{ "metadata": { "ParamSize": 805, "ParamBytes": 39688355840.0, "BitsPerParam": 4.356224340918386 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 525336576, "records": [ { "name": "lm_head.q_weight", "shape": [ 128256, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 525336576, "byteOffset": 0 } ], "md5sum": "8ce90b178d5b46d9b4d77a6b67793a12" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 65667072, "records": [ { "name": "lm_head.q_scale", "shape": [ 128256, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 65667072, "byteOffset": 0 } ], "md5sum": "398a4fc97e15c1489664474d216fba47" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 525336576, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 128256, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 525336576, "byteOffset": 0 } ], "md5sum": "ffbcf858e73d9dac33de1b4ac72fb338" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 65667072, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 128256, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 65667072, "byteOffset": 0 } ], "md5sum": "9442466073a3d40dc02751c3eadfa598" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "ac22ece93421b7579c689ceeb79f4dc8" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "a69365348b24a226098fb03979d55116" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "e3156866e9a4e0019bafd42f572e16d2" }, { "dataPath": "params_shard_7.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": "9a0e1bea7a75f971cf0fc55a5ff6f0f3" }, { "dataPath": "params_shard_8.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": "b00b5532dac9a7eb8608b3a194bb6925" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "07a444db1846b6752ec367612be9af2e" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "dc27ccba6b2931fba8398bad169c2da2" }, { "dataPath": "params_shard_11.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": "213176a88ba1e08147bc147dab6f0664" }, { "dataPath": "params_shard_12.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": "c735e175751a1acc72c4fbce2421c7ec" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 29392896, "records": [ { "name": "model.layers.0.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 0 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 16384 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14696448 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14712832 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19955712 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24150016 } ], "md5sum": "b03e6c109d055471097d921813c784be" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "d09a24cdb2c9b3c67802c5a95461d5bd" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "b29be27783399cfe15f7a7d5209c151f" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.1.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, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "72cdb5113190ee46ba3c6b6ac3b9b0ad" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "0264577d750c9a5718aae90ff3f7ed68" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "f4c50ad8b209da7411c58c5056298d7e" }, { "dataPath": "params_shard_19.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": "5bda62606f89ffb13e86a4f5dd9fb387" }, { "dataPath": "params_shard_20.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": "1d6931e681d9762874af16b823d1454c" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "60ac2b879726a25d0652366105a8563d" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "e9d927f977d8424b1b31814fdfa3ea10" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "386f90437b0c0478999473b5ceba6bf4" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "a2fb51da88511e54ede685fe2515669a" }, { "dataPath": "params_shard_25.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": "6c08d69296193e712bf6b93b8c7f8577" }, { "dataPath": "params_shard_26.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": "dcd25feed7ad6ca887cfd38973e7e950" }, { "dataPath": "params_shard_27.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": "96462960da7b26a1a0693108d0c7c4cf" }, { "dataPath": "params_shard_28.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": "fad87e6abd6faeaad13062b12d855441" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "b51a1c6715d6aab882618a33e9b832e3" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "f906842c5aa10fd2f862f9909ad727bf" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "13e713a701e38f79d845f9afbb49191f" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "541e78d29b504091c0ed3016cdee1549" }, { "dataPath": "params_shard_33.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": "8c28c1a5e6b4cfa18d7e35d8a9bff813" }, { "dataPath": "params_shard_34.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": "de7ac0d726c166d44198d84aae9dbc8e" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "30b822a172cea4f2f6184d3f87c1a9e6" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 28360704, "records": [ { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 18907136 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 24150016 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 28344320 } ], "md5sum": "94559f3e274bb81511b478cdd4ba21f4" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "52cf833d8cb099ac818489e1c02bbdc6" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "6fe91e03e045ac82922f764f22824dc4" }, { "dataPath": "params_shard_39.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": "f98d627aa2f62a25cba4c7b4f4b65475" }, { "dataPath": "params_shard_40.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": "86120d2be3bfdefece91b90ca97510f5" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "943626e262ca853dbf3fa601be854952" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "355cd6fa312be0db48b0ca2c9f5f62fd" }, { "dataPath": "params_shard_43.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": "6e55626cee800c7321c55dac6b134d02" }, { "dataPath": "params_shard_44.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": "4a3a50725bee3848b9500aec317c4bd1" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "fc82cc536e09416cb1df1370d210e454" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "68f3f9da0dc20bb5552e57c13461999b" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "52ad5fdd153c9aa340b93376168c2461" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "f91d93517388f4e70c2e6bf7f6980a22" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "dca14b6facaf63dbc1d78303a192bf4c" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "e3b10dc6455f3d2f14ebc7d7879a5c57" }, { "dataPath": "params_shard_51.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": "cf8e82b07033a94252a62ffea61115cf" }, { "dataPath": "params_shard_52.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": "7ff1346e5645ada88d6b9b3dde90c412" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "2f70eb4eb011368f87467511c008dd8d" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "7d4c3aa24c16704d7b7b5d51cd04cf15" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "5103b27a7555696555db4c6c26369d09" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "0969a147e6aee5afa8ac55da897892ba" }, { "dataPath": "params_shard_57.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": "a6957f0c74372c6ef1e9675cd388358c" }, { "dataPath": "params_shard_58.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": "3372ba84c775dd6ada3bb3638a85c05a" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "8bb09139d9a3c08511c2471ae55e4138" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "888b264656fee710f827531856f62690" }, { "dataPath": "params_shard_61.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": "007bac8c660bafd5d9df92e48987d692" }, { "dataPath": "params_shard_62.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": "3e20b1c891d36343b17aa4b03478d5c9" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "95d92ccbc5bf9bd0b8a1abbc145c48a5" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "f4d2c6d6cfa7df0ed9f5aef00672c745" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "ac785aa71aef35bf1166abba20608060" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "197e288efb898f061bc989f3060a4cee" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "d40a66ccb087bfa4c0c2191c86ba99f8" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "544b6236dd3ec078f7262a31c68f8824" }, { "dataPath": "params_shard_69.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": "1a6df62ec82413a525b557976f61e177" }, { "dataPath": "params_shard_70.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": "7409d0bd8f2b17b3f895afd5354dc3d0" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "44216786b954ed8cdc70352593f704a5" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "c84aa5c9b7adf95d61226a8a87f1daa1" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "64b0b87ebeafe3c861abebd9eaaf2458" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "c9a8bbc2b7fb4056551016f3af18cec6" }, { "dataPath": "params_shard_75.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": "26c9f636e95712ceb5a9408b0e12a47a" }, { "dataPath": "params_shard_76.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": "dbaf8e56e40e4c6ebf8c5bf5fa5e5e1b" }, { "dataPath": "params_shard_77.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": "e84d4ff46005d921b71842ac9aa41256" }, { "dataPath": "params_shard_78.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": "dc53824dfb11128df8a82269a804e06d" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "0cd07668ebe53ecf7f3062d1a519e667" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "0be881dd12eb1628cc66340257ec085f" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "9dc07e4c18eae8390046baf851e876f1" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "eccc8b8b9235f35f39dbb47aea566e2f" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "cbbde4c633a7cc79fa2c3eff84a0d36c" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "15860a995a9a0d1831d14ff492da46a6" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "58ee551093468a9801491d619a8b4261" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "77c5aa87342318fa1e2ec0fd9a548353" }, { "dataPath": "params_shard_87.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": "bf3a218801d8c95fa14be3b752c5f767" }, { "dataPath": "params_shard_88.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": "20ab142556c593382ed2e0d73d9f1fde" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "d5de22a9b0e00d12acd894687b052cff" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "7b2f1301ad4a0ac93a2c997248caf125" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "4a45542db749ad2f5f389a099be8c280" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "f7b5f84ed8f2c76436eef1a6ae83713a" }, { "dataPath": "params_shard_93.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": "118104f58d0ca29212fd8502392d8dd4" }, { "dataPath": "params_shard_94.