{ "metadata": { "ParamSize": 313, "ParamBytes": 4760885248.0, "BitsPerParam": 5.0011817065612245 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 272498688, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 152064, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 272498688, "byteOffset": 0 } ], "md5sum": "0a2026f87dc5626e82ab721125371d08" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 34062336, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 152064, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 34062336, "byteOffset": 0 } ], "md5sum": "69ae1a8dc4aacfa8a78f5374a735fa9f" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "55ef9d1fda79a3ccb14bda7e1f477eb8" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "11ffef0c093491cd9fbad9378c57e625" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 29278208, "records": [ { "name": "model.layers.0.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 9216 }, { "name": "model.layers.0.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8266752 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9298944 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15721472 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 16524288 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25011200 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29254656 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29261824 }, { "name": "model.layers.1.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29268992 } ], "md5sum": "868708637fcce02d9366c5d23e0fd937" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "cc315322746a861bb7550e9d5356ad07" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "7faa5c4d28742f5a0510d279f0144b8f" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.1.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.1.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 16515072 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25001984 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29245440 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.2.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "4e319a76bfc4e1f3afe87629a0cebb45" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "c950f7788a179f9776f8d4cb35e6f937" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "dd6948a48a87aed5f1c81b4c46fbab64" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.2.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.2.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 16515072 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25001984 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29245440 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.3.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "6da99d32a0f29340775d06c06c067e16" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "d48e704c96198695a8118b5418ca95a9" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "867234b28c700e5e361ee2deadab2331" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.3.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.3.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 16515072 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25001984 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29245440 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.4.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "260b61a1f92a658a6eaf6f60ab1759bc" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "c2300956750bc5f08137a4b501399b82" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "2efba13d319ecc5c8b5edb4399c043ed" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.4.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.4.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 16515072 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25001984 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29245440 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.5.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "7c05ae2bf26306b565e524eb42eb7af2" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "55ae4222441e62183ff4a56c9779b240" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "61cd1f6120d66932981ddb6a1fef2df2" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.5.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.5.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 16515072 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25001984 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29245440 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.6.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "4434eff322cd43eac285d2fb1026b84c" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "a308b272cf405495efc574f289758e0e" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "eda4461a5e0e3efb07a8426223b31136" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.6.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.6.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 16515072 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25001984 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29245440 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.7.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "1bd0fe5325678a1cf66cc6cde34575ce" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "a2538f385aa369a6acf2e87c084aae6a" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "ab4bf1fad7bb52355cd8db751b572ecd" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.7.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.7.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 16515072 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25001984 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29245440 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.8.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "87b5376bd33a5c41428a48a7063fd7bf" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "2066e09cc52df95b0e5e77703790ace7" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "32249e71ce533340a18a5442981f4b99" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.8.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.8.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 16515072 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25001984 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29245440 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.9.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "4f7b22b3b1f87c359c1fad4970bab9c2" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "cbdc774eb2a4c33ca644d65416a77e37" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "5a92fb07d83d3e53115282d67a32fcc7" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.9.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.9.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 16515072 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25001984 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29245440 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.10.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "d6eddfc3598c7297e7b714d8d5943e1e" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "ec81b4e9cd55de9f08b706b5c6f80dc9" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "2794893d49c3e3b662555c51195ed192" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.10.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.10.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 16515072 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25001984 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29245440 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.11.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "fedb0972a2656f1b85da6765622c0485" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "d111a0f3ce61a68274e5f0cf4e9d7bde" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "8b634dc5d68a14eab303e68094fe72e5" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.11.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.11.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 16515072 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25001984 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29245440 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.12.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "73622baa176e88347755927d54fe86dd" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "1a020a3738115a77f41e7b3b8578ebeb" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "afae1de598a1585a0027488ca3db22a8" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.12.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.12.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 16515072 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25001984 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29245440 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.13.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "1626891795c9cf29f33012218ef0f060" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "7783a3a1f4586956d11c883d5c8da74f" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "dd3ca77a77c5903ddfcd9f9aa4e3bc5b" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.13.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.13.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 16515072 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25001984 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29245440 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.14.