{ "metadata": { "ParamSize": 773, "ParamBytes": 20478611456.0, "BitsPerParam": 3.6844888186260407 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 388956160, "records": [ { "name": "lm_head.q_weight", "shape": [ 151936, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 388956160, "byteOffset": 0 } ], "md5sum": "fdfb3f93dc1b4d46cc8bc33fc698cb05" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 48619520, "records": [ { "name": "lm_head.q_scale", "shape": [ 151936, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 48619520, "byteOffset": 0 } ], "md5sum": "0550e956295bf480ca54636812a29fad" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.62.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "5008fa10454d2d20329ee85d66d6c492" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.62.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "072808ce644ce1db3acb67ae09c7718b" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.63.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "a6fcf42c30dc63098bfae429ecb5fb27" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.63.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "71fd4ddac6f7a3f7b8706c57c77a055b" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 32798720, "records": [ { "name": "model.layers.62.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 0 }, { "name": "model.layers.62.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 10240 }, { "name": "model.layers.62.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8202240 }, { "name": "model.layers.62.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24586240 }, { "name": "model.layers.63.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24596480 }, { "name": "model.layers.63.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 24606720 } ], "md5sum": "2d0fefc2044d98efb9dd73964d66abfe" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.63.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "cd3e75321734e89b2abd8078c91d15d9" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.63.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "a17235de79b8234dcf3e78b0c04f64e9" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 388956160, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 151936, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 388956160, "byteOffset": 0 } ], "md5sum": "48d51b72408c9a13d6c8dfb6bdeb14a7" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 48619520, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 151936, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 48619520, "byteOffset": 0 } ], "md5sum": "d1b1c4be39b05d32b448452486e69151" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "84b6a01b196d2e07c99cedd71c1bbd06" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "6f7a09648e0384140caeb632e654bb90" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 30505472, "records": [ { "name": "model.layers.63.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 0 }, { "name": "model.layers.63.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 16384000 }, { "name": "model.layers.63.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 16394240 }, { "name": "model.layers.63.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 16394496 }, { "name": "model.layers.63.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19671296 }, { "name": "model.layers.63.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 22292736 }, { "name": "model.norm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22292992 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22303232 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 22313472 } ], "md5sum": "f6bf0cc47f434c09cb5b3a000d5c700e" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.0.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "c38cc31c5750bf3ee81014713cec24d2" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "b9396a8089e97623c3689d15d8196f08" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "3bef37ff56a5749687f6a93b981b8b35" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "3c2d661f4dfde0d2f2f5efc1f73eb29d" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 30495232, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 0 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 16384000 }, { "name": "model.layers.0.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 16394240 }, { "name": "model.layers.0.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 16394496 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19671296 }, { "name": "model.layers.0.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 22292736 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22292992 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 22303232 } ], "md5sum": "d7657ed96f4ba7889a7cf43d0a3c747a" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.1.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "67050ac0ab720547983561c8a31dd39d" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "e0952f3a13ca9611a744c156ce5807db" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "a936e5d43d3486b0d0359fc6d3b62734" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 22292992, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 0 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 16384000 }, { "name": "model.layers.1.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 16394240 }, { "name": "model.layers.1.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 16394496 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19671296 }, { "name": "model.layers.1.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 22292736 } ], "md5sum": "2040989f2b62e2cec5ec47460543dee7" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.2.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "a22a803e759d83e998d92e25b1d5b6b2" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "7a7054ae310bac83510e00af7a7397bd" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "40d5f022527d740b04fbffbc3d0c716b" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "632281049322e54c6734eb2dbc419c69" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 30484992, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 0 }, { "name": "model.layers.2.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 16384000 }, { "name": "model.layers.2.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 16384256 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19661056 }, { "name": "model.layers.2.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 22282496 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22282752 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 22292992 } ], "md5sum": "1b5d1dea6889abe17106cdaa450d3f9d" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "20f190f8f2d4a08fdd1e7c6555d28877" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "746edb1c3a6016c85ec1a6685d42d098" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 24596480, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 0 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 16384000 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 16394240 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 16404480 } ], "md5sum": "83465a41cfb88c5f046ef22d31b8ccdd" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.11.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "a1daf7175ea4c471627fa951f98e9c89" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "17acbdbfcbe18be488e17dcc79875607" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "e6ba6dd66b4ffc614d4d6731433331a0" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "5f2e18f441686be777033e42230410b6" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 30495232, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 0 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 16384000 }, { "name": "model.layers.11.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 16394240 }, { "name": "model.layers.11.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 16394496 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19671296 }, { "name": "model.layers.11.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 22292736 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22292992 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 22303232 } ], "md5sum": "f6f5d8241a8a48c70dbbe410740a84b5" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.12.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "b3af81dd05f4e46017607c769a353bf1" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "126839476e9a8fbc49e8e89e5bf44f2b" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "9333272d14f028e6934b251066a66738" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "c6000c79ae9c12624eea0ba994f8f78f" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 30495232, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 0 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 16384000 }, { "name": "model.layers.12.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 16394240 }, { "name": "model.layers.12.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 16394496 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19671296 }, { "name": "model.layers.12.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 22292736 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22292992 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 22303232 } ], "md5sum": "48158e7ed7276e28eb33b3f6d7ef07c0" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.13.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "07bfb7eb1e39986393778ac8c3366448" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "06be09a0cadacdbb41a113c6a65888cf" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "35c4e34d8bcf4bc2ad91f7dd27c37e81" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 22292992, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 0 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 16384000 }, { "name": "model.layers.13.