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": "b9f63740cfe7f8e2dc52dceec2ceac53" }, { "dataPath": "params_shard_95.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": "7ef7640255139af3bbec384ae5e2dcb3" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "47607559ba2480ac3bc36b66c8701197" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 29392896, "records": [ { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 29376512 } ], "md5sum": "aba309a73faf3f39a3acaaca7c40033a" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "241c171ec73f7968c7c139c73a3f7723" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "ebec1ecada2923e46b208f51ab44d80a" }, { "dataPath": "params_shard_100.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": "f04433a74c7af273bb748e66d60f26c5" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "5adaffdd7e30e7c665b3b84b6c87338f" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 18907136, "records": [ { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14696448 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 } ], "md5sum": "2fd1c98ebfef27d1828b4fa0128dc086" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "755480b40fdef482aeedd6096645d84b" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "cf025460f9c068ab8ad0998f2fbfa5bc" }, { "dataPath": "params_shard_105.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": "95f8bc00aca7efdce720aae193603c2e" }, { "dataPath": "params_shard_106.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": "d8afece8e05f8d8f18a61d12295f7a12" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "56077849736a8334c4065fcdf54676c9" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.22.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "5987187a3b2c147b4cc4b1f450da3155" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "083f9c321bf11e7c17d0d04b79e1246d" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "18f7d68d67c8f9e016454775608bcd5e" }, { "dataPath": "params_shard_111.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": "cd039586249f83db982146a244609a33" }, { "dataPath": "params_shard_112.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": "0b3a2248809c1e68db16a6c3440a9ff8" }, { "dataPath": "params_shard_113.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "bd174c674963c807a051f6db76093788" }, { "dataPath": "params_shard_114.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.23.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "49c3116d2515a2ce384972df77514abd" }, { "dataPath": "params_shard_115.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "1ce59d32e3cbbf36418e8cf60b8c8c45" }, { "dataPath": "params_shard_116.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "a11d8eaf4b6b2d679e701977fe39ee3d" }, { "dataPath": "params_shard_117.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": "1661890a759f943052d3d1ba6bea0652" }, { "dataPath": "params_shard_118.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": "2627881c3dd73e567f6ed489e91991bc" }, { "dataPath": "params_shard_119.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "a6c8f3c355d201cea700f14730dacdc0" }, { "dataPath": "params_shard_120.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.24.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "6fa81652f2220268409545002dc08c07" }, { "dataPath": "params_shard_121.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "51089758a158d0181b4905c14b6e325f" }, { "dataPath": "params_shard_122.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "78e3ebc9664ba62139cb37d56e1f0f68" }, { "dataPath": "params_shard_123.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": "d4a128b12781f0125cb098c07652ebba" }, { "dataPath": "params_shard_124.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": "1a44bb8e9f620de4bff0bd9e59c7281c" }, { "dataPath": "params_shard_125.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "c25f59460a16094da327b824ab3bdd79" }, { "dataPath": "params_shard_126.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "e95c767ccf76fcffe3ee8abb9b9fca07" }, { "dataPath": "params_shard_127.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": "35efcdb70874048ad498afd9d1bd2c24" }, { "dataPath": "params_shard_128.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": "b0ce448b0e8b1b992a7c9197be250417" }, { "dataPath": "params_shard_129.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.25.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.26.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "7abf2c141827d7cc8dcee429b4a753e0" }, { "dataPath": "params_shard_130.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "08463aefbca7dba8cb4fb9aa8558ffbe" }, { "dataPath": "params_shard_131.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "55225ebc191b62ac169b6fd9ea24072e" }, { "dataPath": "params_shard_132.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "0790a9406bfc9d8e89a516751b48d212" }, { "dataPath": "params_shard_133.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "b2e44647d461a89220192f6e62012d2d" }, { "dataPath": "params_shard_134.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "f4f084b56943f8d987c11b394e9b0492" }, { "dataPath": "params_shard_135.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": "5f371a76e20ea4dab2655f99a56206d0" }, { "dataPath": "params_shard_136.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": "7cfc451e06e1ef3dbc161e7b2e262347" }, { "dataPath": "params_shard_137.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "69b198d33e468fa69557acfbe4f1b50e" }, { "dataPath": "params_shard_138.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.27.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "7a00da8d86b8a70ece22e3247e40c085" }, { "dataPath": "params_shard_139.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "c9693f2ddfcc81addbef55904f599d40" }, { "dataPath": "params_shard_140.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "9d1667c534844541e535a01a2ae2a7b1" }, { "dataPath": "params_shard_141.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": "0aab9c22a2c0b8385f464d32e7e79322" }, { "dataPath": "params_shard_142.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": "229a5164e3646cc3d012107e3a8db78c" }, { "dataPath": "params_shard_143.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "b1e4287a97f506be7eac85f325c8b35b" }, { "dataPath": "params_shard_144.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "57c03c1421a258ab87248a89b7f50dbb" }, { "dataPath": "params_shard_145.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": "55c3cbc9d48f2a560ed479b20e32aa06" }, { "dataPath": "params_shard_146.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": "73fe845e8cbbec88e8b70e91ceadcd96" }, { "dataPath": "params_shard_147.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.28.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.29.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "2cbfe7d8517faf0e39de6f568727b143" }, { "dataPath": "params_shard_148.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "2278a3aeca926b56bf02a58683e173a1" }, { "dataPath": "params_shard_149.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "3422f35ef2ed44089676cb18f2179c3d" }, { "dataPath": "params_shard_150.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "f682adc87cc48cc99d38349ac20027a0" }, { "dataPath": "params_shard_151.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "27e412b941d4f584f4c55d6136353470" }, { "dataPath": "params_shard_152.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "948d140181ae4ee253ee325e62e32574" }, { "dataPath": "params_shard_153.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": "de7c4d0100a871ebe0869e23b9f86791" }, { "dataPath": "params_shard_154.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": "d11d4150627a06e36aede1cdd11ea171" }, { "dataPath": "params_shard_155.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "acac8ff4b8e7e1d79f4b9196c2f26136" }, { "dataPath": "params_shard_156.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.30.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "8f5a8afa7bd263ea65f4f29effb53120" }, { "dataPath": "params_shard_157.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "9c3b623d2a055dff63d36051a768994a" }, { "dataPath": "params_shard_158.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "81ee906e6db7a3d5e9448dc59a1f5e80" }, { "dataPath": "params_shard_159.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": "ffe7f9a9bafc93f41f3927c0db1dd9db" }, { "dataPath": "params_shard_160.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": "40de9c138b4577a4d86e4d8f798b5cdf" }, { "dataPath": "params_shard_161.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": "ce69b6f9d0369366e199f9cde785c760" }, { "dataPath": "params_shard_162.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": "a813ca1b7278fabd55f0f6d51faf28ce" }, { "dataPath": "params_shard_163.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.31.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.32.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "b2554dda995a27216fb46c7a8f7c62a5" }, { "dataPath": "params_shard_164.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.32.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "0f52ab8b0963c0bfc33776057ff294f1" }, { "dataPath": "params_shard_165.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "68ba6d563f911f35b41fbc0e9cd43592" }, { "dataPath": "params_shard_166.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "28ebbb8d3a3bf0ca8f76ea48accd2425" }, { "dataPath": "params_shard_167.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.33.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "011dfa7e7fd4ecdb56565070627e742d" }, { "dataPath": "params_shard_168.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.32.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.32.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.32.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.32.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.33.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "f0dc3e838141c6e3cabfec3b9227f85c" }, { "dataPath": "params_shard_169.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "abca547a060ae8e48bbf119ddcec0dc4" }, { "dataPath": "params_shard_170.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "a7f7de456b93e91e40a274c5effd28e9" }, { "dataPath": "params_shard_171.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": "d60edfb4c872a7987408fcf9a67a624b" }, { "dataPath": "params_shard_172.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": "1c6b2787f7be4d1b12d64e9afba2a074" }, { "dataPath": "params_shard_173.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.34.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "3e72a4c296ee97c69d4ecc9e3c9d0996" }, { "dataPath": "params_shard_174.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.33.