{ "metadata": { "ParamSize": 533, "ParamBytes": 8309352448.0, "BitsPerParam": 4.50065457508222 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 389283840, "records": [ { "name": "lm_head.q_weight", "shape": [ 152064, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 389283840, "byteOffset": 0 } ], "md5sum": "1bbf61cb88d129f21ff0661f173940b5" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 48660480, "records": [ { "name": "lm_head.q_scale", "shape": [ 152064, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 48660480, "byteOffset": 0 } ], "md5sum": "82e987918b7b5d6f4bfb121490d09d43" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.33.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "eb236d1d882ce2e0bc924303b190040c" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "9761bb94d22f86c4b955257e18e9a5f5" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.34.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "1c54e4a786d4cba058e3799ed03ab95a" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "f7b4a019bd42908a4d2b8bb5bcef8567" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.34.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "bfd153025e6d71c7ac1034b0da0414af" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 28891136, "records": [ { "name": "model.layers.33.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 0 }, { "name": "model.layers.33.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 10240 }, { "name": "model.layers.33.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 4433920 }, { "name": "model.layers.33.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13281280 }, { "name": "model.layers.34.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13291520 }, { "name": "model.layers.34.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13301760 }, { "name": "model.layers.34.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 17725440 }, { "name": "model.layers.34.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 26572800 }, { "name": "model.layers.34.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 26583040 }, { "name": "model.layers.34.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 26597376 } ], "md5sum": "6c967d18014d304787a1ff4809deb595" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.35.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "2f05b31690ade2fe37c79fdd2956d984" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "5bf28d75f4413be99300a4c94d564cf2" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.35.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "7c6239ef2d592cf9775c2695205a0204" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.34.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.34.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.35.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.35.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.35.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.35.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.35.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.35.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "5fbdce597da916decd6ea57dd674e510" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.36.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "40e96ba4514f4ffcef39ef375358c367" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "1ad0523c635f2e87e35eabe5d950cb77" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.36.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "ee4bf19384bb89803ebb31f275600f64" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.35.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.35.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.36.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.36.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.36.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.36.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.36.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.36.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "647f544a4316d5cc386407640417bcee" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.37.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "464567832a80cb3e6e6243da3a073a1c" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.37.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "66484667a7a257515536842a327a2be0" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.37.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "603fa287b0cd0b24c65fcb010c2902a0" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.36.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.36.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.37.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.37.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.37.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.37.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.37.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.37.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "38740821556bf17a95098c42d35ffd8c" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.38.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "59273de18fd4cb1c73032e6884e17fff" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "31ea0cbcda17109795b39018092a3b85" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.38.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "32ccb4474c73d3caa068083bcf68e230" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.37.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.37.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.38.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.38.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.38.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.38.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.38.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.38.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "f4e3c68f30605a3e79cecdee671a3188" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.39.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "879d8ec4e3ef3d29bb9f9841493e12b0" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.39.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "9256d0b74ee30ce86a0b4d01ed131e4e" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.39.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "50f735cb24d4f935b8badf4249381cfa" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.38.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.38.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.39.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.39.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.39.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.39.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.39.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.39.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "a176defe1d0f789dad23e75a66fbeaaf" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.40.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "bdf1ca93644f037f145094797eb0b5ec" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.40.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "c93447b9ef087dff77075e17d3d15e60" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.40.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "5129039e559a036aceba9db784dda1cd" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.39.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.39.