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "aebfb889d97d7d2173ff45b6fb25bc08" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "8af2d1613f39bf72ea3a1512f53ab0c5" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "2916ff45ead84766037add669aaa51eb" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.14.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 16515072 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25001984 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29245440 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.15.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "0f63302294092f3002a42a58035cdc74" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "5664fcb0c595289208446ad0585c7f89" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "3fbabba0722025eec9bf45e0dcc9a888" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.15.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.15.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 16515072 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25001984 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29245440 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.16.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "11b2dbf1acb107236565a5568699be67" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "cabdd7fbd67a05165a446e24a3b75f30" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "e65cc2cf04fc8b48def615a54049a0ce" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.16.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.16.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 16515072 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25001984 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29245440 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.17.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "23eac41d62336c8ce2368db4937f5619" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "1c6b6b26be9b4b86bcb43f717cc5a6cd" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "c6c915e7161e0aec0ac1281f3f078de4" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.17.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.17.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 16515072 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25001984 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29245440 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.18.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "b14b4ffdf9cc9de407291591d5b7e674" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "ef9c84ac446ec00e8b6e1e0df2752744" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "cc1adfb2c61690f014dff810446b00c4" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.18.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.18.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 16515072 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25001984 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29245440 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.19.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "d17c3419fa97aa918af9b2540155a9a3" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "9cda1ec1a104ab3b81e66d6dd9ceb7da" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "bde1cb2f33f6e5f32695a045a45ed789" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.19.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.19.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 16515072 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25001984 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29245440 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.20.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "4ac0d0e57643cb2fc1a915b4ec1fb717" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "09d346819db52b20efc68ffa8613ee29" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "ac58754b9848631b127c81705005324f" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.20.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.20.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 16515072 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25001984 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29245440 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.21.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "0dbc3745bceecaae32855b02cea28ef3" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "86f1405352d3fdeabeb37e7ebb034c92" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "fe0b525b0de47d7ba6ca5fc6f22b3364" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.21.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.21.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 16515072 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25001984 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29245440 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.22.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "94f6e6a29fae3616516153cb8c1f930c" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "645464ebdba4bad73a412ec70c7952ac" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "03242f3874fa3d6750bd0f9e1e1867a3" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.22.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.22.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 16515072 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25001984 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29245440 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.23.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "5cd5aebbd01e74c1f8046d1fa0421c16" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "53d2c5e3693e6d0e83fef9c5d9de8d24" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "4cb685a2dc25e1a4c9b8589c28fdbe1a" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.23.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.23.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 16515072 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25001984 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29245440 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.24.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "f4da6ffb88809c3bda1700b8f6fe7b19" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "835fb96e5e2d32b6d7f20625cd981dab" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "ce0fe58232f2a22d381647552b7cae74" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.24.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.24.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 16515072 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25001984 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29245440 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.25.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "408d79a53adac0544978bb5c50fe208e" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "cea2d5fa4f998e028e0515392faffb08" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "4ee148938e4b44f6593fbe9d94281a74" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.25.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.25.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 16515072 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25001984 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29245440 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.26.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "e0914b304fcecdfc82687b4317e032c3" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "686e578bcfb0c6e88a818536302dc278" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "1a14d968d818d367418a2a9f44fc728a" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.26.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.26.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 16515072 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25001984 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29245440 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.27.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "664116ccbac6e47000f04fe9984ad2a9" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "986e808496c2f8b4ac4a0fa77a16d8df" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "455c5b7dc9c460ff5d6ab3ed3686d85f" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 272498688, "records": [ { "name": "lm_head.q_weight", "shape": [ 152064, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 272498688, "byteOffset": 0 } ], "md5sum": "7de582c38b84f3b7186282cca8af9d13" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 34062336, "records": [ { "name": "lm_head.q_scale", "shape": [ 152064, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 34062336, "byteOffset": 0 } ], "md5sum": "26dcf1e305f09cf2172649370821ca07" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 29266944, "records": [ { "name": "model.layers.27.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.27.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 16515072 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25001984 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29245440 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.norm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29259776 } ], "md5sum": "eed8a90298e1307880439dfabbf8adb9" } ] }