diff --git "a/ndarray-cache.json" "b/ndarray-cache.json" new file mode 100644--- /dev/null +++ "b/ndarray-cache.json" @@ -0,0 +1,4303 @@ +{ + "metadata": { + "ParamSize": 325, + "ParamBytes": 3274746880.0, + "BitsPerParam": 3.6176393565388256 + }, + "records": [ + { + "dataPath": "params_shard_0.bin", + "format": "raw-shard", + "nbytes": 52736000, + "records": [ + { + "name": "lm_head.q_weight", + "shape": [ + 32000, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 52736000, + "byteOffset": 0 + } + ], + "md5sum": "9057609f70a0099a30869c069330ef9e" + }, + { + "dataPath": "params_shard_1.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.22.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "030ec45538d37953bb39f97770b0fe23" + }, + { + "dataPath": "params_shard_2.bin", + "format": "raw-shard", + "nbytes": 33068544, + "records": [ + { + "name": "lm_head.q_scale", + "shape": [ + 32000, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6592000, + "byteOffset": 0 + }, + { + "name": "model.layers.22.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 6592000 + }, + { + "name": "model.layers.22.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 6600192 + }, + { + "name": "model.layers.22.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 30127616 + } + ], + "md5sum": "2d4defc6c3b5487a7b4201ee3c25e611" + }, + { + "dataPath": "params_shard_3.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.23.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "6973ffafad00655d64fa894867350250" + }, + { + "dataPath": "params_shard_4.bin", + "format": "raw-shard", + "nbytes": 32391168, + "records": [ + { + "name": "model.layers.22.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 0 + }, + { + "name": "model.layers.22.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5906432 + }, + { + "name": "model.layers.23.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5914624 + }, + { + "name": "model.layers.23.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 5922816 + }, + { + "name": "model.layers.23.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 29450240 + } + ], + "md5sum": "ed9879a15a166625774fd86b1a6926ea" + }, + { + "dataPath": "params_shard_5.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.24.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "d918083d130cd487a8129e182e2f2f9c" + }, + { + "dataPath": "params_shard_6.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.24.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "ab0a9e8d8cfd5d411b3c0a55fe260607" + }, + { + "dataPath": "params_shard_7.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.23.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 0 + }, + { + "name": "model.layers.23.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5906432 + }, + { + "name": "model.layers.23.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 5914624 + }, + { + "name": "model.layers.23.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 16039936 + }, + { + "name": "model.layers.23.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 17305600 + }, + { + "name": "model.layers.23.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 24055808 + }, + { + "name": "model.layers.24.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24899584 + }, + { + "name": "model.layers.24.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 24907776 + } + ], + "md5sum": "d6189d4770551c48d02ed0bad0024fee" + }, + { + "dataPath": "params_shard_8.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.25.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "747ea83c0a7a509aeed307a7739e3658" + }, + { + "dataPath": "params_shard_9.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.25.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "ffba8681110f19f080716018488b653b" + }, + { + "dataPath": "params_shard_10.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.24.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 0 + }, + { + "name": "model.layers.24.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5906432 + }, + { + "name": "model.layers.24.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 5914624 + }, + { + "name": "model.layers.24.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 16039936 + }, + { + "name": "model.layers.24.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 17305600 + }, + { + "name": "model.layers.24.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 24055808 + }, + { + "name": "model.layers.25.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24899584 + }, + { + "name": "model.layers.25.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 24907776 + } + ], + "md5sum": "794478f52152dc507e9e0a9e5d9032ac" + }, + { + "dataPath": "params_shard_11.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.26.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "4883d15be9bc59da184e11f506da1c09" + }, + { + "dataPath": "params_shard_12.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.26.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "b8970c0de410e5a65c59f07c25d4137e" + }, + { + "dataPath": "params_shard_13.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.25.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 0 + }, + { + "name": "model.layers.25.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5906432 + }, + { + "name": "model.layers.25.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 5914624 + }, + { + "name": "model.layers.25.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 16039936 + }, + { + "name": "model.layers.25.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 17305600 + }, + { + "name": "model.layers.25.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 24055808 + }, + { + "name": "model.layers.26.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24899584 + }, + { + "name": "model.layers.26.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 24907776 + } + ], + "md5sum": "362cdd2a32c0404de50610c6dd0fd15b" + }, + { + "dataPath": "params_shard_14.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.27.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "be687dbb1f36eb7cae06347348dc1b27" + }, + { + "dataPath": "params_shard_15.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.27.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "a0e31521640d0e5f7192fb18be5152db" + }, + { + "dataPath": "params_shard_16.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.26.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 0 + }, + { + "name": "model.layers.26.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5906432 + }, + { + "name": "model.layers.26.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 5914624 + }, + { + "name": "model.layers.26.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 16039936 + }, + { + "name": "model.layers.26.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 17305600 + }, + { + "name": "model.layers.26.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 24055808 + }, + { + "name": "model.layers.27.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24899584 + }, + { + "name": "model.layers.27.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 24907776 + } + ], + "md5sum": "95de00f5bd49b45b461a0b7f3b9fb7d0" + }, + { + "dataPath": "params_shard_17.