{ "metadata": { "ParamSize": 225, "ParamBytes": 618909696.0, "BitsPerParam": 4.500963448531369 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 32768000, "records": [ { "name": "lm_head.q_weight", "shape": [ 32000, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 32768000, "byteOffset": 0 } ], "md5sum": "a328b629e4579dc3473f022797af6fb0" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 32768000, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 32000, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 32768000, "byteOffset": 0 } ], "md5sum": "d57f00a68d3959e6a805e3ba862798f4" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 32976896, "records": [ { "name": "lm_head.q_scale", "shape": [ 32000, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096000, "byteOffset": 0 }, { "name": "model.embed_tokens.q_scale", "shape": [ 32000, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096000, "byteOffset": 4096000 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 8192000 }, { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 8196096 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 13963264 }, { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 14684160 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 26218496 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 27660288 }, { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 27664384 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 30285824 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 30613504 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 32710656 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 32972800 } ], "md5sum": "a4808a5f0a553b9fa350a54a988fbd43" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 31268864, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 0 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 5767168 }, { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 6488064 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 18022400 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 19464192 }, { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 19468288 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 22089728 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 22417408 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 24514560 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 24776704 }, { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 24780800 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 30547968 } ], "md5sum": "d2e08a7ec9430ff451fe865675be2b14" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "8063f8d12a1f4889e3e594606ada683e" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "e25dc7c5f1ff07b67295457d19a3f197" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "4080f5dd0a57b4df73676f2fd382cc58" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "03e8e714aa62131caf1075f46412175f" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "634eae4d09f488190d70cf445be13eee" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "13762a267dee781a354f574bbf41df43" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "4213ab17d642e001eaac07de6a4cba7d" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "235c8c082014991a94ac998998ab83fd" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.18.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "8aae7d37cd99afa57259902610dfb068" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.19.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "0bdab311c9b2575622238accfd7cf438" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "4334672620b6b74b62ceb6b6d55a998c" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.20.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "16559d01b2179406dcf510e5c564e03f" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.21.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "3571314fa149c3d0491248d021f45252" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "33f5cd853511203794856e406040acaf" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "c6a1e2e56c20b674e15ee1e4fbd3acfe" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "f737f4da051728a1da9559a1dda1de1a" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "fcca986721ad09af5b07790eba4bd40f" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "5c3133a9ea2a5cb4cb7bee9e740e3349" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 24780800, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18288640 }, { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 2048, 704 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 18292736 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 2048, 176 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 24059904 } ], "md5sum": "ce54167af3ce71c6236191822d866e98" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 18292736, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 11264, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 11264, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 2560, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2621440, "byteOffset": 12980224 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 2560, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 327680, "byteOffset": 15601664 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 15929344 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 18026496 }, { "name": "model.norm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 18288640 } ], "md5sum": "eb52992493116d1804613ef684124a05" } ] }