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.40.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.40.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.40.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.40.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.40.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.40.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "7ceb2b4b7e5e1a6a4e7438ee9ad86e95" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.41.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "d62b737e03b52d4cc8ad2710b2c1135e" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.41.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "7755c3ac5fa6e545b5116742dfb8374b" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.41.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "2be2254633cdf1c3a71e15ea39af8f8b" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.40.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.40.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.41.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.41.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.41.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.41.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.41.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.41.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "abae32de2d9e194d182ec68c3f162c38" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.42.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "4c89c147be5dcb686a47b11ed23f7f8a" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.42.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "6b2f99be3da23a0f846944a41deae606" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.42.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "93a5949afa47c5df8b7a3fe097650daf" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.41.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.41.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.42.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.42.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.42.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.42.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.42.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.42.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "dcfdf0d345369cd843c6a70543faa411" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.43.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "cb877c60464e1ee7a9bbf8853b62c59c" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.43.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "953648664aac30685fe5395136fc2f48" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.43.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "01c75324d6e1025eb1c851e77ab47f93" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.42.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.42.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.43.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.43.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.43.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.43.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.43.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.43.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "55e81369e95ab4c26b5f00dd5dcbc23e" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.44.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "3900c1a3db304a8ccada7dc2b5a71388" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.44.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "69a8347394429be2de0d30185ad5deac" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.44.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "199d1effb793af0400deda5088757e4b" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.43.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.43.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.44.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.44.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.44.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.44.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.44.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.44.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "1e8b15d07d9d4513cc84d9b2ebe72d08" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.45.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "0ae1ec8fbdf8bc4a5ebe05c106eea2b9" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.45.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "1a0e790a2a10fdaa6cc62eaace3ef92e" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.45.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "2f2ae899bfbc9bc6b61ff379f0a0b3dc" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.44.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.44.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.45.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.45.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.45.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.45.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.45.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.45.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "81d32f2fb3c7ee19208056e49d57917c" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.46.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "80b0243442f165c929599c608c18493c" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.46.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "86597e54318536cfbb2496e2ccd9bf08" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.46.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "fbe4a32a69bdf32519f9aa96692dd32e" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.45.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.45.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.46.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.46.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.46.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.46.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.46.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.46.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "b685e4c62ebc31427411fbd5cf114740" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.47.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "a2019d94fc2d7391bd1a9e7765f9df10" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.47.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "e170828df805bba976818640658c6106" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.47.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "a2c18f43466e5c5cac8cacb37bd60308" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.46.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.46.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.47.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.47.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.47.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.47.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.47.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.47.