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.28.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "51a3f2fbce5c9cba77c1feab0674d891" + }, + { + "dataPath": "params_shard_18.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.28.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "43d3af64f5cd44277223727ce3eecd92" + }, + { + "dataPath": "params_shard_19.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.27.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 0 + }, + { + "name": "model.layers.27.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5906432 + }, + { + "name": "model.layers.27.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 5914624 + }, + { + "name": "model.layers.27.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 16039936 + }, + { + "name": "model.layers.27.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 17305600 + }, + { + "name": "model.layers.27.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 24055808 + }, + { + "name": "model.layers.28.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24899584 + }, + { + "name": "model.layers.28.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 24907776 + } + ], + "md5sum": "4003464d80e95fcfeeedd9bd4d1ca611" + }, + { + "dataPath": "params_shard_20.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.29.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "3c59105b372ddc361bd9f29ee68f37c8" + }, + { + "dataPath": "params_shard_21.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.29.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "b1fccfe13f9467fae288e8d3c256cdf2" + }, + { + "dataPath": "params_shard_22.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.28.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 0 + }, + { + "name": "model.layers.28.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5906432 + }, + { + "name": "model.layers.28.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 5914624 + }, + { + "name": "model.layers.28.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 16039936 + }, + { + "name": "model.layers.28.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 17305600 + }, + { + "name": "model.layers.28.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 24055808 + }, + { + "name": "model.layers.29.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24899584 + }, + { + "name": "model.layers.29.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 24907776 + } + ], + "md5sum": "e4ecf71e01c4cda74371a64a4bb081fb" + }, + { + "dataPath": "params_shard_23.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.30.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "3edba6ce14cfb77d047d3a6b2051743e" + }, + { + "dataPath": "params_shard_24.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.30.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "0c6b28b8a73333e0464cdc6015511a13" + }, + { + "dataPath": "params_shard_25.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.29.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 0 + }, + { + "name": "model.layers.29.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5906432 + }, + { + "name": "model.layers.29.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 5914624 + }, + { + "name": "model.layers.29.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 16039936 + }, + { + "name": "model.layers.29.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 17305600 + }, + { + "name": "model.layers.29.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 24055808 + }, + { + "name": "model.layers.30.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24899584 + }, + { + "name": "model.layers.30.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 24907776 + } + ], + "md5sum": "58c50bb8659a8a78123d0800df79666c" + }, + { + "dataPath": "params_shard_26.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.31.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "dba3c49f1de097a567104a254a098f96" + }, + { + "dataPath": "params_shard_27.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.31.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "717a380481102b193e7bd48856323bef" + }, + { + "dataPath": "params_shard_28.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.30.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 0 + }, + { + "name": "model.layers.30.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5906432 + }, + { + "name": "model.layers.30.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 5914624 + }, + { + "name": "model.layers.30.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 16039936 + }, + { + "name": "model.layers.30.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 17305600 + }, + { + "name": "model.layers.30.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 24055808 + }, + { + "name": "model.layers.31.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24899584 + }, + { + "name": "model.layers.31.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 24907776 + } + ], + "md5sum": "e004659bb99057a45a68a4ba4e4c80c2" + }, + { + "dataPath": "params_shard_29.bin", + "format": "raw-shard", + "nbytes": 52736000, + "records": [ + { + "name": "model.embed_tokens.q_weight", + "shape": [ + 32000, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 52736000, + "byteOffset": 0 + } + ], + "md5sum": "7f39b21ea37fed3ac77551f92a538d52" + }, + { + "dataPath": "params_shard_30.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.0.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "9dfa0766bd1dff4bff587e3a9dd11f0f" + }, + { + "dataPath": "params_shard_31.bin", + "format": "raw-shard", + "nbytes": 31507968, + "records": [ + { + "name": "model.layers.31.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 0 + }, + { + "name": "model.layers.31.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5906432 + }, + { + "name": "model.layers.31.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 5914624 + }, + { + "name": "model.layers.31.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 16039936 + }, + { + "name": "model.layers.31.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 17305600 + }, + { + "name": "model.layers.31.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 24055808 + }, + { + "name": "model.norm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24899584 + }, + { + "name": "model.embed_tokens.q_scale", + "shape": [ + 32000, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6592000, + "byteOffset": 24907776 + }, + { + "name": "model.layers.0.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 31499776 + } + ], + "md5sum": "df2f1e35f4ba667b2ed00124205e3dab" + }, + { + "dataPath": "params_shard_32.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.0.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "42e0c76bb7400d8602eb0e7e70c147d4" + }, + { + "dataPath": "params_shard_33.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.1.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "a250be4cdf7dbacf97799d573b555be6" + }, + { + "dataPath": "params_shard_34.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.1.