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.33.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.33.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.33.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.34.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "de5bf19526b39fca07148f4e86b8c55a" }, { "dataPath": "params_shard_175.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "7e4453ca398018f5f82728b542ebfc0e" }, { "dataPath": "params_shard_176.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "dd1a10cfd98ae98df32612ba2bf2e507" }, { "dataPath": "params_shard_177.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": "9f7743c267bdd21803ca7a2f2fe8c1b1" }, { "dataPath": "params_shard_178.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": "a1f8518b76612d82cda59bd7045e3794" }, { "dataPath": "params_shard_179.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": "7c1b6e578bbe7668f2ad175e8c158374" }, { "dataPath": "params_shard_180.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.35.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "e69a36a6d1666ed7d5e2da43ba6b62eb" }, { "dataPath": "params_shard_181.bin", "format": "raw-shard", "nbytes": 29392896, "records": [ { "name": "model.layers.34.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.34.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.34.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.34.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.35.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 }, { "name": "model.layers.35.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 29376512 } ], "md5sum": "f9f6f4854ef485168ae5e0168f872925" }, { "dataPath": "params_shard_182.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "c0e2f441a96dcc03cde593645c597c0d" }, { "dataPath": "params_shard_183.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "b93330a8fb41b566331e64f19defe35b" }, { "dataPath": "params_shard_184.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": "aa84fbcca5cf5be28b269adef2ba5328" }, { "dataPath": "params_shard_185.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.36.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "ea4ff406518c4f245fabbaa41830daa4" }, { "dataPath": "params_shard_186.bin", "format": "raw-shard", "nbytes": 18907136, "records": [ { "name": "model.layers.35.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.35.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.35.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14696448 }, { "name": "model.layers.36.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 } ], "md5sum": "7fda434dba3a52e6d7437ea8584bea5b" }, { "dataPath": "params_shard_187.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "a1fc75fe12dd7dd1e31f439782d8c149" }, { "dataPath": "params_shard_188.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "b5ba09fa85b8fb4434d33067f17ae45d" }, { "dataPath": "params_shard_189.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": "9592aa1f4d1b3cbe26809153505eb9cc" }, { "dataPath": "params_shard_190.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": "f6bf62e6ad9dd6d5380c6a29fdecbae4" }, { "dataPath": "params_shard_191.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.37.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "d3381867310686215c5810abcf9402bf" }, { "dataPath": "params_shard_192.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.36.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.36.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.36.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.36.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.37.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "4682e57d59822fc8ebc7e49b8f8ca467" }, { "dataPath": "params_shard_193.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.37.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "14ffe9a95eaf2e24eaddf7004440ad8e" }, { "dataPath": "params_shard_194.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.37.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "8b6abd6c29c824de503833413f3b832b" }, { "dataPath": "params_shard_195.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": "375ec84adca3d8350c1e2ce5e96c173a" }, { "dataPath": "params_shard_196.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": "508548ec3a261aeae3699c713004b9d9" }, { "dataPath": "params_shard_197.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.38.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "04bd9199d53a81247eaa385735483d0a" }, { "dataPath": "params_shard_198.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.37.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.37.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.37.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.37.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.38.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "9f5ef65b1f1994094bdfaae4c333c391" }, { "dataPath": "params_shard_199.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "66bb10bd0e33e78df6fafc8ef3576cab" }, { "dataPath": "params_shard_200.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "68426f0fdaf4e8f7057da6c3c987cfcd" }, { "dataPath": "params_shard_201.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": "7203d60d67a225320b15328ec7e52129" }, { "dataPath": "params_shard_202.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": "53e8e653e16b01adb321ddbf4ea15b25" }, { "dataPath": "params_shard_203.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.39.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "7617a5791efc4761a4207c25856713b3" }, { "dataPath": "params_shard_204.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.38.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.38.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.38.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.38.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.39.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "a59efc784be7d44fb78e19067ce9d3ee" }, { "dataPath": "params_shard_205.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.39.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "d7c56bc32c21f1e41fa5dd25c59823ad" }, { "dataPath": "params_shard_206.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.39.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "6fe19e8ec7e194dec7eda4c52586078d" }, { "dataPath": "params_shard_207.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": "1cded5aaaaebbe6e6875be733d9641a9" }, { "dataPath": "params_shard_208.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": "fceb68ecf70807bb78dc6c03508c378c" }, { "dataPath": "params_shard_209.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.40.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "71dcca77cf45255442efbe59ef90a6d5" }, { "dataPath": "params_shard_210.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.40.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "98f87b1c2c7020e65e22807f0c7316c3" }, { "dataPath": "params_shard_211.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": "206806db7dcf7d0d54ab6f2b3892bf5f" }, { "dataPath": "params_shard_212.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": "8966b5503c7e4cf2cf2e67175ae8ad8c" }, { "dataPath": "params_shard_213.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.39.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.39.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.39.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.39.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.40.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "537c007e7806f321ecf1bdae50049111" }, { "dataPath": "params_shard_214.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "b8e9040842a706ed5e3e4722f3a83109" }, { "dataPath": "params_shard_215.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "f7c10d66ab654133a5518031d439c347" }, { "dataPath": "params_shard_216.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "c8b532109b06a74c9d1789248c302cef" }, { "dataPath": "params_shard_217.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "ddf84ac6318fe7c7006bcabc07f3ae69" }, { "dataPath": "params_shard_218.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.40.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "d0a47d5169c2c7210ac7a3158ff21301" }, { "dataPath": "params_shard_219.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "bd5f5e678b452d2f94042db9e9ef482f" }, { "dataPath": "params_shard_220.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "bd046fabf7ea6260ca5dd72850e18324" }, { "dataPath": "params_shard_221.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": "d61dac351c46d9b73c061bd2cc1c4ebf" }, { "dataPath": "params_shard_222.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": "7eb61aa37153c3ceb30dad335cea3f29" }, { "dataPath": "params_shard_223.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "919eeeb861ab43379ae03188dd2fd4e5" }, { "dataPath": "params_shard_224.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "45d827e1987e7e180f772420879e8ae3" }, { "dataPath": "params_shard_225.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "d1e65c61a324656ec61c32fb63030335" }, { "dataPath": "params_shard_226.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "53a5ddeea3e2ddc3b32979d981ce1d4c" }, { "dataPath": "params_shard_227.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": "9630e71fc3f3d09945f5db78aace0298" }, { "dataPath": "params_shard_228.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": "27c5a7b7bc42ca222f01beeed8e82108" }, { "dataPath": "params_shard_229.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": "657dc2c8f253c033fc97c08ebe8c1df0" }, { "dataPath": "params_shard_230.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.40.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "4198b7a995218887c4f69d3042355488" }, { "dataPath": "params_shard_231.bin", "format": "raw-shard", "nbytes": 29392896, "records": [ { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 }, { "name": "model.layers.40.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 29376512 } ], "md5sum": "0cf2a65f504ba08752c0cc5ce18c49ea" }, { "dataPath": "params_shard_232.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.41.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "9afef59efa57f02b72579c896275362a" }, { "dataPath": "params_shard_233.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.41.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "185b04633ffa36008082b2cb529c342a" }, { "dataPath": "params_shard_234.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.41.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "20a057e8ef9f7e0a73c026e898c6f662" }, { "dataPath": "params_shard_235.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": "235a3c67368e2fadd84c3097247b33cb" }, { "dataPath": "params_shard_236.bin", "format": "raw-shard", "nbytes": 29409280, "records": [ { "name": "model.layers.40.