{ "metadata": { "ParamSize": 245, "ParamBytes": 1030231040.0, "BitsPerParam": 4.500787767033453 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 40960000, "records": [ { "name": "lm_head.q_weight", "shape": [ 32000, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 40960000, "byteOffset": 0 } ], "md5sum": "c7d59a2c38a6b98b426ae1b3a7b42c24" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 40960000, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 32000, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 40960000, "byteOffset": 0 } ], "md5sum": "1627d303b40b5e0a3ad71091018cb7ec" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 13824, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "1326e122c3d3fa87f3dcb9b8b74e1d7b" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 31636480, "records": [ { "name": "lm_head.q_scale", "shape": [ 32000, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120000, "byteOffset": 0 }, { "name": "model.embed_tokens.q_scale", "shape": [ 32000, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120000, "byteOffset": 5120000 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 10240000 }, { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 2560, 864 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 10245120 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 2560, 216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1105920, "byteOffset": 19092480 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 13824, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 20198400 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 22410240 }, { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 3840, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4915200, "byteOffset": 22415360 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 3840, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 614400, "byteOffset": 27330560 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 2560, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 27944960 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 2560, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 31221760 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 31631360 } ], "md5sum": "8a6a0bfed389edd426bced66516b7b1a" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 29864960, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 2560, 864 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 2560, 216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1105920, "byteOffset": 8847360 }, { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 13824, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 9953280 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 13824, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 27648000 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 29859840 } ], "md5sum": "076341535abf83920b13d3c4c6357aaf" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 13824, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "0a3d02d8b09ca8a5409d0ebe41f60915" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 30612480, "records": [ { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 3840, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4915200, "byteOffset": 0 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 3840, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 614400, "byteOffset": 4915200 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 2560, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 5529600 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 2560, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 8806400 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 9216000 }, { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 2560, 864 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 9221120 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 2560, 216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1105920, "byteOffset": 18068480 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 13824, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 19174400 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 21386240 }, { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 3840, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4915200, "byteOffset": 21391360 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 3840, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 614400, "byteOffset": 26306560 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 2560, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 26920960 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 2560, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 30197760 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 30607360 } ], "md5sum": "d5c72edbb7ec0ab2a20f132c8f976ee7" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 29864960, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 2560, 864 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 2560, 216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1105920, "byteOffset": 8847360 }, { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 13824, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 9953280 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 13824, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 27648000 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 29859840 } ], "md5sum": "c560dbc33f52ec12062867b9cc988374" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 13824, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "f49ed01e90b45a827b239c7b879e9a16" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 30612480, "records": [ { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 3840, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4915200, "byteOffset": 0 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 3840, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 614400, "byteOffset": 4915200 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 2560, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 5529600 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 2560, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 8806400 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 9216000 }, { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 2560, 864 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 9221120 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 2560, 216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1105920, "byteOffset": 18068480 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 13824, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 19174400 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 21386240 }, { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 3840, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4915200, "byteOffset": 21391360 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 3840, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 614400, "byteOffset": 26306560 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 2560, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 26920960 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 2560, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 30197760 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 30607360 } ], "md5sum": "1f47830360b2d3237dde7993b1d797a6" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 29864960, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 2560, 864 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 2560, 216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1105920, "byteOffset": 8847360 }, { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 13824, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 9953280 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 13824, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 27648000 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 29859840 } ], "md5sum": "ffebb7138b228c9c2bcd0d8e4ef254fc" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 13824, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "e0aa147f1b2dbd493298c0616626f924" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 30612480, "records": [ { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 3840, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4915200, "byteOffset": 0 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 3840, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 614400, "byteOffset": 4915200 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 2560, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 5529600 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 2560, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 8806400 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 9216000 }, { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 2560, 864 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 9221120 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 2560, 216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1105920, "byteOffset": 18068480 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 13824, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 19174400 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 21386240 }, { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 3840, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4915200, "byteOffset": 21391360 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 3840, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 614400, "byteOffset": 26306560 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 2560, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 26920960 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 2560, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 30197760 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 30607360 } ], "md5sum": "a91f189c114c5318bb3aebad201a5951" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 29864960, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 2560, 864 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 2560, 216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1105920, "byteOffset": 8847360 }, { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 13824, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 9953280 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 13824, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 27648000 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 29859840 } ], "md5sum": "d86c257917fdeafcbeb6e35275c76f0f" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 