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "d223825a73b6e208336656ab64f1d04a" + }, + { + "dataPath": "params_shard_35.bin", + "format": "raw-shard", + "nbytes": 30789632, + "records": [ + { + "name": "model.layers.0.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 0 + }, + { + "name": "model.layers.0.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 2940928 + }, + { + "name": "model.layers.0.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 8847360 + }, + { + "name": "model.layers.0.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 8855552 + }, + { + "name": "model.layers.0.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 18980864 + }, + { + "name": "model.layers.0.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 20246528 + }, + { + "name": "model.layers.0.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 26996736 + }, + { + "name": "model.layers.1.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + }, + { + "name": "model.layers.1.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 27848704 + } + ], + "md5sum": "be43f38052c79032460f6b64f7c2e4c8" + }, + { + "dataPath": "params_shard_36.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.10.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "1239d1b294e3d51d60ec00c0d1c1b0b3" + }, + { + "dataPath": "params_shard_37.bin", + "format": "raw-shard", + "nbytes": 30806016, + "records": [ + { + "name": "model.layers.1.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 0 + }, + { + "name": "model.layers.1.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5906432 + }, + { + "name": "model.layers.1.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 5914624 + }, + { + "name": "model.layers.1.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 16039936 + }, + { + "name": "model.layers.1.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 17305600 + }, + { + "name": "model.layers.1.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 24055808 + }, + { + "name": "model.layers.10.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 24899584 + } + ], + "md5sum": "d464025985da27d7e3c6c6eb0e5ea8cb" + }, + { + "dataPath": "params_shard_38.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.2.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "4d94324f5481df43675b31601dbaf98e" + }, + { + "dataPath": "params_shard_39.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.2.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "f46e11ca602d9301534b7fd18b8e978c" + }, + { + "dataPath": "params_shard_40.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.10.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.10.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.10.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.10.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.2.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.2.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.2.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.2.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "1a9a0169bf58e2ebd0eb9a51f674b55f" + }, + { + "dataPath": "params_shard_41.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.3.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "68c33fa657f1a09e5fc2e7ac550f71dc" + }, + { + "dataPath": "params_shard_42.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.3.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "e636aca1293f5ed37a662d944287d706" + }, + { + "dataPath": "params_shard_43.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.2.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.2.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.2.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.2.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.3.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.3.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.3.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.3.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "b54ae08238921110be9e9ffb5b6684b9" + }, + { + "dataPath": "params_shard_44.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.4.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "62295dc79d4cecc8a6c212e39cf26430" + }, + { + "dataPath": "params_shard_45.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.4.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "862a0b0b5d48afeb0b0421c2dc35ec31" + }, + { + "dataPath": "params_shard_46.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.3.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.3.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.3.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.3.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.4.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.4.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.4.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.4.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "e42693c9ee118fa00e5b4c7900f630ba" + }, + { + "dataPath": "params_shard_47.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.5.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "290d8315738e69bbd294a5311a4a95f6" + }, + { + "dataPath": "params_shard_48.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.5.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "6dbc709ea9469203cc21f8c0969f35e5" + }, + { + "dataPath": "params_shard_49.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.4.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.4.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.4.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.4.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.5.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.5.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.5.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.5.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "203303e09e1fc8227d56d3beb137d4eb" + }, + { + "dataPath": "params_shard_50.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.6.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "66167f23985454977d4c32c50623c439" + }, + { + "dataPath": "params_shard_51.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.6.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "919bc6ece17fed19e22089ccbe7ea386" + }, + { + "dataPath": "params_shard_52.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.5.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.5.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.5.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.5.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.6.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.6.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.6.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.6.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "ad1be6eae09473ff0092456e0fe9eb78" + }, + { + "dataPath": "params_shard_53.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.7.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "1aad69d3df2ab460c17f06de56899315" + }, + { + "dataPath": "params_shard_54.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.7.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "af0f8d82db080492a449ae7f8917f237" + }, + { + "dataPath": "params_shard_55.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.6.