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.40.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.41.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14696448 }, { "name": "model.layers.41.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 14712832 }, { "name": "model.layers.41.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 29392896 } ], "md5sum": "28e5a9fe323df18656bda67844f5933c" }, { "dataPath": "params_shard_237.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": "4acca40fb84a2c4310dcf3cc98409d18" }, { "dataPath": "params_shard_238.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.42.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "6c748059db110d195bef2a77245db728" }, { "dataPath": "params_shard_239.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.42.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "2fcb0fe787459c08d6bc6546054e2f4d" }, { "dataPath": "params_shard_240.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.42.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "493ed7d0770ffb33683a8b41f9b1e472" }, { "dataPath": "params_shard_241.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": "ec38e9724bb4939bbc0422334976e2ff" }, { "dataPath": "params_shard_242.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": "99a5ed7fd85b4bbb80fc8256a907ac13" }, { "dataPath": "params_shard_243.bin", "format": "raw-shard", "nbytes": 29392896, "records": [ { "name": "model.layers.41.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.41.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.42.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.42.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 9453568 }, { "name": "model.layers.42.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 }, { "name": "model.layers.42.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24150016 } ], "md5sum": "843e92715fdc776f13549e4259481965" }, { "dataPath": "params_shard_244.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.43.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "89a98fc084c5d2ec256143c00a30e399" }, { "dataPath": "params_shard_245.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.43.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "561558bf7cebf93a6703d8d81f716695" }, { "dataPath": "params_shard_246.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": "56ac2b85c02657e24e8585729e458aaf" }, { "dataPath": "params_shard_247.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": "84aef44e7d2ffee672a54c6345b37ab9" }, { "dataPath": "params_shard_248.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.43.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "e418523023be4e9be2e2d232ee996386" }, { "dataPath": "params_shard_249.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.44.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "7c8d5e77a3db067a30ff3095ffdd71c4" }, { "dataPath": "params_shard_250.bin", "format": "raw-shard", "nbytes": 28360704, "records": [ { "name": "model.layers.42.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.43.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 4194304 }, { "name": "model.layers.43.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 9437184 }, { "name": "model.layers.43.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 13631488 }, { "name": "model.layers.43.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 13647872 }, { "name": "model.layers.43.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 28327936 }, { "name": "model.layers.44.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 28344320 } ], "md5sum": "afff556154c8544e674331e72464840e" }, { "dataPath": "params_shard_251.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.44.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "e6190c46043a48ec49ada5009ab3b567" }, { "dataPath": "params_shard_252.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.44.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "f8f5aecdd1c82697f28768ac936a639a" }, { "dataPath": "params_shard_253.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": "2abfddfc726ee92eb94b1b64367a48fe" }, { "dataPath": "params_shard_254.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": "84125b09103cc4e54e68f22ba4864af4" }, { "dataPath": "params_shard_255.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.45.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "df551f06ce60b1633cd16add2f0aa026" }, { "dataPath": "params_shard_256.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.44.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.44.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.44.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.44.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.45.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "9fd72796d3a57723e86edb81336e4db4" }, { "dataPath": "params_shard_257.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.45.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "d371b1218d2fdf12105279b26da5a246" }, { "dataPath": "params_shard_258.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.45.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "efa705bd6252debbae9f9809bb10ec46" }, { "dataPath": "params_shard_259.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": "953aaa81f4452d9182a8a50c2755762b" }, { "dataPath": "params_shard_260.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": "2f77ee261bcb19790473a1a0ec9afedc" }, { "dataPath": "params_shard_261.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": "10b4ca9203ee28d3a8de19d78892b04b" }, { "dataPath": "params_shard_262.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": "9b8548272ce94e3a8f9af364f9e32a66" }, { "dataPath": "params_shard_263.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.45.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.45.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.45.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.45.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.46.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "aa4af3707f75da5a9650335be0001e08" }, { "dataPath": "params_shard_264.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.46.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "8d5c2f5adc206dbcdb1b1c5f853698b2" }, { "dataPath": "params_shard_265.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.46.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "0defee78355844ef76f1a50dc6c6489e" }, { "dataPath": "params_shard_266.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.46.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "da539b73be1df2a96e10e1044aa4f17b" }, { "dataPath": "params_shard_267.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.47.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "54d008773c4fbbf64b02688194c26193" }, { "dataPath": "params_shard_268.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.46.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.46.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.46.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.46.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.47.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "878bf9b8adfca2341134c9c82b96303b" }, { "dataPath": "params_shard_269.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.47.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "34cdaff497414dd3945e2cb3f593c489" }, { "dataPath": "params_shard_270.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.47.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "086346842988c4a4064414fa989b26ff" }, { "dataPath": "params_shard_271.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": "673201125930a6d09fd0528b6bae6bac" }, { "dataPath": "params_shard_272.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": "57dfbe9b4d13d8238d2cc7116c560d00" }, { "dataPath": "params_shard_273.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.48.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "302ec103cdec521cfc737b66a3347074" }, { "dataPath": "params_shard_274.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.47.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.47.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.47.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.47.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.48.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "e3e3942ed11c1cd36e988427503e36d3" }, { "dataPath": "params_shard_275.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.48.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "a7e3de199de1f1f00c02410682234a2b" }, { "dataPath": "params_shard_276.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.48.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "372b5b6643c7634905e955c3fe8a4dda" }, { "dataPath": "params_shard_277.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.48.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "4a158dfa9f7cce433e480bfa6b1bc9be" }, { "dataPath": "params_shard_278.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.48.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "b8b1fe968b64449bc9ffffa72362ad33" }, { "dataPath": "params_shard_279.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.49.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "ac92a39c09d4ce1f6cca1dcef7b91707" }, { "dataPath": "params_shard_280.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.49.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "b7fb1faf9abc1188e3c7f32fea2913a3" }, { "dataPath": "params_shard_281.bin", "format": "raw-shard", "nbytes": 29392896, "records": [ { "name": "model.layers.48.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.48.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.48.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.48.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.49.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 }, { "name": "model.layers.49.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 29376512 } ], "md5sum": "fd77fdd147a333c74bd65f963bee3577" }, { "dataPath": "params_shard_282.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.49.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "444f8a578eee8ac07d6e4806a125a2b8" }, { "dataPath": "params_shard_283.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.49.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "8334150398386e412ae1b5f0870b2736" }, { "dataPath": "params_shard_284.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.49.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "5fe7807fcdd50033d748ee27d8f1422a" }, { "dataPath": "params_shard_285.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.50.