{ "metadata": { "ParamSize": 311, "ParamBytes": 965310464.0, "BitsPerParam": 5.002534272041053 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 116686848, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 151936, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 116686848, "byteOffset": 0 } ], "md5sum": "109a5e60ccd3722189055b62b5030f33" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 22330368, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 151936, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 14585856, "byteOffset": 0 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 14585856 }, { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 14588928 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 21470208 } ], "md5sum": "f8985bc995a90440519cff0252929d26" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.0.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.0.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.0.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "613bd35bd7abb017b5d1e86113e6a204" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.1.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.1.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.1.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "ee11b0a17a15199df570e0884a4f63c0" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.10.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.10.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.10.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "c72686f6e3fa52f0ee37fd8a7c48ba1b" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.11.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.11.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.11.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "11982cd8f209337b23e1db166964e091" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.12.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.12.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.12.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "31c16283df97d02e4b407a2495e46aae" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.13.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.13.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.13.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "4cc9ebe936dfd5b7e5c2eec85c84f769" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.14.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.14.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.14.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "d211178fc72cf6eae3ea8fdb5905fdb2" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.15.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.15.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.15.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "8423b4aec223a86994a5be1817e82cbf" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.16.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.16.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.16.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "923266fc3f9260bb805fab5279853797" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.17.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.17.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.17.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "9df2a78bac51540e1597669500ada35e" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.18.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.18.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.18.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "2c60199211894ea2902f05813938bef7" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.19.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.19.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.19.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "a0283ffd3634bd1d39c6eb4b45fe4aba" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.2.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.2.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.2.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "824c8d222f257874524df27077a649ac" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.20.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.20.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.20.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "2a410299270e597e91aa4e4d0f98f1f8" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.21.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.21.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.21.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "72fea9cac19c4584c8840941a3a71025" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.22.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.22.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.22.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "3fe86d8343637813b2777e48c76f5da0" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.23.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.23.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.23.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "e166053255ea77310fa6422a3766e4bb" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.24.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.24.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.24.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "9aecb8fb54dbfa4e176cbc4fcf2f9558" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.25.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.25.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.25.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "04b3c445a03e37c9f6597bb2e802494d" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.26.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.26.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.26.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "6fb5acd0ee48cf511576d63813d3d5f4" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.27.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.27.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.27.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "15f432e5b178e1a79bf9ca21d3704734" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.3.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.3.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.3.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "211ec6fd0ac0ab448b783f1deb3b39c7" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.4.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.4.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.4.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "7ca65717fc912b12b915c54f2fd77fcc" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.5.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.5.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.5.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "bee2c0df93d9fc41f9b06c69df4a98eb" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.6.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.6.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.6.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "d347d4ba4a1d1cb293c46ecbdccbfe5f" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.7.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.7.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.7.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "7fc2d411a777332f26abadb79e4a9ce8" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 26331136, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.8.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.8.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.8.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 }, { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 1536, 1120 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6881280, "byteOffset": 18589696 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 1536, 280 ], "dtype": "bfloat16", "format": "raw", "nbytes": 860160, "byteOffset": 25470976 } ], "md5sum": "268f44e9c8e82a38167664b93120715a" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 18589696, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 17920, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13762560, "byteOffset": 0 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 17920, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1720320, "byteOffset": 13762560 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 15482880 }, { "name": "model.layers.9.self_attn.c_attn.bias", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 15485952 }, { "name": "model.layers.9.self_attn.c_attn.q_weight", "shape": [ 2048, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1572864, "byteOffset": 15490048 }, { "name": "model.layers.9.self_attn.c_attn.q_scale", "shape": [ 2048, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 196608, "byteOffset": 17062912 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 1536, 192 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 1179648, "byteOffset": 17259520 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 1536, 48 ], "dtype": "bfloat16", "format": "raw", "nbytes": 147456, "byteOffset": 18439168 }, { "name": "model.norm.weight", "shape": [ 1536 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3072, "byteOffset": 18586624 } ], "md5sum": "4c5596114473f2398c6a5ea0903ab400" } ] }