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.6.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.6.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.6.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.7.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.7.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.7.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.7.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "05d89484b8efb06051918d4c4d544b9f" + }, + { + "dataPath": "params_shard_56.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.8.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "eed22e406b86dbd694856c2af8b7aede" + }, + { + "dataPath": "params_shard_57.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.8.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "211521c64e7f55844961343bc4b6141d" + }, + { + "dataPath": "params_shard_58.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.7.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.7.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.7.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.7.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.8.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.8.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.8.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.8.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "488fb9b02cdf8c83aeb7f97ad8eade6d" + }, + { + "dataPath": "params_shard_59.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.9.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "9fc08ad711e9711a6df8b51a34986c8f" + }, + { + "dataPath": "params_shard_60.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.9.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "2709b913f4ee7aab72a1c429bb5837bc" + }, + { + "dataPath": "params_shard_61.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.8.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.8.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.8.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.8.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.9.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.9.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.9.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.9.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "052a1ab7ca398219289f2246943db080" + }, + { + "dataPath": "params_shard_62.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.10.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "e9d2c5a76c5f5988b83e0a87834ed169" + }, + { + "dataPath": "params_shard_63.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.11.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "be44eee6752868c3dd1de7cf09cbf51b" + }, + { + "dataPath": "params_shard_64.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.11.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "d7dc0b13cdf4eddc55fe0dce9119b65c" + }, + { + "dataPath": "params_shard_65.bin", + "format": "raw-shard", + "nbytes": 30806016, + "records": [ + { + "name": "model.layers.9.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.9.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.9.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.9.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.10.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.10.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.10.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21934080 + }, + { + "name": "model.layers.11.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 21942272 + }, + { + "name": "model.layers.11.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 21950464 + }, + { + "name": "model.layers.11.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 24891392 + }, + { + "name": "model.layers.11.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 30797824 + } + ], + "md5sum": "7b1075b5aeb1f011e25b4ee2e6f0dfb9" + }, + { + "dataPath": "params_shard_66.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.12.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "44a6020fcb9b5081689b4a0dbb40fc49" + }, + { + "dataPath": "params_shard_67.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.12.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "09ab72c24751eff1015a09cfda4a8658" + }, + { + "dataPath": "params_shard_68.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.11.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.11.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.11.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.11.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.12.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.12.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.12.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.12.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "d75289efcecdecce4f054db52558fbab" + }, + { + "dataPath": "params_shard_69.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.13.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "f4438aef04806f125ff94b45ade58531" + }, + { + "dataPath": "params_shard_70.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.13.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "146f64632dac1b4cf6361e4498ec4ed5" + }, + { + "dataPath": "params_shard_71.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.12.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.12.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.12.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.12.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.13.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.13.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.13.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.13.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "bd8eb3833faad1ff4bd2ee244183ea78" + }, + { + "dataPath": "params_shard_72.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.14.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "f2e2bb7fba02b2ff04a308cc09d4df24" + }, + { + "dataPath": "params_shard_73.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.14.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "f5aab16b3e8ca680908155d77ecfa89f" + }, + { + "dataPath": "params_shard_74.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.13.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.13.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.13.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.13.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.14.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.14.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.14.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.14.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "8b3bba515e71243c5a2217889aa57e25" + }, + { + "dataPath": "params_shard_75.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.15.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "9a1f257de73914048aa5d9322f422c72" + }, + { + "dataPath": "params_shard_76.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.15.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "1e80ff58a0120615a71aab05237dcaf5" + }, + { + "dataPath": "params_shard_77.