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 16394240 }, { "name": "model.layers.13.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 16394496 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19671296 }, { "name": "model.layers.13.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 22292736 } ], "md5sum": "23b956c52bbc482f95af234979bb9c2d" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.14.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "aeb9d59823a605ad4db073e1263208fd" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "6144b02e3d98c16e57be903c632e2330" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.10.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "26bfa937f9ff196d22afed96b3923f05" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "dc43c005c2519257be120df6c5acb3f6" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "26138dc8644f6290882da49479cddc4d" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 28191744, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 16384000 }, { "name": "model.layers.14.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 16384256 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19661056 }, { "name": "model.layers.14.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 22282496 }, { "name": "model.layers.10.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 22282752 }, { "name": "model.layers.10.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 22283008 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 25559808 }, { "name": "model.layers.10.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 28181248 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28181504 } ], "md5sum": "2d7915647aaa8691baa8518abe6a5f44" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "da3a013217703af2f9c0a7812f2a1d4d" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "cdfcdccccde12d4840aa8ba153a902d4" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "967dbe91ca09ac5b54e682b3284d4d16" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 32788480, "records": [ { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24586240 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 24596480 } ], "md5sum": "c64bf1f35216d5985fc42d97367d96b3" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.7.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "087e57c4548c3ba1dce0d6338f22dfc4" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "53937aa4db406d99996fee45f2647d4f" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "86f2f4d9c88d13037c51d3403497ceb9" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "57ed20207cf45a2d1296c5087792bdd9" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 30495232, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 0 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 16384000 }, { "name": "model.layers.7.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 16394240 }, { "name": "model.layers.7.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 16394496 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19671296 }, { "name": "model.layers.7.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 22292736 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22292992 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 22303232 } ], "md5sum": "8ed65dbc9a6d260f3fc1be7aaceaeb96" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.8.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "b435c99241d92e7d79094117580ceb2d" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "26c96fd5f0180a463fdedb0ea26482c1" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "240308067ba5b81baa651191c0b5d65e" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "9b23e4fb12de77320faedf04ccc4dd2c" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 30495232, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 0 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 16384000 }, { "name": "model.layers.8.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 16394240 }, { "name": "model.layers.8.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 16394496 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19671296 }, { "name": "model.layers.8.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 22292736 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22292992 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 22303232 } ], "md5sum": "183a5e3a3575307cbb243356f43bdb2c" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.9.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "ba0cd268503344040a55a08d1b394a93" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "ff426720b916758d8a07fa49f9d9c8fc" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "39293d31c6ad701678bf3b0ca4827273" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "deea5886ee56b547f07b0a12a405fab8" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 30515712, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 0 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 16384000 }, { "name": "model.layers.9.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 16394240 }, { "name": "model.layers.9.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 16394496 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19671296 }, { "name": "model.layers.9.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 22292736 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22292992 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 22303232 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30495232 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30505472 } ], "md5sum": "4b566771957c5b0fdb839ad37051da10" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "fc703961d371aef975a73105df401d69" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.15.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "ed9f87f4b4ea6d472000ae84b98786f4" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "d7974035970212c6e86f188a51a4981f" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "789f3ed0f45e2ea7913d406f23fcf45d" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 30495232, "records": [ { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.15.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.15.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.15.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 } ], "md5sum": "717d8bf3e8f5f4847b614cb9077ef423" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "8845abfaab60993574882fe74cd6a52e" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.16.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "a8ac9ed519ba24504b8192d352ed9f72" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "2380c34ed6a7f1b3529fd2ce7b41f706" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "ac1eb506b5edad6be90594683d0b7ab4" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 30495232, "records": [ { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.16.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.16.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.16.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 } ], "md5sum": "9bde70dc5fe9fc9ec2efdcabe6c2e650" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "701db814e7b456dc51cd328407c9c5a6" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.17.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "3d52dce5ae45d6e620d8c1f38934eccf" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "3df42ad3c27750810bffa47305487d9f" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "b76d4369efc6bc7fe408e77350a45d09" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 30484992, "records": [ { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.17.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.17.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.17.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 } ], "md5sum": "9a9b46ef811ccfd8e3f5adebe017cf9e" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.18.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "93ad443aa7755978dc349e3e433d3e52" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "1f5616a5a0848e6ae2107e9b9cddfa33" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "91761682a1fff853c689642819bd1c30" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "1033d38fc683c5692c2145a5d626aaa8" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 30505472, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 0 }, { "name": "model.layers.18.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 16384000 }, { "name": "model.layers.18.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 16384256 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19661056 }, { "name": "model.layers.18.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 22282496 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22282752 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 22292992 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30495232 } ], "md5sum": "ec96ae9180eae690f2b4fb430b235eb7" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "226c00ad310d6c91cc127e5c78feed55" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.19.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "1dd275e4de45399ded0308c7571279ea" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "f653fc23892004d4d4ff4dfe5b089c2a" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "025e69d74005ef1b000a528c58546cf4" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 30495232, "records": [ { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.19.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.19.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.19.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 } ], "md5sum": "929ca626c0689f421fa7ad10bdce0bfc" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "6b5ac81d9cae17dca57966aa98e6f294" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.20.