" }, { "dataPath": "params_shard_232.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.34.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "b71033774138847d8adbd7723bf1eba1" }, { "dataPath": "params_shard_233.bin", "format": "raw-shard", "nbytes": 31981568, "records": [ { "name": "model.layers.33.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.33.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.34.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 9437184 } ], "md5sum": "dd37f29dd26093d855270025765a7b67" }, { "dataPath": "params_shard_234.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.34.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "b81080e8f9eacad079a613fccf157196" }, { "dataPath": "params_shard_235.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.34.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "e320400058b031c4fa14d1096c3dd90a" }, { "dataPath": "params_shard_236.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.35.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "22d705fc46d8a990d44786466ae2c858" }, { "dataPath": "params_shard_237.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "5ac035746b826dec3b0b6a755f3afb61" }, { "dataPath": "params_shard_238.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "1adf88aa1de1954c16ecddb930a3c713" }, { "dataPath": "params_shard_239.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.35.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "aa8a5f8263e3a46a552c60b5e8727970" }, { "dataPath": "params_shard_240.bin", "format": "raw-shard", "nbytes": 32047104, "records": [ { "name": "model.layers.34.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.34.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.34.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.34.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 9453568 }, { "name": "model.layers.34.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.35.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20742144 }, { "name": "model.layers.35.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 20758528 }, { "name": "model.layers.35.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 32030720 } ], "md5sum": "4e06b8d380b324be4e998f3d7c2658d4" }, { "dataPath": "params_shard_241.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.35.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "209ad342d16e357467aee471adb2e959" }, { "dataPath": "params_shard_242.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.36.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "a490551ba7dcc9929fcf0826f2e2985e" }, { "dataPath": "params_shard_243.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "013ff80c74f5ed16f9d83054e51a8449" }, { "dataPath": "params_shard_244.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "550af92474dad31982de8442116d2f56" }, { "dataPath": "params_shard_245.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.36.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "839c8dc519020fed6e9312865a31575a" }, { "dataPath": "params_shard_246.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.36.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "dd5705abb6d8f8bc627b5686c80553ef" }, { "dataPath": "params_shard_247.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.37.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "432e81b71a6357fe99bfd9faa9b41d84" }, { "dataPath": "params_shard_248.bin", "format": "raw-shard", "nbytes": 30195712, "records": [ { "name": "model.layers.35.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.35.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.36.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.36.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 9453568 }, { "name": "model.layers.36.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.36.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 20742144 }, { "name": "model.layers.36.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 25985024 }, { "name": "model.layers.37.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30179328 } ], "md5sum": "a58b80c7817d25ff15305fb2f09e1202" }, { "dataPath": "params_shard_249.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.37.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "b6b56a937bf02d9e596ce393c35d011c" }, { "dataPath": "params_shard_250.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.37.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "71c6f3bd9f3e66220809c85320722da9" }, { "dataPath": "params_shard_251.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.37.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "bf52656e09162ba2e9411ff064222916" }, { "dataPath": "params_shard_252.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.37.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c4912b00e20b5ee5d68d27205e3f6572" }, { "dataPath": "params_shard_253.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.38.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "598489438b339f3ca9e2aa8f55d43a4e" }, { "dataPath": "params_shard_254.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "1e7ed5a060e93152699292d61d6d6bc5" }, { "dataPath": "params_shard_255.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "0ac7081e98475690ebe36e42c6e5b455" }, { "dataPath": "params_shard_256.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.38.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "6d9bd8734d1a071b450330fcfe6933ae" }, { "dataPath": "params_shard_257.bin", "format": "raw-shard", "nbytes": 32030720, "records": [ { "name": "model.layers.37.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.37.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.37.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 11288576 }, { "name": "model.layers.37.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 16531456 }, { "name": "model.layers.38.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.38.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 20742144 }, { "name": "model.layers.38.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 32014336 } ], "md5sum": "00531291f9267a480773b88f9db44c37" }, { "dataPath": "params_shard_258.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.38.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "88fe8386c9f5d6730db9cebdee985258" }, { "dataPath": "params_shard_259.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.39.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "851cc2242001ddc0aaace47ea0caaedd" }, { "dataPath": "params_shard_260.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.39.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "08b7cf8ebadbebad1cf3411f29c5e03b" }, { "dataPath": "params_shard_261.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.39.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "2528fa320d0a91c76d7add34963f54ca" }, { "dataPath": "params_shard_262.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.39.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "36bc80dd3e8d8f75311d482dfed6c65d" }, { "dataPath": "params_shard_263.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.39.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "32e42b6f4948e7dfe2a7f6a3c7486cd4" }, { "dataPath": "params_shard_264.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.40.mlp.down_proj.q_weight", "shape": [ 8192, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "572ab8c1df5c7ea617e79c7cd6d6690a" }, { "dataPath": "params_shard_265.bin", "format": "raw-shard", "nbytes": 30195712, "records": [ { "name": "model.layers.38.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.38.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.39.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.39.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 9453568 }, { "name": "model.layers.39.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 20725760 }, { "name": "model.layers.39.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 20742144 }, { "name": "model.layers.39.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 25985024 }, { "name": "model.layers.40.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30179328 } ], "md5sum": "cc95cc05b7372041601a33f47ee5be9f" }, { "dataPath": "params_shard_266.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.40.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "363e4bcd201558f675b007e081b1ac35" }, { "dataPath": "params_shard_267.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.40.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "30f9f0d8739060f1a094f90b7596c32f" }, { "dataPath": "params_shard_268.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.40.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "85052e0b7526272e59326b87fcb01bdd" }, { "dataPath": "params_shard_269.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.40.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c722ae244bcc44cd66e3a5d6217dc2cc" }, { "dataPath": "params_shard_270.bin", "format": "raw-shard", "nbytes": 180355072, "records": [ { "name": "model.layers.41.mlp.gate_up_proj.q_weight", "shape": [ 44032, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 180355072, "byteOffset": 0 } ], "md5sum": "aa908d24efc594721c61e85b9937254c" }, { "dataPath": "params_shard_271.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.41.mlp.gate_up_proj.q_scale", "shape": [ 44032, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "b6abe29c77f3d6b2d4a40c7dbaa12557" }, { "dataPath": "params_shard_272.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.41.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "cabb8d033c415d27eaf2d67149d089e7" }, { "dataPath": "params_shard_273.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.41.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "f25f2eef4ae6c0942acf41539e952fb3" }, { "dataPath": "params_shard_274.bin", "format": "raw-shard", "nbytes": 30162944, "records": [ { "name": "model.layers.40.mlp.down_proj.q_scale", "shape": [ 8192, 688 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11272192, "byteOffset": 0 }, { "name": "model.layers.40.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11272192 }, { "name": "model.layers.40.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 11288576 }, { "name": "model.layers.40.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 16531456 }, { "name": "model.layers.41.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 20725760 }, { "name": "model.layers.41.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 25968640 } ], "md5sum": "c16ab83a90c0b482ad586f5c42dbb538" } ] }