13824, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "3a5f78e351d7f00d659d2429fa2167e9" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 30612480, "records": [ { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 3840, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4915200, "byteOffset": 0 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 3840, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 614400, "byteOffset": 4915200 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 2560, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 5529600 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 2560, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 8806400 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 9216000 }, { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 2560, 864 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 9221120 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 2560, 216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1105920, "byteOffset": 18068480 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 13824, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 19174400 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 21386240 }, { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 3840, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4915200, "byteOffset": 21391360 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 3840, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 614400, "byteOffset": 26306560 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 2560, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 26920960 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 2560, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 30197760 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 30607360 } ], "md5sum": "21dd5d226944c5b561c1ce43ba7dcce2" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 29864960, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 2560, 864 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 2560, 216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1105920, "byteOffset": 8847360 }, { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 13824, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 9953280 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 13824, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 27648000 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 29859840 } ], "md5sum": "443a5625dbd4c1ec6d63525fec56e042" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 13824, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "b224bfc9ea48a3903cf9f35fa09c2b69" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 30612480, "records": [ { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 3840, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4915200, "byteOffset": 0 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 3840, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 614400, "byteOffset": 4915200 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 2560, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 5529600 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 2560, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 8806400 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 9216000 }, { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 2560, 864 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 9221120 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 2560, 216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1105920, "byteOffset": 18068480 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 13824, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 19174400 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 21386240 }, { "name": "model.layers.18.self_attn.qkv_proj.q_weight", "shape": [ 3840, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4915200, "byteOffset": 21391360 }, { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 3840, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 614400, "byteOffset": 26306560 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 2560, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 26920960 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 2560, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 30197760 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 30607360 } ], "md5sum": "b27f36814d914bab643bae0847c2ec74" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 29864960, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 2560, 864 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 2560, 216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1105920, "byteOffset": 8847360 }, { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 13824, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 9953280 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 13824, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 27648000 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 29859840 } ], "md5sum": "f6f1eb5f91a37ac40810c51733f40b82" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 13824, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "fc278b8c98802713f235700f726f5d3c" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 30612480, "records": [ { "name": "model.layers.19.self_attn.qkv_proj.q_weight", "shape": [ 3840, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4915200, "byteOffset": 0 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 3840, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 614400, "byteOffset": 4915200 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 2560, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 5529600 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 2560, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 8806400 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 9216000 }, { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 2560, 864 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 9221120 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 2560, 216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1105920, "byteOffset": 18068480 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 13824, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 19174400 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 21386240 }, { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 3840, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4915200, "byteOffset": 21391360 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 3840, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 614400, "byteOffset": 26306560 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 2560, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 26920960 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 2560, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 30197760 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 30607360 } ], "md5sum": "ab1d348da4351cebf1e583b66fa5177a" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 29864960, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 2560, 864 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 2560, 216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1105920, "byteOffset": 8847360 }, { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 13824, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 9953280 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 13824, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 27648000 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 29859840 } ], "md5sum": "99fc3aa88d3923b543fff9990d902056" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 13824, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "175d44b78a472ee1498923d93566f3eb" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 30612480, "records": [ { "name": "model.layers.20.self_attn.qkv_proj.q_weight", "shape": [ 3840, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4915200, "byteOffset": 0 }, { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 3840, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 614400, "byteOffset": 4915200 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 2560, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 5529600 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 2560, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 8806400 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 9216000 }, { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 2560, 864 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 9221120 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 2560, 216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1105920, "byteOffset": 18068480 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 13824, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 19174400 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 21386240 }, { "name": "model.layers.21.self_attn.qkv_proj.q_weight", "shape": [ 3840, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4915200, "byteOffset": 21391360 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 3840, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 614400, "byteOffset": 26306560 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 2560, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 26920960 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 2560, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 30197760 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 30607360 } ], "md5sum": "17d5babe20dd83c71c3992d662aba5e7" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 29864960, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 2560, 864 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 2560, 216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1105920, "byteOffset": 8847360 }, { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 13824, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 9953280 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 13824, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 27648000 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 29859840 } ], "md5sum": "38e0ee407d0d882018cbc9eb5d9541f4" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 13824, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "aa55b3d4e04792898628f9e56dc662bb" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 30612480, "records": [ { "name": "model.layers.22.self_attn.qkv_proj.q_weight", "shape": [ 3840, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4915200, "byteOffset": 0 }, { "name": "model.layers.22.self_attn.qkv_proj.q_scale", "shape": [ 3840, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 614400, "byteOffset": 4915200 