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "d997c8a4161288de3c698cabb8356725" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "dbc44d7cae594d7e9e647338775f183f" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "73e650f5ae293b152c397f2dc30804f0" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 30495232, "records": [ { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.20.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.20.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.20.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 } ], "md5sum": "87d8c2f03d013ad3a2ba33270a6be9d4" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "8cf1d811039fd8ef578a19ad76f8d346" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.21.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "933fea71f7a95a240d07938fece05ef6" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "8c3109bec334463e8036f725b0896c21" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "bfdd91b034829519eb4a870a716f2f99" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 30484992, "records": [ { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.21.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.21.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.21.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 } ], "md5sum": "a65da903c7e9287ed7b9c82d70950cfb" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.22.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "d48380295059e27fee5e085be61cf523" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "8641e5dfeb87f33f633b4c4f26f81b28" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "3e8e6f88a6434fe01603a1fc4f4d0cad" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "7c8b8b14c82fdafcd2ecf9c13a91d24b" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 30505472, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 0 }, { "name": "model.layers.22.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 16384000 }, { "name": "model.layers.22.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 16384256 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19661056 }, { "name": "model.layers.22.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 22282496 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22282752 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 22292992 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30495232 } ], "md5sum": "762a00d8562de40550690697bd5fb40b" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "70281c20e69bbd608f8bda7db7098a2a" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.3.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "d572633a0badd3ab9c350dfa2d0802a9" }, { "dataPath": "params_shard_112.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "1746b35c6ad30371246611d485ed2a5d" }, { "dataPath": "params_shard_113.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "6792375251598697d2ea9aeb7323394c" }, { "dataPath": "params_shard_114.bin", "format": "raw-shard", "nbytes": 30495232, "records": [ { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.3.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.3.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.3.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 } ], "md5sum": "13cd2c74c05a9066ab14463454e29510" }, { "dataPath": "params_shard_115.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "7898a8e87bebb3e626aa4f9863b92a6b" }, { "dataPath": "params_shard_116.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.4.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "37eefd3ba3cad83a6d9275867ff5bd39" }, { "dataPath": "params_shard_117.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "9ba82c73b7d9b4001ff1c199722ebe7e" }, { "dataPath": "params_shard_118.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "4dc9e062cf9f1b0c4d92af1360e9f42b" }, { "dataPath": "params_shard_119.bin", "format": "raw-shard", "nbytes": 30495232, "records": [ { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.4.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.4.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.4.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 } ], "md5sum": "a8c4b8bcb78655b2c0e07d025fe427c0" }, { "dataPath": "params_shard_120.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "657d12e6dac010be4ffb1e0eff85525f" }, { "dataPath": "params_shard_121.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.5.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "b64e3f2829a661f85aa4f1d145702df7" }, { "dataPath": "params_shard_122.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "f7423b217363588fdc659ec340140ccc" }, { "dataPath": "params_shard_123.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.6.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "44db1b8365a71dd1e3843c47428d435e" }, { "dataPath": "params_shard_124.bin", "format": "raw-shard", "nbytes": 30485248, "records": [ { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.5.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.5.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.5.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 }, { "name": "model.layers.6.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484992 } ], "md5sum": "2de06e31c3c5c83e73e96cccde21a901" }, { "dataPath": "params_shard_125.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "28b092f1c447414518e0b55f5572a57f" }, { "dataPath": "params_shard_126.bin", "format": "raw-shard", "nbytes": 26880256, "records": [ { "name": "model.layers.6.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 0 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 3276800 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 24248320 }, { "name": "model.layers.6.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 26869760 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 26870016 } ], "md5sum": "ca780635e8e6c971e9229dca80f7225d" }, { "dataPath": "params_shard_127.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "7022b1d788e190faaa8d179fa159efe7" }, { "dataPath": "params_shard_128.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "e628e1554827db95b154efe69e70360e" }, { "dataPath": "params_shard_129.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.23.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "b2046a88ef1885bdc8ce75c2965156fa" }, { "dataPath": "params_shard_130.bin", "format": "raw-shard", "nbytes": 32798976, "records": [ { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8192000 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8202240 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 8212480 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 16404480 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 32788480 }, { "name": "model.layers.23.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 32798720 } ], "md5sum": "2331319821a1f141ff46dca7a8f30ddb" }, { "dataPath": "params_shard_131.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "a8986d63ce95d33e19f3275f131ab038" }, { "dataPath": "params_shard_132.bin", "format": "raw-shard", "nbytes": 26880256, "records": [ { "name": "model.layers.23.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 0 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 3276800 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 24248320 }, { "name": "model.layers.23.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 26869760 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 26870016 } ], "md5sum": "383d7a77b38f633ff1e6bbb9665d9616" }, { "dataPath": "params_shard_133.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "740036a22c49042a9d1a4c6034556605" }, { "dataPath": "params_shard_134.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.24.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "9e6827dce7c04bc18920167894c73c4f" }, { "dataPath": "params_shard_135.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "87db26fded86637c820b6c8c582cc3ed" }, { "dataPath": "params_shard_136.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "efd7a2ceb7594a51e8e301afe4b17cd7" }, { "dataPath": "params_shard_137.bin", "format": "raw-shard", "nbytes": 30495232, "records": [ { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.24.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.24.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.24.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 } ], "md5sum": "9eda48777e2f13c668eb8b4bb676a64e" }, { "dataPath": "params_shard_138.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "96aebf3a5a7badc78f023b45a648cc8f" }, { "dataPath": "params_shard_139.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.25.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "1ef6189b08b500c007891e091a9ea1d7" }, { "dataPath": "params_shard_140.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "046bb5599004d1b6fe5a4b35a8e1b178" }, { "dataPath": "params_shard_141.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "030701c341785a8c4a5548f0dd997c2f" }, { "dataPath": "params_shard_142.bin", "format": "raw-shard", "nbytes": 30484992, "records": [ { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.25.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.25.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.25.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 } ], "md5sum": "fdd24188fdd743b62f022ecbeb9fc6ff" }, { "dataPath": "params_shard_143.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.26.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "c85ee1b88a08e888ea3812ac8ddeb32b" }, { "dataPath": "params_shard_144.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "5679a524a5a3b8abe84ef6f7c6a79326" }, { "dataPath": "params_shard_145.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "bcd0bc93398258c7175bccaf0027ed69" }, { "dataPath": "params_shard_146.