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "450194719c7e8a775ca4d07e9bb12a9d" }, { "dataPath": "params_shard_286.bin", "format": "raw-shard", "nbytes": 18907136, "records": [ { "name": "model.layers.49.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.49.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.49.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14696448 }, { "name": "model.layers.50.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 } ], "md5sum": "de919647995617c0ca452a2106799798" }, { "dataPath": "params_shard_287.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.50.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "a49ad03e4691ac58735b0568e2d08d19" }, { "dataPath": "params_shard_288.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.50.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "77cf2fa1667b0b4987aa80c16872e20f" }, { "dataPath": "params_shard_289.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.50.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "724e3cfe4205b2dbed78b22282283e24" }, { "dataPath": "params_shard_290.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.50.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "cfd5e5546a2295228b7726bad363bdbe" }, { "dataPath": "params_shard_291.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.51.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "06a9ec6e709f085480fd479292356723" }, { "dataPath": "params_shard_292.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.50.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.50.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.50.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.50.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.51.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "c2cd969b0c16a4dfe78e7c82da6c4a98" }, { "dataPath": "params_shard_293.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.51.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "f80173007a11bcec985090423931dff1" }, { "dataPath": "params_shard_294.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.51.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "dd1c24cae7af7d0045a4abae0f5d9568" }, { "dataPath": "params_shard_295.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.51.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "34a37c10a6bdfd0e35e19858496f18a4" }, { "dataPath": "params_shard_296.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.51.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "b8e3d14f0105c71d6347b97ecf177f5d" }, { "dataPath": "params_shard_297.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.52.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "d1e9625035ee15a0b5fce6361903f5a4" }, { "dataPath": "params_shard_298.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.51.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.51.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.51.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.51.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.52.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "ca8a977c22f8ebc1b2c66b8b63a8a5e7" }, { "dataPath": "params_shard_299.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.52.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "7251ddc06e57d40937a2d2f6b1b52664" }, { "dataPath": "params_shard_300.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.52.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "605ffd68bace87cdb7b1b035a7236031" }, { "dataPath": "params_shard_301.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.52.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "c28c564471db1ea906517bc7345b0a74" }, { "dataPath": "params_shard_302.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.52.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "366042dc21fde4713168491b726bc1d7" }, { "dataPath": "params_shard_303.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.53.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "39178e23a35fae600d7fd6a6c038d867" }, { "dataPath": "params_shard_304.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.52.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.52.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.52.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.52.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.53.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "d4f37bc3b392736d64aa82a28cc23ae6" }, { "dataPath": "params_shard_305.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.53.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "6a02f3debf84a167fa9bba3cdbefdb23" }, { "dataPath": "params_shard_306.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.53.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "a9a3474303e23e351afc4bcdcccba238" }, { "dataPath": "params_shard_307.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.53.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "e15f3a434f77d4589dfe4a0b40bff49c" }, { "dataPath": "params_shard_308.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.53.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "aafea4bc4ad67a7e41fc0adb8b857ba7" }, { "dataPath": "params_shard_309.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.54.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "f7d838311d69bac62ff618b8f97edd2a" }, { "dataPath": "params_shard_310.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.54.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "41de3117cb82c23a2a2de9e87474de2c" }, { "dataPath": "params_shard_311.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.54.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "8b44652a67a2d3726919a4d5c035464a" }, { "dataPath": "params_shard_312.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.54.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "2410b0dddf12f610c77336c2528ce68c" }, { "dataPath": "params_shard_313.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.53.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.53.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.53.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.53.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.54.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "9e6b11358f4d72264c7595ff4949a541" }, { "dataPath": "params_shard_314.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.54.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "4c6391cd1d131ceaa1f2b84cce19c780" }, { "dataPath": "params_shard_315.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.55.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "6338b603748687c44fefe9840961cf9f" }, { "dataPath": "params_shard_316.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.54.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.54.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.54.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.54.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.55.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "0b7601402cba5a6a44a0a07d6cf4a2e9" }, { "dataPath": "params_shard_317.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.55.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "ccac38b7417b515dc7f8041f3a49d882" }, { "dataPath": "params_shard_318.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.55.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "65c3604c724a358e75b43aab89da3c4c" }, { "dataPath": "params_shard_319.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.55.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "c74abd0614621ce5a8dc1bdcbd7c0f00" }, { "dataPath": "params_shard_320.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.55.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "7e141b8df8bed9aeecd7f18b60fd56d3" }, { "dataPath": "params_shard_321.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.56.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "70eaf1c553e83d4a484cc3cce4c12949" }, { "dataPath": "params_shard_322.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.55.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.55.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.55.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.55.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.56.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "7a2b8f45cfd51ec5f8633192cbe81e67" }, { "dataPath": "params_shard_323.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.56.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "807a475475dc76aaa1e4ddb7433a21c4" }, { "dataPath": "params_shard_324.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.56.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "29043c0ad599de232eceb1b0ff9bbf23" }, { "dataPath": "params_shard_325.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.56.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "8a3d14f8c80c5a02d3ed717a1bf57c1f" }, { "dataPath": "params_shard_326.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.56.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "7aa5bb31b29c46103dd333cc442d364e" }, { "dataPath": "params_shard_327.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.57.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "376f35ecb49afae4c549a6052d7da8a3" }, { "dataPath": "params_shard_328.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.57.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "2244b331bd00e83480bd35a2e6e3da20" }, { "dataPath": "params_shard_329.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.57.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "4e687bcd749877289d7b7ccd704eb9c0" }, { "dataPath": "params_shard_330.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.57.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "2de76f53d8d0b2095c1d7fbbb368b08f" }, { "dataPath": "params_shard_331.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.56.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.56.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.56.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.56.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.57.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "9cd741ab1f99acf6780256c6bf312250" }, { "dataPath": "params_shard_332.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.57.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "c45488c19a2317aefdda542f66096e96" }, { "dataPath": "params_shard_333.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.58.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "d23b0c5cefc9aa18999d5d6f73881765" }, { "dataPath": "params_shard_334.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.57.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.57.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.57.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.57.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.58.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "fbed768c940a0e91a74d2565c0b606b2" }, { "dataPath": "params_shard_335.