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "1504f0018b43ed96db19411ba3dfaaa5" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 389283840, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 152064, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 389283840, "byteOffset": 0 } ], "md5sum": "01dee9cbf8461fd9eaf15ac8d0408423" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 48660480, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 152064, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 48660480, "byteOffset": 0 } ], "md5sum": "8c451797c0d6307feb7f5d7a2c4ae063" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "7038343377e0041c41fcdade9eca492d" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "2a8fc7114112c2dfc5e54c740a63db8d" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.0.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "78782a457470ce0116a538b9b1dbe4cd" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 30355456, "records": [ { "name": "model.layers.47.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.47.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.norm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14755840 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14766080 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19189760 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28037120 }, { "name": "model.layers.0.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28047360 }, { "name": "model.layers.0.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28061696 } ], "md5sum": "99387febb6298240b317293ba85909eb" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "9a29315717479ec49bcb8d5202afa6b9" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "1fd5d9df5fd8e09e6bddcc3e24860634" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.1.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "815d3bd4a71f815e7fe555e9903704c0" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.1.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.1.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "71b7e1d3c8a51d4b67a08b8a3c5a8378" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "be44e968d3643492c89e5c31d451eabf" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "85f6ff1eabedc0d2d46375ec2101dc92" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.10.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "09bab4ec8d130fb742395efb4007e2ed" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.10.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.10.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "607e87ee12cfa7fd8f113db32577f844" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "17351abb85d96f8cde6354134ea0df05" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "28cfb7ee4f91c6919c1259fe0af3e69f" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.11.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "4ea5b031d092b241e8244ae4f3959191" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.11.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.11.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "d28a69c2fa8ef9bb8f6081773fea6424" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "eeaf33d5f95d7a5a2fc4f4174d916944" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "e1b8f3a93c8c94cf7d219b851ca42349" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.12.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "af22496809132f5e439cdc1fbf45fdec" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.12.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.12.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "05152ef30aa141a55cc22338c3f3ec4f" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "2d7055b697689e47dcfd4e01eb9e6186" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "db7fb792114a3b8889f210eb9ed81aa2" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.13.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "d234caa7e233d0aa68f0333a9932c20f" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.13.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.13.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "af2509e5214c78c1480c85ae23ed8f13" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "fec49a107e05b1a86dd1201a64705873" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "0c1f7b58eb70c309c7541397fa88fcb3" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.14.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "c932cc28386eecd0746d4b8cd7a99239" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.14.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.14.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "f13e67c268ef5d0f2f803b87e0632108" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 33110016, "records": [ { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.15.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 14745600 }, { "name": "model.layers.15.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 14759936 } ], "md5sum": "e7077d1ad2776f7c8ff3fdcccd5ecc89" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "23d1ddc7705dc523321c5754a3d6bd09" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "f9b895e7884ee08e15c85fe4a1c9c274" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.2.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "f98183ae9ce33f8fdfb496beaf1d9fb8" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 32638976, "records": [ { "name": "model.layers.15.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 17039360 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 17049600 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 21473280 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30320640 }, { "name": "model.layers.2.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 30330880 }, { "name": "model.layers.2.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 30345216 } ], "md5sum": "457f7c2afcb066eed7323ab272477a15" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "44ba40dcd9e249d42072ccb307c949a5" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "637d0969b3b5ad0758ae8a22c6b5ec85" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.3.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "a519ce5f2c3f2c592e26407e8ce4d51f" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.3.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.3.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "4335a0e5c2043a2bd0c81da1f5c047a6" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "1b77de64c9cea691bf19a5cf2d5f8024" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "8a994003552ba1321f84e53edc953d52" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.4.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "cd019a5ce3659307b13b6795cd21e4d4" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.4.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.4.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "162d9ad72c111be687a7add6b5a4df2e" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "1aa33230a7c34f943dc97310438d7713" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "28e7894af936ce5b0bac1b2ab9644041" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.5.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "b533e9380814743d28f52f018d5f03d0" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.5.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.5.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "be5c390f28e1a08e59267a2e3989ca16" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "e3b38021af11ae9fb252d15bca8fdfeb" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "c2c6028d7f27f793f70b1f79d0ade1cb" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.6.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "7aebac1bbc9d252cc844138a44781873" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.6.