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "b36962c652a75ca6f8c9a8754247cf6a" }, { "dataPath": "params_shard_147.bin", "format": "raw-shard", "nbytes": 30505472, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 0 }, { "name": "model.layers.26.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 16384000 }, { "name": "model.layers.26.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 16384256 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19661056 }, { "name": "model.layers.26.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 22282496 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22282752 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 22292992 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30495232 } ], "md5sum": "e485ebfa93ecca06389644b190047f55" }, { "dataPath": "params_shard_148.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "dc5de52c6c52a4b26426525d142d5eeb" }, { "dataPath": "params_shard_149.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.27.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "c2061c2cdb1750f26e2f5b69bb367f62" }, { "dataPath": "params_shard_150.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "9acba53dd498f4791a434b54571ad903" }, { "dataPath": "params_shard_151.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "06358006a737d1ecc5102a0f18619a36" }, { "dataPath": "params_shard_152.bin", "format": "raw-shard", "nbytes": 30495232, "records": [ { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.27.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.27.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.27.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 } ], "md5sum": "07356cce0f230b8ac8cdc3e181b1f3b9" }, { "dataPath": "params_shard_153.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "396db9e150df924fbe5cb68812214cef" }, { "dataPath": "params_shard_154.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.28.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "9c009b2d08fa0a518add799f4cb04b21" }, { "dataPath": "params_shard_155.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "4b6ee0e9868a826b9833cf5b539b8ab3" }, { "dataPath": "params_shard_156.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "9d4719832e03d2e08df8ae60c2bb6ee8" }, { "dataPath": "params_shard_157.bin", "format": "raw-shard", "nbytes": 30495232, "records": [ { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.28.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.28.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.28.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 } ], "md5sum": "e563759e42144de331f9dca011ddf46b" }, { "dataPath": "params_shard_158.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "c4cba0a4d361ad9a0be7f5e64318f123" }, { "dataPath": "params_shard_159.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.29.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "94d7c7caad55be2778ae984b686c4c73" }, { "dataPath": "params_shard_160.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "55f246c47a35d9e19f9a44ebd4cb8de3" }, { "dataPath": "params_shard_161.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "611f175cf6e7eca6277c2f7f2a3e4f50" }, { "dataPath": "params_shard_162.bin", "format": "raw-shard", "nbytes": 30484992, "records": [ { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.29.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.29.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.29.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 } ], "md5sum": "d75ec1c69f88aeb47210b40bda185d6d" }, { "dataPath": "params_shard_163.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.30.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "2a51d5b0b000ed8ea382600d1972e62a" }, { "dataPath": "params_shard_164.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "7fd67f9c4ed24354db7312f095a80337" }, { "dataPath": "params_shard_165.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "d0ab0fef0f370e802b7d0a418c6edd4d" }, { "dataPath": "params_shard_166.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "23be935395e2e7c20651a6dae9882748" }, { "dataPath": "params_shard_167.bin", "format": "raw-shard", "nbytes": 30505472, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 0 }, { "name": "model.layers.30.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 16384000 }, { "name": "model.layers.30.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 16384256 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19661056 }, { "name": "model.layers.30.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 22282496 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22282752 }, { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 22292992 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30495232 } ], "md5sum": "c4825fb514428a10b7616c6d6f2079af" }, { "dataPath": "params_shard_168.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "06f23c571893d74498903b076a208b93" }, { "dataPath": "params_shard_169.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.31.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "cacc7aae285715611a80a58381288155" }, { "dataPath": "params_shard_170.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "2404a7a7b5750f4ebb5e8734ff198e1a" }, { "dataPath": "params_shard_171.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.32.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "993c844a37d2a83e97b5a80748597bcc" }, { "dataPath": "params_shard_172.bin", "format": "raw-shard", "nbytes": 30495232, "records": [ { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.31.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.31.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.31.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 }, { "name": "model.layers.32.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 } ], "md5sum": "9e68b2bb547083faff65b76541915eac" }, { "dataPath": "params_shard_173.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "663d5c5dfdf219b70582cb06745b5e17" }, { "dataPath": "params_shard_174.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.32.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "8f9782f2971bef8565b2bf3f254fe45b" }, { "dataPath": "params_shard_175.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.32.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "6eef29e84ef9b2f0cbe22bd84087d077" }, { "dataPath": "params_shard_176.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.33.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "7ec9ee485f868644e2a8ce3da2bfa554" }, { "dataPath": "params_shard_177.bin", "format": "raw-shard", "nbytes": 30495232, "records": [ { "name": "model.layers.32.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.32.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.32.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.32.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.32.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.32.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.32.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 }, { "name": "model.layers.33.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 } ], "md5sum": "523dc977bef7c75cb22f4c12a9e24364" }, { "dataPath": "params_shard_178.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "a630cbd28612ea09622f279fd07531ae" }, { "dataPath": "params_shard_179.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.33.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "7a691ff7a467b10da608416e00acc9a2" }, { "dataPath": "params_shard_180.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.33.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "c4f7fa21a2f8b12b7a437b797f4af681" }, { "dataPath": "params_shard_181.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "77a68d5b86934e1d422f6197dbaa08c6" }, { "dataPath": "params_shard_182.bin", "format": "raw-shard", "nbytes": 30484992, "records": [ { "name": "model.layers.33.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.33.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.33.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.33.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.33.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.33.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.33.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 } ], "md5sum": "0b16d33bb7cd1051f1923df1a5395254" }, { "dataPath": "params_shard_183.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.34.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "ff45f42664c590c2f9ab3051a190a068" }, { "dataPath": "params_shard_184.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.34.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "a36d05e66a8abc4d8fb9c930c920056a" }, { "dataPath": "params_shard_185.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.34.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "dd3edbf2493070ddcabec188e3d38604" }, { "dataPath": "params_shard_186.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.35.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "bf55bf89638a843b379bb934facc4cb6" }, { "dataPath": "params_shard_187.bin", "format": "raw-shard", "nbytes": 30505472, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 0 }, { "name": "model.layers.34.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 16384000 }, { "name": "model.layers.34.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 16384256 }, { "name": "model.layers.34.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19661056 }, { "name": "model.layers.34.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 22282496 }, { "name": "model.layers.34.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22282752 }, { "name": "model.layers.34.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 22292992 }, { "name": "model.layers.34.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 }, { "name": "model.layers.35.