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.58.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "7f45d0d8933ed86345719e1de6e5d73b" }, { "dataPath": "params_shard_336.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.58.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "472487a369e2ac9535a0841057b9d282" }, { "dataPath": "params_shard_337.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.58.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "d63fcc10bf190a74c109fccb2fff0c5d" }, { "dataPath": "params_shard_338.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.58.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "ac54625748a1275f3942a8ea9f4ae285" }, { "dataPath": "params_shard_339.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.59.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "1f8b0181916c0bd997505d60f3e87180" }, { "dataPath": "params_shard_340.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.58.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.58.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.58.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.58.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.59.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "cd67fe77960054947204587c5b8c9811" }, { "dataPath": "params_shard_341.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.59.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "8d08782ef88c7c399d4927bd25e2d415" }, { "dataPath": "params_shard_342.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.59.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "54b0d080f4909670c7f892bf64d3a419" }, { "dataPath": "params_shard_343.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.59.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "ed344ac2d2f9c0ac5b380d13d180d891" }, { "dataPath": "params_shard_344.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.59.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "6af91e9b1ea039059fd69e8dcb770467" }, { "dataPath": "params_shard_345.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.60.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "a6fc328eb8999492add0ed48d10f9b68" }, { "dataPath": "params_shard_346.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.60.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "2cd81203326a99b97da38f4821a82564" }, { "dataPath": "params_shard_347.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.59.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.59.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.59.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.59.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.60.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "1e860d9ef4a3f14df2a61f47da384304" }, { "dataPath": "params_shard_348.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.60.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "fc36ffd36ec91d537d0d107f0370999f" }, { "dataPath": "params_shard_349.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.60.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "7d1cfe4cc4b3e158a70bc378b9434143" }, { "dataPath": "params_shard_350.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.60.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "bbdd13d751561c861b61bac4fd5e32a6" }, { "dataPath": "params_shard_351.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.61.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "263cd7810b9b389e57dd04d87cf8069d" }, { "dataPath": "params_shard_352.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.60.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.60.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.60.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.60.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.61.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "d481fb10f9738eedc794b349ee47b537" }, { "dataPath": "params_shard_353.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.61.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "c3b7d9a086e3d33c54d1bd3be5430708" }, { "dataPath": "params_shard_354.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.61.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "e883adeeed62136fdf6f013cc7e1db16" }, { "dataPath": "params_shard_355.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.61.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "b74714c02edee8789a9d2a9cbdb0d1ea" }, { "dataPath": "params_shard_356.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.61.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "9a28a1bf72f233f5ff0a864813fcf479" }, { "dataPath": "params_shard_357.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.62.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "3930e4b3adade006838215c22d817b8e" }, { "dataPath": "params_shard_358.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.61.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.61.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.61.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.61.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.62.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "c1fe5eab73f5caec8bbeb9a1ca465a6d" }, { "dataPath": "params_shard_359.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.62.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "85e54b4b2ddd2e548cc8ec01b527528d" }, { "dataPath": "params_shard_360.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.62.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "ebaacdee596a85756cbf783b65466eaf" }, { "dataPath": "params_shard_361.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.62.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "62e5f592b5321dc21023c90df8d9a4c4" }, { "dataPath": "params_shard_362.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.62.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "e9d2ea35c6d665e2f1f2c977cfd4f93f" }, { "dataPath": "params_shard_363.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.63.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "234229403f94b1b4c621beecb56041ee" }, { "dataPath": "params_shard_364.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.63.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "19a3aca5cc72380913a5ce56ad6900d9" }, { "dataPath": "params_shard_365.bin", "format": "raw-shard", "nbytes": 29392896, "records": [ { "name": "model.layers.62.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.62.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.62.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.62.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.63.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 }, { "name": "model.layers.63.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 29376512 } ], "md5sum": "316f3be524082eff92bda4666abc072c" }, { "dataPath": "params_shard_366.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.63.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "385f264675b8286f3bc189f988a16363" }, { "dataPath": "params_shard_367.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.63.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "2a221ea95b93f1a76ba90d9a76a390f5" }, { "dataPath": "params_shard_368.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.63.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "a1e03cbb3c83502c5015bf7160bf8683" }, { "dataPath": "params_shard_369.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.64.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "9450aea1521bce7dcf340a0e6c5c2a4e" }, { "dataPath": "params_shard_370.bin", "format": "raw-shard", "nbytes": 18907136, "records": [ { "name": "model.layers.63.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.63.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.63.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14696448 }, { "name": "model.layers.64.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 } ], "md5sum": "a703e8c3b703ec9a31595364a8e51abb" }, { "dataPath": "params_shard_371.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.64.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "9a1e9db00d7125eed502ddf55cfe2112" }, { "dataPath": "params_shard_372.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.64.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "b4280ac24e8635bf330471d028b500db" }, { "dataPath": "params_shard_373.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.64.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "1a661218d39c937011ed60f375414bfc" }, { "dataPath": "params_shard_374.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.64.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "8dcb6ac55c9f431157f2a001792e7560" }, { "dataPath": "params_shard_375.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.65.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "f051eca80367cbc0fbfedf56cddeff98" }, { "dataPath": "params_shard_376.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.64.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.64.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.64.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.64.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.65.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "9b4cf8323b5fc8824ab633df52291fea" }, { "dataPath": "params_shard_377.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.65.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "d7de50136174910ccbc93b8ecd9f190c" }, { "dataPath": "params_shard_378.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.65.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "8f8e251226e643f41488b5208203f3d1" }, { "dataPath": "params_shard_379.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.65.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "09f6def62128b9c53fe112e7199b4fdf" }, { "dataPath": "params_shard_380.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.65.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "4ec9686674a2e1c46f1c54321dba361e" }, { "dataPath": "params_shard_381.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.66.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "1ca407860c32e4d1b8cf50d775556235" }, { "dataPath": "params_shard_382.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.65.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.65.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.65.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.65.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.66.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "cb9f55077e43f2c0c6faf5f15a1c319d" }, { "dataPath": "params_shard_383.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.66.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "c68829fec9b46fec4834328f3a43e5be" }, { "dataPath": "params_shard_384.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.66.