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.6.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "9944cf0e6a3c51c61a5f2d83ee550689" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "c25ebb1f6ce44aeb49030cc644b402e6" }, { "dataPath": "params_shard_112.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "1fe64d44ce6db046bcb6d6c557f26f78" }, { "dataPath": "params_shard_113.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.7.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "f4e1556808d2a80e6c33a3bdc315ed0b" }, { "dataPath": "params_shard_114.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.7.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.7.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "f2039d8c3ef870de2c1308259791cd9b" }, { "dataPath": "params_shard_115.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "2e83deada2905dd201002c1924c40263" }, { "dataPath": "params_shard_116.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "c4197eb2c71ffe3aab0ef17caf2064f5" }, { "dataPath": "params_shard_117.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.8.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "79e553e5799c8631e60b8b6f28b5b3c7" }, { "dataPath": "params_shard_118.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.8.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.8.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "c96895ac29203464faf0cb575394ca4a" }, { "dataPath": "params_shard_119.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "6e9a289195d742fb42bb9d6f13beed4f" }, { "dataPath": "params_shard_120.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "05215c0d38847953d507da0ecb4268df" }, { "dataPath": "params_shard_121.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.9.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "42283cfad1698e60eab0b59d7ea01f43" }, { "dataPath": "params_shard_122.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.9.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.9.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "eed50f72f5745b167bb761d7d8c75501" }, { "dataPath": "params_shard_123.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "96a6e333e336198d2810060e6ea77073" }, { "dataPath": "params_shard_124.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "2da6584332f72331c44d92d63164f2c6" }, { "dataPath": "params_shard_125.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "3c3b733b6338e54ec4b3bed56013a625" }, { "dataPath": "params_shard_126.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "d236b9deea15b7b014000663a1bc4ba2" }, { "dataPath": "params_shard_127.bin", "format": "raw-shard", "nbytes": 32471040, "records": [ { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28037120 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 28047360 } ], "md5sum": "f630cbcb9fc9a990c198aa2d2038f070" }, { "dataPath": "params_shard_128.bin", "format": "raw-shard", "nbytes": 29515776, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.16.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8857600 }, { "name": "model.layers.16.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8871936 }, { "name": "model.layers.16.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27222016 } ], "md5sum": "78db96a52364ecf4db89d3fb85fbf203" }, { "dataPath": "params_shard_129.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "5f83d0edc87a0e966691600664af0ad3" }, { "dataPath": "params_shard_130.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "5e1c7bbc6ea2273c29c53552a8bc1c6a" }, { "dataPath": "params_shard_131.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.17.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "0e0777a39a1cba20309095eefb6dcf77" }, { "dataPath": "params_shard_132.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.17.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.17.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "c50d01044d4cf8a3e20cdba0cb4c89bd" }, { "dataPath": "params_shard_133.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "2075357f07b4508e9e47d99d1f1b5131" }, { "dataPath": "params_shard_134.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "6008fc307db7cbce5f386b14f0f681f2" }, { "dataPath": "params_shard_135.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.18.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "970947a114bd2bdf2b7f386cf1b0905c" }, { "dataPath": "params_shard_136.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.18.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.18.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "29dc821c169e65a71f052259697a9eeb" }, { "dataPath": "params_shard_137.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "ca656cb2f81a4adf36e45de503c3c6cd" }, { "dataPath": "params_shard_138.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "095572b8d4963598c09fe53940c76246" }, { "dataPath": "params_shard_139.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.19.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "39c843fc0935b91af5f307312740b91b" }, { "dataPath": "params_shard_140.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.19.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.19.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "626b097686abb4531de2f36ea95eea37" }, { "dataPath": "params_shard_141.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "f88d135abb2018ebffd06f6c4b2375bf" }, { "dataPath": "params_shard_142.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "23fee7156e96483533670fa9c53c089e" }, { "dataPath": "params_shard_143.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.20.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "88a8652a225bc67235c166c66cf49303" }, { "dataPath": "params_shard_144.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.20.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.20.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "eb4fe2b15727a25f639924df3405d1e2" }, { "dataPath": "params_shard_145.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "b97fa0cd8dfa0014578e5274f78bf893" }, { "dataPath": "params_shard_146.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "e7ec434c9c74e7b1d0e61ac6269a8e1b" }, { "dataPath": "params_shard_147.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.21.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "14bca9aed2f0777903b115ea77fa0d02" }, { "dataPath": "params_shard_148.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.21.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.21.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "293f4c7bb67e6333fab485a84b6a3075" }, { "dataPath": "params_shard_149.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "c61175bc089805c53ad148f59d22b3bb" }, { "dataPath": "params_shard_150.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "21b028188f85ec86f10dc4fd003617b8" }, { "dataPath": "params_shard_151.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.22.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "4461a868ae50e4553fc91a640008fba9" }, { "dataPath": "params_shard_152.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.22.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.22.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "ab6c361b87ed7b0b17ed87d51416bdd9" }, { "dataPath": "params_shard_153.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "bf1946181a094b9ebaf219780ae4ab8e" }, { "dataPath": "params_shard_154.