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.14.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.14.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.14.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.14.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.15.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.15.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.15.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.15.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "32f525aa33a36adf2fa0a1ded90e5cd5" + }, + { + "dataPath": "params_shard_78.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.16.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "f1983fff238bcc23d9586186e57a64f0" + }, + { + "dataPath": "params_shard_79.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.16.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "bdc6178c387c329706e09f4e8526e268" + }, + { + "dataPath": "params_shard_80.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.15.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.15.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.15.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.15.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.16.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.16.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.16.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.16.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "8a94e8c6828a592b76ff35bf184bdb81" + }, + { + "dataPath": "params_shard_81.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.17.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "20f50c85c0c1d49dc2d4157f7f6124e5" + }, + { + "dataPath": "params_shard_82.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.17.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "24d1ff648ff508493a0a49a07501db54" + }, + { + "dataPath": "params_shard_83.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.16.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.16.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.16.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.16.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.17.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.17.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.17.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.17.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "cc31a59dfb67b65f44f2234be8b874d8" + }, + { + "dataPath": "params_shard_84.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.18.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "4a6c7cdc472da8d185e23aa21a2920b2" + }, + { + "dataPath": "params_shard_85.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.18.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "d268367e98b733e3e61d9654fc8ce26f" + }, + { + "dataPath": "params_shard_86.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.17.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.17.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.17.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.17.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.18.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.18.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.18.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.18.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "5228f1d08430981c2d18171e22dacac3" + }, + { + "dataPath": "params_shard_87.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.19.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "1db60801f5bf06d6d4dc62e1421ccd19" + }, + { + "dataPath": "params_shard_88.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.19.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "49be90ebbec1666e04823eb593bee3f3" + }, + { + "dataPath": "params_shard_89.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.18.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.18.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.18.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.18.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.19.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.19.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.19.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.19.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "46d21a488b03c18f304769c64345514b" + }, + { + "dataPath": "params_shard_90.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.20.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "3117c699721d3a40ccd3ea549cf19d93" + }, + { + "dataPath": "params_shard_91.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.20.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "9cc64ac0b21dc1a884c42757bba1001a" + }, + { + "dataPath": "params_shard_92.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.19.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.19.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.19.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.19.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.20.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.20.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.20.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.20.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "94228133bf29acfbb801370b7bee31a2" + }, + { + "dataPath": "params_shard_93.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.21.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "21af318251aa70d7be8e738a682310ba" + }, + { + "dataPath": "params_shard_94.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.21.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "a906820c9b07c28bdbe95bbd105faa13" + }, + { + "dataPath": "params_shard_95.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.20.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.20.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.20.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.20.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.21.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.21.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.21.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.21.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "9af338275502baa847721575cda3a1b2" + }, + { + "dataPath": "params_shard_96.bin", + "format": "raw-shard", + "nbytes": 30375936, + "records": [ + { + "name": "model.layers.21.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.21.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.21.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.21.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.22.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 18984960 + }, + { + "name": "model.layers.22.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 29110272 + } + ], + "md5sum": "c4d136b8999a5925d9e70c5eae06e758" + }, + { + "dataPath": "params_shard_97.bin", + "format": "raw-shard", + "nbytes": 7593984, + "records": [ + { + "name": "model.layers.22.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 0 + }, + { + "name": "model.layers.22.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 6750208 + } + ], + "md5sum": "5e02b244caa80b38e32191f98d84761b" + } + ] +} \ No newline at end of file