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30495232 } ], "md5sum": "9386462dfdf1fc84511e9a3302b26efd" }, { "dataPath": "params_shard_188.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "86074b6b22a57cbf547b0a6dd5f8c57b" }, { "dataPath": "params_shard_189.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.35.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "3a0fce34e1e1b26c0833b3f896b805d8" }, { "dataPath": "params_shard_190.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.35.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "7302cbe75726f40558897b63ab907edb" }, { "dataPath": "params_shard_191.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.36.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "ac3f3e886cca843c55fbafa73935e812" }, { "dataPath": "params_shard_192.bin", "format": "raw-shard", "nbytes": 30495232, "records": [ { "name": "model.layers.35.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.35.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.35.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.35.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.35.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.35.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.35.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 }, { "name": "model.layers.36.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 } ], "md5sum": "f0c12f1d30e9b198a6a3ae26389f5215" }, { "dataPath": "params_shard_193.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "4dc0c5b5c487cd82c117197cc19ae99f" }, { "dataPath": "params_shard_194.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.36.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "fbd6989ffd144bd5869ffc39829f838b" }, { "dataPath": "params_shard_195.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.36.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "4a5233351f2293f6b7926baae68e20c4" }, { "dataPath": "params_shard_196.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.37.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "efe1c346ea252f7024581520e5a7feb7" }, { "dataPath": "params_shard_197.bin", "format": "raw-shard", "nbytes": 30495232, "records": [ { "name": "model.layers.36.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.36.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.36.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.36.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.36.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.36.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.36.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 }, { "name": "model.layers.37.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 } ], "md5sum": "6ccc5d62937bbd91be53a8b020c1d61d" }, { "dataPath": "params_shard_198.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.37.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "6a9e079c4d3deb9c7b7c508084ae7559" }, { "dataPath": "params_shard_199.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.37.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "19e94ac0c2e8209e984e07d4ff026eda" }, { "dataPath": "params_shard_200.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.37.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "f99407200689bcd7339bbea23d68c3e4" }, { "dataPath": "params_shard_201.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "58debe6f45d14acfa34c31190f207f80" }, { "dataPath": "params_shard_202.bin", "format": "raw-shard", "nbytes": 30484992, "records": [ { "name": "model.layers.37.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.37.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.37.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.37.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.37.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.37.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.37.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 } ], "md5sum": "88c57ad04ef9e6f6d79bff592bc60126" }, { "dataPath": "params_shard_203.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.38.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "32f2dd64114b043ee66b5698d765c6da" }, { "dataPath": "params_shard_204.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.38.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "34f8e40efd292af7beaa5ebcb3d7bb0e" }, { "dataPath": "params_shard_205.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.38.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "d19b43b96eb9ca82db05cec79d5bd179" }, { "dataPath": "params_shard_206.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.39.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "724ef645e48b1e749f15848da2c919a6" }, { "dataPath": "params_shard_207.bin", "format": "raw-shard", "nbytes": 30505472, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 0 }, { "name": "model.layers.38.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 16384000 }, { "name": "model.layers.38.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 16384256 }, { "name": "model.layers.38.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19661056 }, { "name": "model.layers.38.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 22282496 }, { "name": "model.layers.38.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22282752 }, { "name": "model.layers.38.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 22292992 }, { "name": "model.layers.38.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 }, { "name": "model.layers.39.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30495232 } ], "md5sum": "ff07dae2d5a486e1456c85cb83f39b49" }, { "dataPath": "params_shard_208.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.39.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "674e36704d26cd8d203b8f8682f62d94" }, { "dataPath": "params_shard_209.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.39.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "eaf120fa6d0bf196067295a1a133f0d4" }, { "dataPath": "params_shard_210.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.39.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "d34b9de340fdb55c06a5f049229570c8" }, { "dataPath": "params_shard_211.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.40.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "cc01dc05bf82efd0aec9a3de4e93599c" }, { "dataPath": "params_shard_212.bin", "format": "raw-shard", "nbytes": 30495232, "records": [ { "name": "model.layers.39.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.39.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.39.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.39.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.39.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.39.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.39.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 }, { "name": "model.layers.40.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 } ], "md5sum": "e59da815f3964ec3593bccddd4379448" }, { "dataPath": "params_shard_213.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.40.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "1e8b673b89687b4e2064146c88d97089" }, { "dataPath": "params_shard_214.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.40.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "981d2f678683c256fa8e2dfb848d4193" }, { "dataPath": "params_shard_215.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.40.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "a8cda928f38a956fdf28e9f2438ad82e" }, { "dataPath": "params_shard_216.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.41.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "a27d5f9b0f273406d6fa83310dae869d" }, { "dataPath": "params_shard_217.bin", "format": "raw-shard", "nbytes": 30495232, "records": [ { "name": "model.layers.40.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.40.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.40.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.40.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.40.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.40.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.40.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 }, { "name": "model.layers.41.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 } ], "md5sum": "dab065c2d43118be9a83f1a69ba7591b" }, { "dataPath": "params_shard_218.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.41.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "7c1032ebc5f86f5634fbd8843ca6549b" }, { "dataPath": "params_shard_219.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.41.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "d99ad917196b11538325f53b042146bb" }, { "dataPath": "params_shard_220.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.41.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "b2b6e22a51b0361ac6d4454561ba42a9" }, { "dataPath": "params_shard_221.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.42.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "78188426db8b9a057541ef444c322653" }, { "dataPath": "params_shard_222.bin", "format": "raw-shard", "nbytes": 30484992, "records": [ { "name": "model.layers.41.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.41.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.41.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.41.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.41.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.41.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.41.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 } ], "md5sum": "c26879eb3631daeeed253ed92efa209d" }, { "dataPath": "params_shard_223.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.42.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "e492c8b27f5722087cea267b34ce240e" }, { "dataPath": "params_shard_224.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.42.