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "9a5ca51cd015ed5711897492e0104d2b" }, { "dataPath": "params_shard_385.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.66.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "56b76b01e998801aac3ab1f825913eb0" }, { "dataPath": "params_shard_386.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.66.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "10e6513cddb193e604a206a896929cbb" }, { "dataPath": "params_shard_387.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.67.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "0f637abca59d22d5296f8c898496658a" }, { "dataPath": "params_shard_388.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.66.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.66.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.66.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.66.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.67.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "38bb3553c4f086f94a342c6f07f3d349" }, { "dataPath": "params_shard_389.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.67.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "3dd357e5830e592e57a451c4d43a19ad" }, { "dataPath": "params_shard_390.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.67.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "329647a7782358db9d7ccb8e6d62b5d7" }, { "dataPath": "params_shard_391.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.67.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "d01b38085e49481c3035988ca61b5b90" }, { "dataPath": "params_shard_392.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.67.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "fcdc51a64e601b36b16ea1f93102bd52" }, { "dataPath": "params_shard_393.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.68.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "eda5eb23a44f05fdbe9b301d0eb0b4d5" }, { "dataPath": "params_shard_394.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.68.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "6cc7b4a3de56bdf4ff0a317f516652a6" }, { "dataPath": "params_shard_395.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.68.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "4dc5f288b0560542b76907a42fcfaa32" }, { "dataPath": "params_shard_396.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.68.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "5465899def06e35c8f6f267d0137fcea" }, { "dataPath": "params_shard_397.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.67.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.67.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.67.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.67.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.68.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "2a7541b7b5a74ae7a1ae25bb72206163" }, { "dataPath": "params_shard_398.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.68.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "2b625b607cf8810f7d8d45db15b2a770" }, { "dataPath": "params_shard_399.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.69.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "2bcf2fdb261bbf4b4c4726d5ca63360f" }, { "dataPath": "params_shard_400.bin", "format": "raw-shard", "nbytes": 18923520, "records": [ { "name": "model.layers.68.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.68.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.68.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.68.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.69.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18907136 } ], "md5sum": "27aff138bb23723cf7fe4f79a6dd0a29" }, { "dataPath": "params_shard_401.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.69.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "ab196d71fa039d40ae778beddce415fe" }, { "dataPath": "params_shard_402.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.69.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "3da8d5f68705ef23a611b528ce8d2fa6" }, { "dataPath": "params_shard_403.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.69.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "2e600a6121de6cbd52e99be2dfd760b5" }, { "dataPath": "params_shard_404.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.69.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "fa89418762216a4e8a02bda1521cfc57" }, { "dataPath": "params_shard_405.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.70.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "3ddf7403c86584b26121b137434e9ed8" }, { "dataPath": "params_shard_406.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.69.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.69.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.69.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.69.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.70.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "ecbfca1f7dc02f2b2ef0798cc16c9aca" }, { "dataPath": "params_shard_407.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.70.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "012f7b89d18b07e67bc1595c64e1dcc8" }, { "dataPath": "params_shard_408.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.70.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "07c1fd185b65b6a7a9972352bc1e479c" }, { "dataPath": "params_shard_409.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.70.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "a093d82fcb679ce393f2845d415975b5" }, { "dataPath": "params_shard_410.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.70.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "b84a0cab3e056d5e028a71f6388cd66f" }, { "dataPath": "params_shard_411.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.71.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "5968efc5047fb57fca9542143742c099" }, { "dataPath": "params_shard_412.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.71.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "48987368b8345cdfb7e0ac0927fd9f6d" }, { "dataPath": "params_shard_413.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.71.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "bafdad1ef90d68d0a762db3febc96cbd" }, { "dataPath": "params_shard_414.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.71.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "d1e737bf17f91e4c6a7ece23a6fa1bd2" }, { "dataPath": "params_shard_415.bin", "format": "raw-shard", "nbytes": 29376512, "records": [ { "name": "model.layers.70.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.70.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.70.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.70.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.71.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 } ], "md5sum": "a2e79d63c4e299e3999a12a18cceef09" }, { "dataPath": "params_shard_416.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "124b67095aa3e47e7646f903b0c8e341" }, { "dataPath": "params_shard_417.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "bdeafbb0048e015fe41c25778104ca55" }, { "dataPath": "params_shard_418.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "abf357ec216087d3eb60c7e04eaaf614" }, { "dataPath": "params_shard_419.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": "5e3d5b6df1ba12c311228b2d478b177a" }, { "dataPath": "params_shard_420.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "bf3e80d21bf57f8fa01bc45a062fabbf" }, { "dataPath": "params_shard_421.bin", "format": "raw-shard", "nbytes": 23117824, "records": [ { "name": "model.layers.71.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 4194304 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 4210688 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 18907136 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23101440 } ], "md5sum": "e6b3ebdfe4a9904366eca9deec5f0038" }, { "dataPath": "params_shard_422.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "b8b2859f482a04f31e867f7b6b294d35" }, { "dataPath": "params_shard_423.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "310a2ec0d9d9c7c272437c8b525d4521" }, { "dataPath": "params_shard_424.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": "20dd9749af76ead1f0429589167df2cb" }, { "dataPath": "params_shard_425.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": "2f7465de99c8ecddfd1a91a29f34dd0b" }, { "dataPath": "params_shard_426.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "eb582aa0d88edf7e15fd4e52c896902a" }, { "dataPath": "params_shard_427.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "c742f73885ce6be94c5fee9afefb01b6" }, { "dataPath": "params_shard_428.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "84dbb3287aca29516fd22b5cb38b0e5d" }, { "dataPath": "params_shard_429.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "be12b171cec48803375959727fefcee1" }, { "dataPath": "params_shard_430.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": "3264dd1b8beffb1e726005e808623f9d" }, { "dataPath": "params_shard_431.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": "2a4bca5e905fa4f8d83fbe88650baec0" }, { "dataPath": "params_shard_432.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.71.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "c20cd30f9c648379f697ae85475e724d" }, { "dataPath": "params_shard_433.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.71.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "46474768869ba17d10eeb4145b687bc2" }, { "dataPath": "params_shard_434.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.72.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "fc9f77404c6e338cbff914e3a7f51620" }, { "dataPath": "params_shard_435.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.72.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "f6e4951f56d1e326a0f5945f8e95ef80" }, { "dataPath": "params_shard_436.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.72.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "faa8fc3b838ddf4ca43d9cd1e6a75391" }, { "dataPath": "params_shard_437.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.72.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "2839ed297d1884b63e77e1a1e2aeed6c" }, { "dataPath": "params_shard_438.bin", "format": "raw-shard", "nbytes": 29409280, "records": [ { "name": "model.layers.71.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.71.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.72.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14696448 }, { "name": "model.layers.72.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 14712832 }, { "name": "model.layers.72.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 29392896 } ], "md5sum": "d7be5f2caadbeb40256185cc0f65179f" }, { "dataPath": "params_shard_439.