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 2560, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 5529600 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 2560, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 8806400 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 9216000 }, { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 2560, 864 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 9221120 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 2560, 216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1105920, "byteOffset": 18068480 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 13824, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 19174400 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 21386240 }, { "name": "model.layers.23.self_attn.qkv_proj.q_weight", "shape": [ 3840, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4915200, "byteOffset": 21391360 }, { "name": "model.layers.23.self_attn.qkv_proj.q_scale", "shape": [ 3840, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 614400, "byteOffset": 26306560 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 2560, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 26920960 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 2560, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 30197760 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 30607360 } ], "md5sum": "05183df776cbc713fc5c37782e735e9d" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 29864960, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 2560, 864 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 2560, 216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1105920, "byteOffset": 8847360 }, { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 13824, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 9953280 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 13824, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 27648000 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 29859840 } ], "md5sum": "d78cd51477ab6e8eb3a052229600ee39" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 13824, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "872661df73a84e8f63f0ec2cb7bc96c6" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 30612480, "records": [ { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 3840, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4915200, "byteOffset": 0 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 3840, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 614400, "byteOffset": 4915200 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 2560, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 5529600 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 2560, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 8806400 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 9216000 }, { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 2560, 864 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 9221120 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 2560, 216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1105920, "byteOffset": 18068480 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 13824, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 19174400 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 21386240 }, { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 3840, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4915200, "byteOffset": 21391360 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 3840, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 614400, "byteOffset": 26306560 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 2560, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 26920960 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 2560, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 30197760 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 30607360 } ], "md5sum": "1fee6c6b250a141e8f86f3fae5008381" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 29864960, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 2560, 864 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 2560, 216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1105920, "byteOffset": 8847360 }, { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 13824, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 9953280 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 13824, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 27648000 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 29859840 } ], "md5sum": "4b8f9558e8c37812bc3689c1d2d4edd3" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 13824, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "6b8be47d21f2a55e27922b783680b902" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 30612480, "records": [ { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 3840, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4915200, "byteOffset": 0 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 3840, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 614400, "byteOffset": 4915200 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 2560, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 5529600 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 2560, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 8806400 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 9216000 }, { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 2560, 864 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 9221120 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 2560, 216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1105920, "byteOffset": 18068480 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 13824, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 19174400 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 21386240 }, { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 3840, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4915200, "byteOffset": 21391360 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 3840, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 614400, "byteOffset": 26306560 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 2560, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 26920960 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 2560, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 30197760 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 30607360 } ], "md5sum": "44b9766913c48317340097f97a2362ed" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 29864960, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 2560, 864 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 2560, 216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1105920, "byteOffset": 8847360 }, { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 13824, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 9953280 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 13824, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 27648000 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 29859840 } ], "md5sum": "288ea39a782ae84a8db25d75a89b60d7" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 17694720, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 13824, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 0 } ], "md5sum": "de9e57882e6f58a970502688e3d41623" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 30612480, "records": [ { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 3840, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4915200, "byteOffset": 0 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 3840, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 614400, "byteOffset": 4915200 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 2560, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 5529600 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 2560, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 8806400 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 9216000 }, { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 2560, 864 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 9221120 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 2560, 216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1105920, "byteOffset": 18068480 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 13824, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 19174400 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 21386240 }, { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 3840, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4915200, "byteOffset": 21391360 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 3840, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 614400, "byteOffset": 26306560 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 2560, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 26920960 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 2560, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 30197760 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 30607360 } ], "md5sum": "a8e73d93005869316dfce8671d13a436" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 29864960, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 2560, 864 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 2560, 216 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1105920, "byteOffset": 8847360 }, { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 13824, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 17694720, "byteOffset": 9953280 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 13824, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2211840, "byteOffset": 27648000 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 29859840 } ], "md5sum": "bc79518a710482d3b7855ebe48bc3b36" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 9221120, "records": [ { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 3840, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 4915200, "byteOffset": 0 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 3840, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 614400, "byteOffset": 4915200 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 2560, 320 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 5529600 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 2560, 80 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 409600, "byteOffset": 8806400 }, { "name": "model.norm.weight", "shape": [ 2560 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5120, "byteOffset": 9216000 } ], "md5sum": "c6cb1789e90845167679a5bfda8494c4" } ] }