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "8aad7e604b66c957391c1bb67693856a" }, { "dataPath": "params_shard_225.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.42.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "ff809799134dfd0b428852e1fba2f748" }, { "dataPath": "params_shard_226.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.43.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "d9f32e785f84a568da5eb0c1a121a321" }, { "dataPath": "params_shard_227.bin", "format": "raw-shard", "nbytes": 30505472, "records": [ { "name": "model.layers.42.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 0 }, { "name": "model.layers.42.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 16384000 }, { "name": "model.layers.42.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 16384256 }, { "name": "model.layers.42.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19661056 }, { "name": "model.layers.42.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 22282496 }, { "name": "model.layers.42.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22282752 }, { "name": "model.layers.42.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 22292992 }, { "name": "model.layers.42.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 }, { "name": "model.layers.43.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30495232 } ], "md5sum": "f77f8778db17102726bbf8973916efc4" }, { "dataPath": "params_shard_228.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.43.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "b00818fc8125ba850e10bdbc52e301ba" }, { "dataPath": "params_shard_229.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.43.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "208e653e8d043423a4d04952f09eca52" }, { "dataPath": "params_shard_230.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.43.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "98a47d89563542609bdfcd847bff6072" }, { "dataPath": "params_shard_231.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.44.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "b3e8c5c6eb30a7da16bd0eb9e2542220" }, { "dataPath": "params_shard_232.bin", "format": "raw-shard", "nbytes": 30495232, "records": [ { "name": "model.layers.43.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.43.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.43.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.43.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.43.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.43.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.43.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 }, { "name": "model.layers.44.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 } ], "md5sum": "975c699285f65a9d3fd7b6cde5acb602" }, { "dataPath": "params_shard_233.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.44.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "e785253a558477fbce17437770c2ddb9" }, { "dataPath": "params_shard_234.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.44.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "427516e7eae3a9018f9f4d861fa36441" }, { "dataPath": "params_shard_235.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.44.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "887114923ee8b85f7e808c10884e3c7b" }, { "dataPath": "params_shard_236.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.45.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "8096c4dadf675db9e70359065727d571" }, { "dataPath": "params_shard_237.bin", "format": "raw-shard", "nbytes": 30495232, "records": [ { "name": "model.layers.44.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.44.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.44.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.44.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.44.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.44.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.44.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 }, { "name": "model.layers.45.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 } ], "md5sum": "97a7bde0c9f4aae417fbb0b18f26c598" }, { "dataPath": "params_shard_238.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.45.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "468ca180498728fa69f4497a1f0184f7" }, { "dataPath": "params_shard_239.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.45.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "fa7fc1394b0071b255a9e1e022febd8a" }, { "dataPath": "params_shard_240.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.45.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "5d5db0773e94a1b02dd56d30c00b6941" }, { "dataPath": "params_shard_241.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.46.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "533ba59634cdb774f3c5f737ad5a6351" }, { "dataPath": "params_shard_242.bin", "format": "raw-shard", "nbytes": 30484992, "records": [ { "name": "model.layers.45.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.45.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.45.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.45.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.45.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.45.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.45.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 } ], "md5sum": "a8e113775feebb0cb47fd3840459cd99" }, { "dataPath": "params_shard_243.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.46.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "8dd229398a0d4aff2edd0185c579e693" }, { "dataPath": "params_shard_244.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.46.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "4130338c620128d360e0cd66f4ae4129" }, { "dataPath": "params_shard_245.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.46.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "6f968c561d43974c74b7ad93552897e5" }, { "dataPath": "params_shard_246.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.47.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "bdd271846859fbc655177f1b968291a9" }, { "dataPath": "params_shard_247.bin", "format": "raw-shard", "nbytes": 30505472, "records": [ { "name": "model.layers.46.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 0 }, { "name": "model.layers.46.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 16384000 }, { "name": "model.layers.46.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 16384256 }, { "name": "model.layers.46.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19661056 }, { "name": "model.layers.46.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 22282496 }, { "name": "model.layers.46.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22282752 }, { "name": "model.layers.46.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 22292992 }, { "name": "model.layers.46.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 }, { "name": "model.layers.47.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30495232 } ], "md5sum": "fe5eb41aca3a42cd755563dfdc864a4f" }, { "dataPath": "params_shard_248.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.47.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "e8e656e0e41a63375c1e5d40a9c72ca6" }, { "dataPath": "params_shard_249.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.47.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "304a5ab926f14acacff03bf96063db4f" }, { "dataPath": "params_shard_250.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.47.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "fcda5dba3b36750e95ca98031cd0a097" }, { "dataPath": "params_shard_251.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.48.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "bc9c1509597ea54f4f3d962e547853b7" }, { "dataPath": "params_shard_252.bin", "format": "raw-shard", "nbytes": 30495232, "records": [ { "name": "model.layers.47.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.47.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.47.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.47.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.47.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.47.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.47.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 }, { "name": "model.layers.48.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 } ], "md5sum": "bafbcaf292f8e1ac893c9842dcbe0015" }, { "dataPath": "params_shard_253.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.48.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "82eb16cd267f82b0f746558dfc5afc25" }, { "dataPath": "params_shard_254.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.48.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "ae97e4542e89fc829122c2e9d21f4296" }, { "dataPath": "params_shard_255.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.48.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "7c93652af8aa833773af4146fe566ad6" }, { "dataPath": "params_shard_256.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.49.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "24b57e7e430db37def1f88792afbb85f" }, { "dataPath": "params_shard_257.bin", "format": "raw-shard", "nbytes": 30495232, "records": [ { "name": "model.layers.48.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.48.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.48.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.48.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.48.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.48.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.48.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 }, { "name": "model.layers.49.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 } ], "md5sum": "17d92ff9c6e3a28a12ed3d75e69a6b01" }, { "dataPath": "params_shard_258.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.49.