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.72.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c8a19bd92a19914b66d8c8aca7acbe31" }, { "dataPath": "params_shard_440.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.73.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "69059ded5bd88d52193ba920105fd738" }, { "dataPath": "params_shard_441.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.73.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "5ff6e0f833eec8de8b734ee77f2d0be0" }, { "dataPath": "params_shard_442.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.73.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "c81613bc6549e33d1fcb54018dd0d52e" }, { "dataPath": "params_shard_443.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.73.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "4f3e73e8efb79fe9922bf67ad8e8052f" }, { "dataPath": "params_shard_444.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.73.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "638ece025eba47b364792a2b196058f2" }, { "dataPath": "params_shard_445.bin", "format": "raw-shard", "nbytes": 29392896, "records": [ { "name": "model.layers.72.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 0 }, { "name": "model.layers.72.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 5242880 }, { "name": "model.layers.73.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9437184 }, { "name": "model.layers.73.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 9453568 }, { "name": "model.layers.73.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 }, { "name": "model.layers.73.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24150016 } ], "md5sum": "c645ca718242cc34b0e3ad68938661d0" }, { "dataPath": "params_shard_446.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.74.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "130d62725c7c8777a462c8739c09bbe9" }, { "dataPath": "params_shard_447.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.74.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "2bb18b635db79de1f5da6181d13bc765" }, { "dataPath": "params_shard_448.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.74.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "e33e3fa32462266dd9f09499c0807c68" }, { "dataPath": "params_shard_449.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.74.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "838b5fba2d17115577f9b64e2c36cef4" }, { "dataPath": "params_shard_450.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.74.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "dae8e95d2b36e403495abf3a73405485" }, { "dataPath": "params_shard_451.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.75.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "41b87436e63b180e3307d9622979640d" }, { "dataPath": "params_shard_452.bin", "format": "raw-shard", "nbytes": 28360704, "records": [ { "name": "model.layers.73.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 0 }, { "name": "model.layers.74.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 4194304 }, { "name": "model.layers.74.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 9437184 }, { "name": "model.layers.74.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 13631488 }, { "name": "model.layers.74.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 13647872 }, { "name": "model.layers.74.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 28327936 }, { "name": "model.layers.75.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 28344320 } ], "md5sum": "abfe31d6f021d4fd0439697caf70db94" }, { "dataPath": "params_shard_453.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.75.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "57fc02b8ad36a3132a33f2b973c58274" }, { "dataPath": "params_shard_454.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.75.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "55b3b6f80cfd9105ea5ec976a902a6dd" }, { "dataPath": "params_shard_455.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.75.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "6016eeca8ffce0df1c67cfd7e7680c67" }, { "dataPath": "params_shard_456.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.75.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "ecd5c91a0d85cbdaf119e09970a08360" }, { "dataPath": "params_shard_457.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.76.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "b5cb7c88e32386f13854aff069d3dcb4" }, { "dataPath": "params_shard_458.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.75.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.75.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.75.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.75.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.76.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "b7c01ad6c84e69d744f5d924408737f0" }, { "dataPath": "params_shard_459.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.76.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "ab54adad0c153018e995803c5505b104" }, { "dataPath": "params_shard_460.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.76.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "898c2cbf3f5456da93f020ea357baecf" }, { "dataPath": "params_shard_461.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.76.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "3e7e1d2bac7b01e6aef341614a04acc8" }, { "dataPath": "params_shard_462.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.76.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "e9ba8b15bdf4f0335f39c87652812ab5" }, { "dataPath": "params_shard_463.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.77.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "3474c962f33ab4271f74db103f356b04" }, { "dataPath": "params_shard_464.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.77.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "0713b3573814f097c928567a8e2269f1" }, { "dataPath": "params_shard_465.bin", "format": "raw-shard", "nbytes": 29392896, "records": [ { "name": "model.layers.76.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.76.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.76.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.76.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.77.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 24133632 }, { "name": "model.layers.77.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 29376512 } ], "md5sum": "dbfb430e9d51f7a88e87caadaa8f9901" }, { "dataPath": "params_shard_466.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.77.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "702d86303bb81b0dcaff3733b9b6c375" }, { "dataPath": "params_shard_467.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.77.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "d8ecb63e6f1a154d8e3ffd87d75b82d7" }, { "dataPath": "params_shard_468.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.77.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "45f0432a6b93a9014e01352025e39ae9" }, { "dataPath": "params_shard_469.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.78.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "1fcd56f0ec75554319ddd7f562fded0d" }, { "dataPath": "params_shard_470.bin", "format": "raw-shard", "nbytes": 18907136, "records": [ { "name": "model.layers.77.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.77.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.77.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 14696448 }, { "name": "model.layers.78.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18890752 } ], "md5sum": "65c21dd21a01aa76524cbc233bcc51e8" }, { "dataPath": "params_shard_471.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.78.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "b91659bfa57c56e26ccb944ecd070985" }, { "dataPath": "params_shard_472.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.78.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "abb6cddb3dd611185c1f99659608906f" }, { "dataPath": "params_shard_473.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.78.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "b0153716c73e55aea012529b285070bc" }, { "dataPath": "params_shard_474.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.78.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "c6664e85386b09c7d38eff33556af2e9" }, { "dataPath": "params_shard_475.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.79.mlp.down_proj.q_weight", "shape": [ 8192, 3584 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "6f549b5e07bd11c85507e881a124b1f8" }, { "dataPath": "params_shard_476.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.78.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.78.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.78.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.78.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.layers.79.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "bcadf2ffef4a0de62cbd5461d392f727" }, { "dataPath": "params_shard_477.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.79.mlp.gate_up_proj.q_weight", "shape": [ 57344, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "19de06753e8c48f1dfda3cb6cd08a52e" }, { "dataPath": "params_shard_478.bin", "format": "raw-shard", "nbytes": 29360128, "records": [ { "name": "model.layers.79.mlp.gate_up_proj.q_scale", "shape": [ 57344, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 29360128, "byteOffset": 0 } ], "md5sum": "3a96826aece1e5c3c4e31f158dc04142" }, { "dataPath": "params_shard_479.bin", "format": "raw-shard", "nbytes": 41943040, "records": [ { "name": "model.layers.79.self_attn.qkv_proj.q_weight", "shape": [ 10240, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 41943040, "byteOffset": 0 } ], "md5sum": "6a133c0d624042da48b4919a94ed9c4e" }, { "dataPath": "params_shard_480.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.79.self_attn.o_proj.q_weight", "shape": [ 8192, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "bdf87bd707856d2b0cdcbd0894aaebfb" }, { "dataPath": "params_shard_481.bin", "format": "raw-shard", "nbytes": 24150016, "records": [ { "name": "model.layers.79.mlp.down_proj.q_scale", "shape": [ 8192, 896 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14680064, "byteOffset": 0 }, { "name": "model.layers.79.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 14680064 }, { "name": "model.layers.79.self_attn.qkv_proj.q_scale", "shape": [ 10240, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5242880, "byteOffset": 14696448 }, { "name": "model.layers.79.self_attn.o_proj.q_scale", "shape": [ 8192, 256 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4194304, "byteOffset": 19939328 }, { "name": "model.norm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 24133632 } ], "md5sum": "4f74f6eaa1dc5951d751092536a8c3cf" } ] }