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "ca4b57786c5b0262bbc6aa92e9b5a9d4" }, { "dataPath": "params_shard_155.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.23.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "2ec659a86e8819fc288c5be2b3258141" }, { "dataPath": "params_shard_156.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.23.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.23.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "cfdf05914e9cb55fd2c0759dd1d99aa2" }, { "dataPath": "params_shard_157.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "5b0302b9fddf82fdc3d810870850f5f7" }, { "dataPath": "params_shard_158.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "27fb1cc97e12a0b44b5dd7a4082223f6" }, { "dataPath": "params_shard_159.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.24.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "7980e832fb01da74b61f6c114766375d" }, { "dataPath": "params_shard_160.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.24.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.24.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "38bed790d8954b9cf89394e0cdda7e8e" }, { "dataPath": "params_shard_161.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "866c5eed5afb1ce123886684c24c1b41" }, { "dataPath": "params_shard_162.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "f305e92e6081a7e2e8fda52ec9ba3d61" }, { "dataPath": "params_shard_163.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.25.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "417ad706f712f88801638bf483f84d0c" }, { "dataPath": "params_shard_164.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.25.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.25.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "056eeec81ee8f53d082ce18c6f706f9c" }, { "dataPath": "params_shard_165.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "d2a0b3505e559ed396e3c49e4d9bcead" }, { "dataPath": "params_shard_166.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "4769fa9b702eb1a4799642b7c5cf7fc4" }, { "dataPath": "params_shard_167.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.26.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "cc34a987445700ef1843251eae2368ca" }, { "dataPath": "params_shard_168.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.26.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.26.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "f014ecfa971636d696ac723ce646c602" }, { "dataPath": "params_shard_169.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "4462ef276729527ff1c8be4bbc407ca0" }, { "dataPath": "params_shard_170.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "181dd6678da90c66bcaeaec7eefd3c1d" }, { "dataPath": "params_shard_171.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.27.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "8dd67e320e62e620698f7134d202781c" }, { "dataPath": "params_shard_172.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.27.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.27.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "ae6f765083ba779f711033958dd32fe5" }, { "dataPath": "params_shard_173.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "c30fd152938756c0a37f9257c19db15b" }, { "dataPath": "params_shard_174.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "166e6c9908a2dceb9d087b2f9ec80b34" }, { "dataPath": "params_shard_175.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.28.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "91cbefa29b13f62dc4b182b07e129985" }, { "dataPath": "params_shard_176.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.28.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.28.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "643d9ad95ee9864a05b6633a2b1822ce" }, { "dataPath": "params_shard_177.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "2a4c393d9d7bf8a4acbbc0ccce3c5eda" }, { "dataPath": "params_shard_178.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "e0197620c3943fee9605581106cbe14c" }, { "dataPath": "params_shard_179.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.29.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "1f7cd69a0bcbc359d2a897304772155b" }, { "dataPath": "params_shard_180.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.29.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.29.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "2c261fdae9b34a70239a70e93b508756" }, { "dataPath": "params_shard_181.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "e32e69b6cf83dd4b646e13064eb6df1f" }, { "dataPath": "params_shard_182.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "a22804f1c80633cd9bafcaea557dead7" }, { "dataPath": "params_shard_183.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.30.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "e99dd1fcf13be674c56d12b0eb392bf9" }, { "dataPath": "params_shard_184.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.30.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.30.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "516ade5a1b00454624eb6cc34fefe382" }, { "dataPath": "params_shard_185.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "cc9bfdc8b8cbc84399c83b3c80412a9a" }, { "dataPath": "params_shard_186.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "101c51665a58a6b65c6cd19f952f4e2a" }, { "dataPath": "params_shard_187.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.31.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "d3e00283f9a9bd7c4a76c537b070b474" }, { "dataPath": "params_shard_188.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.31.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.31.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "362d580dca51c92d163012aba0323fd9" }, { "dataPath": "params_shard_189.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.32.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "48e1191cdd323dc2c9a85fd703cf1313" }, { "dataPath": "params_shard_190.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "21ac80531532bf114d8da400a2cb09d5" }, { "dataPath": "params_shard_191.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.32.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "2d477d32184621873faf499606095238" }, { "dataPath": "params_shard_192.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.32.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.32.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.32.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.32.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.32.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.32.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "dd9c1356da22e4908795038283f35bc6" }, { "dataPath": "params_shard_193.bin", "format": "raw-shard", "nbytes": 33110016, "records": [ { "name": "model.layers.32.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.32.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.33.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 14745600 }, { "name": "model.layers.33.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 14759936 } ], "md5sum": "a46cfe5a0ded256bfad8fcb9e1089efd" }, { "dataPath": "params_shard_194.bin", "format": "raw-shard", "nbytes": 17039360, "records": [ { "name": "model.layers.33.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.33.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.33.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 } ], "md5sum": "6786adc5edce700a588d5d7b36588b1c" } ] }