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "faacdd2ee77f754dd03d518985ab8768" }, { "dataPath": "params_shard_259.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.49.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "d548804ac4ed0df3078b5d1a7b3ccba7" }, { "dataPath": "params_shard_260.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.49.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "22ea192abf88dbc924122fc7415c7e02" }, { "dataPath": "params_shard_261.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.50.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "0ffded89745a831e0bdbcc77508e1a7a" }, { "dataPath": "params_shard_262.bin", "format": "raw-shard", "nbytes": 30484992, "records": [ { "name": "model.layers.49.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.49.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.49.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.49.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.49.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.49.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.49.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 } ], "md5sum": "c32912d6fc321808e96c9c2a9b7c0bbb" }, { "dataPath": "params_shard_263.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.50.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "f852c2b6832819d6aeb427700a690510" }, { "dataPath": "params_shard_264.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.50.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "1dd718ec699bc8f9fa4aebb82d6d2683" }, { "dataPath": "params_shard_265.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.50.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "692625ef3becd67348a3ca6edf865801" }, { "dataPath": "params_shard_266.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.51.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "cceaa231fa95a0b5b7b268d68b9bd0af" }, { "dataPath": "params_shard_267.bin", "format": "raw-shard", "nbytes": 30505472, "records": [ { "name": "model.layers.50.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 0 }, { "name": "model.layers.50.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 16384000 }, { "name": "model.layers.50.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 16384256 }, { "name": "model.layers.50.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19661056 }, { "name": "model.layers.50.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 22282496 }, { "name": "model.layers.50.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22282752 }, { "name": "model.layers.50.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 22292992 }, { "name": "model.layers.50.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 }, { "name": "model.layers.51.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30495232 } ], "md5sum": "10e108501a302a22eddfa0efb835bdd5" }, { "dataPath": "params_shard_268.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.51.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "78d1b594d74ac814a397d894da72fdda" }, { "dataPath": "params_shard_269.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.51.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "732fd61a276bcd94b1e104c00de8f6e5" }, { "dataPath": "params_shard_270.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.51.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "35355765365d89dc4e99e5dca2291ce6" }, { "dataPath": "params_shard_271.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.52.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "98ff45e286afcbf850720d8df841b28c" }, { "dataPath": "params_shard_272.bin", "format": "raw-shard", "nbytes": 30495232, "records": [ { "name": "model.layers.51.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.51.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.51.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.51.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.51.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.51.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.51.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 }, { "name": "model.layers.52.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 } ], "md5sum": "1d2dc2068157d3e1974e83bf989bee62" }, { "dataPath": "params_shard_273.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.52.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "96cd82470f4ed9d82266cd733161386b" }, { "dataPath": "params_shard_274.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.52.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "9d740f606df356d5f26983e9fe236279" }, { "dataPath": "params_shard_275.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.52.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "1d26afb935bdb70ba6da2d5617cbab0a" }, { "dataPath": "params_shard_276.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.53.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "44ac1e01efc23496652eeab89f763af6" }, { "dataPath": "params_shard_277.bin", "format": "raw-shard", "nbytes": 30495232, "records": [ { "name": "model.layers.52.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.52.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.52.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.52.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.52.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.52.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.52.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 }, { "name": "model.layers.53.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 } ], "md5sum": "7b8aaa67523b4d79d56c5983edc1aff0" }, { "dataPath": "params_shard_278.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.53.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "3cefcd18f4918a4fbbc2662d4ed0f093" }, { "dataPath": "params_shard_279.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.53.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "f1479c0909b7025ffa191df7c98c9d1a" }, { "dataPath": "params_shard_280.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.53.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "9880334045a53f1a28b7aa856fa15cb3" }, { "dataPath": "params_shard_281.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.54.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "edf7c6f1015e6569d405ac81859be5e7" }, { "dataPath": "params_shard_282.bin", "format": "raw-shard", "nbytes": 30484992, "records": [ { "name": "model.layers.53.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.53.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.53.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.53.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.53.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.53.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.53.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 } ], "md5sum": "881f2cc05d607796b2c82dd92212e04d" }, { "dataPath": "params_shard_283.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.54.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "cf319d3888c57b6b767faa4dbd8478d7" }, { "dataPath": "params_shard_284.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.54.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "58f5e56d22959fdc812fe3fddb79683e" }, { "dataPath": "params_shard_285.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.54.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "07d0ba12cd1e1402301d517f88e3947d" }, { "dataPath": "params_shard_286.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.55.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "a6391d4d2a8247502fe6c55576b01937" }, { "dataPath": "params_shard_287.bin", "format": "raw-shard", "nbytes": 30505472, "records": [ { "name": "model.layers.54.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 0 }, { "name": "model.layers.54.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 16384000 }, { "name": "model.layers.54.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 16384256 }, { "name": "model.layers.54.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19661056 }, { "name": "model.layers.54.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 22282496 }, { "name": "model.layers.54.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22282752 }, { "name": "model.layers.54.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 22292992 }, { "name": "model.layers.54.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 }, { "name": "model.layers.55.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30495232 } ], "md5sum": "819dfa72427423c8f0adedbdb4b9743a" }, { "dataPath": "params_shard_288.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.55.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "57a3acf207dd8b342ff85a89df5240a8" }, { "dataPath": "params_shard_289.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.55.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "719a67afe0198f60e54689b00df5bf2a" }, { "dataPath": "params_shard_290.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.55.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "f241ec0ae200c9fac3b745afdb3459a4" }, { "dataPath": "params_shard_291.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.56.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "9b38cd8e5b03ac3f8e8ca481a2e84024" }, { "dataPath": "params_shard_292.bin", "format": "raw-shard", "nbytes": 30495232, "records": [ { "name": "model.layers.55.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.55.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.55.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.55.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.55.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.55.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.55.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 }, { "name": "model.layers.56.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 } ], "md5sum": "03d8242b045fb2973ef55524cd7c0c6e" }, { "dataPath": "params_shard_293.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.56.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "54a9ff62218375a1b646868469d3aca5" }, { "dataPath": "params_shard_294.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.56.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "89907f511895d0dcc59b55c8c42b1076" }, { "dataPath": "params_shard_295.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.56.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "500d3b144f1e463f4092057c59843acc" }, { "dataPath": "params_shard_296.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.57.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "567185bfb7eb0c46c940b6e350fbaaab" }, { "dataPath": "params_shard_297.bin", "format": "raw-shard", "nbytes": 30495232, "records": [ { "name": "model.layers.56.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.56.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.56.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.56.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.56.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.56.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.56.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 }, { "name": "model.layers.57.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 } ], "md5sum": "e8ea47dbc9a0c9dbde88e6507a8a50a1" }, { "dataPath": "params_shard_298.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.57.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "17c2d4aab025c5cdc194157a2a8fe046" }, { "dataPath": "params_shard_299.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.57.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "b9365a56d41eb2f3cd85480fc57ba5fb" }, { "dataPath": "params_shard_300.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.57.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "536b52973be60469d6ca113a0ad1ca38" }, { "dataPath": "params_shard_301.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.58.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "8e0703c6fb3e62406cda5223e83cd876" }, { "dataPath": "params_shard_302.bin", "format": "raw-shard", "nbytes": 30484992, "records": [ { "name": "model.layers.57.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.57.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.57.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.57.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.57.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.57.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.57.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 } ], "md5sum": "5b47bfef55c6d961b451905eaa93e708" }, { "dataPath": "params_shard_303.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.58.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "bd88bf6b134d32d4359a14be5e1b1228" }, { "dataPath": "params_shard_304.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.58.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "a06ba0aedc4ecb66a08f39abb30ede2f" }, { "dataPath": "params_shard_305.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.58.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "151144dbe0589fd3b6cfdf3744865a0b" }, { "dataPath": "params_shard_306.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.59.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "f27579e16fc662f9a917b34a2e2082a7" }, { "dataPath": "params_shard_307.bin", "format": "raw-shard", "nbytes": 30505472, "records": [ { "name": "model.layers.58.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 0 }, { "name": "model.layers.58.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 16384000 }, { "name": "model.layers.58.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 16384256 }, { "name": "model.layers.58.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19661056 }, { "name": "model.layers.58.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 22282496 }, { "name": "model.layers.58.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22282752 }, { "name": "model.layers.58.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 22292992 }, { "name": "model.layers.58.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 }, { "name": "model.layers.59.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30495232 } ], "md5sum": "8b67a52fe2748f902e466311f2eae5f8" }, { "dataPath": "params_shard_308.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.59.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "ef6055e48ad111b3fb71bd4896ba9b0a" }, { "dataPath": "params_shard_309.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.59.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "ed3a6fbe3e709c0300b7ab931a16ccc8" }, { "dataPath": "params_shard_310.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.59.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "1288b361ccbc946450d2554a899f7c8e" }, { "dataPath": "params_shard_311.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.60.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "9dabf6e8c07a0c6ab3072124349c3a90" }, { "dataPath": "params_shard_312.bin", "format": "raw-shard", "nbytes": 30495232, "records": [ { "name": "model.layers.59.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.59.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.59.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.59.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.59.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.59.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.59.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 }, { "name": "model.layers.60.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 } ], "md5sum": "6327ce9607f4e24c1b8f18ae07c5650c" }, { "dataPath": "params_shard_313.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.60.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "d89b20dabd76d18707d0c62271f4087e" }, { "dataPath": "params_shard_314.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.60.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "4ba509f9cdb576a8a498bfb736e4500d" }, { "dataPath": "params_shard_315.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.60.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "3f0a48753d19b9a37cbded650003bfdc" }, { "dataPath": "params_shard_316.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.layers.61.mlp.down_proj.q_weight", "shape": [ 5120, 3200 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "dde5a9d3cd446b596c91f193fc2e7996" }, { "dataPath": "params_shard_317.bin", "format": "raw-shard", "nbytes": 30495232, "records": [ { "name": "model.layers.60.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.60.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.60.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.60.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.60.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.60.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.60.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 }, { "name": "model.layers.61.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30484992 } ], "md5sum": "aa510da25823eb6d058b2981ffae5605" }, { "dataPath": "params_shard_318.bin", "format": "raw-shard", "nbytes": 131072000, "records": [ { "name": "model.layers.61.mlp.gate_up_proj.q_weight", "shape": [ 51200, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131072000, "byteOffset": 0 } ], "md5sum": "b47994e42b0e1f35e8f4925e67d76cd2" }, { "dataPath": "params_shard_319.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.61.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "7c4438103398c4d81dd9534c422fc707" }, { "dataPath": "params_shard_320.bin", "format": "raw-shard", "nbytes": 20971520, "records": [ { "name": "model.layers.61.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 0 } ], "md5sum": "36f5ba616d39dd859d67198bedd9e190" }, { "dataPath": "params_shard_321.bin", "format": "raw-shard", "nbytes": 26214400, "records": [ { "name": "model.layers.62.self_attn.c_attn.q_weight", "shape": [ 10240, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26214400, "byteOffset": 0 } ], "md5sum": "87955a671761343c633ec913c0cb260c" }, { "dataPath": "params_shard_322.bin", "format": "raw-shard", "nbytes": 30485248, "records": [ { "name": "model.layers.61.mlp.down_proj.q_scale", "shape": [ 5120, 800 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.61.mlp.gate_up_proj.q_scale", "shape": [ 51200, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 16384000, "byteOffset": 8192000 }, { "name": "model.layers.61.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 24576000 }, { "name": "model.layers.61.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 24586240 }, { "name": "model.layers.61.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 24586496 }, { "name": "model.layers.61.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27863296 }, { "name": "model.layers.61.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484736 }, { "name": "model.layers.62.self_attn.k_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 30484992 } ], "md5sum": "11053cb0f85488d4e0dc529de030aa7b" }, { "dataPath": "params_shard_323.bin", "format": "raw-shard", "nbytes": 26870016, "records": [ { "name": "model.layers.62.self_attn.c_attn.q_scale", "shape": [ 10240, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 3276800, "byteOffset": 0 }, { "name": "model.layers.62.self_attn.o_proj.q_weight", "shape": [ 5120, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 20971520, "byteOffset": 3276800 }, { "name": "model.layers.62.self_attn.o_proj.q_scale", "shape": [ 5120, 256 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 24248320 }, { "name": "model.layers.62.self_attn.q_norm.weight", "shape": [ 128 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 256, "byteOffset": 26869760 } ], "md5sum": "4860a46b7e055be1ae95233efc4e7a52" } ] }