Qwen2 MOE 57B

297 Pulls Updated 3 weeks ago

96023db93073 · 35GB
{ "metadata": { "general.architecture": "qwen2moe", "general.file_type": 15, "general.name": "Qwen2-57B-A14B-Instruct", "general.quantization_version": 2, "general.source.url": "https://huggingface.co/Qwen/Qwen2-57B-A14B-Instruct", "general.url": "https://huggingface.co/mradermacher/Qwen2-57B-A14B-Instruct-GGUF", "mradermacher.convert_type": "hf", "mradermacher.quantize_version": "2", "mradermacher.quantized_at": "2024-06-07T16:21:16+02:00", "mradermacher.quantized_by": "mradermacher", "mradermacher.quantized_on": "kaos", "qwen2moe.attention.head_count": 28, "qwen2moe.attention.head_count_kv": 4, "qwen2moe.attention.layer_norm_rms_epsilon": 0.000001, "qwen2moe.block_count": 28, "qwen2moe.context_length": 32768, "qwen2moe.embedding_length": 3584, "qwen2moe.expert_count": 64, "qwen2moe.expert_used_count": 8, "qwen2moe.feed_forward_length": 20480, "qwen2moe.rope.freq_base": 1000000, "tokenizer.ggml.bos_token_id": 151643, "tokenizer.ggml.eos_token_id": 151645, "tokenizer.ggml.merges": "... (151387 values)", "tokenizer.ggml.model": "gpt2", "tokenizer.ggml.padding_token_id": 151643, "tokenizer.ggml.pre": "qwen2", "tokenizer.ggml.token_type": "... (151936 values)", "tokenizer.ggml.tokens": "... (151936 values)" }, "num_params": 57408658944, "tensors": [ { "name": "blk.0.ffn_gate_inp.weight", "offset": 306302976, "shape": [ 3584, 64 ], "size": 306302976, "type": 0 }, { "name": "blk.0.attn_k.bias", "offset": 307220480, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.0.attn_k.weight", "offset": 307222528, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.0.attn_output.weight", "offset": 308254720, "shape": [ 3584, 3584 ], "size": 1032192, "type": 12 }, { "name": "blk.0.attn_q.bias", "offset": 315480064, "shape": [ 3584 ], "size": 7225344, "type": 0 }, { "name": "blk.0.attn_q.weight", "offset": 315494400, "shape": [ 3584, 3584 ], "size": 14336, "type": 12 }, { "name": "blk.0.attn_v.bias", "offset": 322719744, "shape": [ 512 ], "size": 7225344, "type": 0 }, { "name": "blk.0.attn_v.weight", "offset": 322721792, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.0.attn_norm.weight", "offset": 324227072, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.0.ffn_down_exps.weight", "offset": 324241408, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.0.ffn_gate_exps.weight", "offset": 805931008, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 12 }, { "name": "blk.0.ffn_up_exps.weight", "offset": 1136232448, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.0.ffn_down_shexp.weight", "offset": 1466533888, "shape": [ 20480, 3584 ], "size": 330301440, "type": 14 }, { "name": "blk.0.ffn_gate_shexp.weight", "offset": 1526745088, "shape": [ 3584, 20480 ], "size": 60211200, "type": 12 }, { "name": "blk.0.ffn_up_shexp.weight", "offset": 1568032768, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.0.ffn_gate_inp_shexp.weight", "offset": 1609320448, "shape": [ 3584 ], "size": 41287680, "type": 0 }, { "name": "blk.0.ffn_norm.weight", "offset": 1609334784, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.1.ffn_gate_inp.weight", "offset": 1609349120, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.1.attn_k.bias", "offset": 1610266624, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.1.attn_k.weight", "offset": 1610268672, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.1.attn_output.weight", "offset": 1611300864, "shape": [ 3584, 3584 ], "size": 1032192, "type": 12 }, { "name": "blk.1.attn_q.bias", "offset": 1618526208, "shape": [ 3584 ], "size": 7225344, "type": 0 }, { "name": "blk.1.attn_q.weight", "offset": 1618540544, "shape": [ 3584, 3584 ], "size": 14336, "type": 12 }, { "name": "blk.1.attn_v.bias", "offset": 1625765888, "shape": [ 512 ], "size": 7225344, "type": 0 }, { "name": "blk.1.attn_v.weight", "offset": 1625767936, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.1.attn_norm.weight", "offset": 1627273216, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.1.ffn_down_exps.weight", "offset": 1627287552, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.1.ffn_gate_exps.weight", "offset": 2108977152, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 12 }, { "name": "blk.1.ffn_up_exps.weight", "offset": 2439278592, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.1.ffn_down_shexp.weight", "offset": 2769580032, "shape": [ 20480, 3584 ], "size": 330301440, "type": 14 }, { "name": "blk.1.ffn_gate_shexp.weight", "offset": 2829791232, "shape": [ 3584, 20480 ], "size": 60211200, "type": 12 }, { "name": "blk.1.ffn_up_shexp.weight", "offset": 2871078912, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.1.ffn_gate_inp_shexp.weight", "offset": 2912366592, "shape": [ 3584 ], "size": 41287680, "type": 0 }, { "name": "blk.1.ffn_norm.weight", "offset": 2912380928, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.2.ffn_gate_inp.weight", "offset": 2912395264, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.2.attn_k.bias", "offset": 2913312768, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.2.attn_k.weight", "offset": 2913314816, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.2.attn_output.weight", "offset": 2914347008, "shape": [ 3584, 3584 ], "size": 1032192, "type": 12 }, { "name": "blk.2.attn_q.bias", "offset": 2921572352, "shape": [ 3584 ], "size": 7225344, "type": 0 }, { "name": "blk.2.attn_q.weight", "offset": 2921586688, "shape": [ 3584, 3584 ], "size": 14336, "type": 12 }, { "name": "blk.2.attn_v.bias", "offset": 2928812032, "shape": [ 512 ], "size": 7225344, "type": 0 }, { "name": "blk.2.attn_v.weight", "offset": 2928814080, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.2.attn_norm.weight", "offset": 2930319360, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.2.ffn_down_exps.weight", "offset": 2930333696, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.2.ffn_gate_exps.weight", "offset": 3412023296, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 12 }, { "name": "blk.2.ffn_up_exps.weight", "offset": 3742324736, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.2.ffn_down_shexp.weight", "offset": 4072626176, "shape": [ 20480, 3584 ], "size": 330301440, "type": 14 }, { "name": "blk.2.ffn_gate_shexp.weight", "offset": 4132837376, "shape": [ 3584, 20480 ], "size": 60211200, "type": 12 }, { "name": "blk.2.ffn_up_shexp.weight", "offset": 4174125056, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.2.ffn_gate_inp_shexp.weight", "offset": 4215412736, "shape": [ 3584 ], "size": 41287680, "type": 0 }, { "name": "blk.2.ffn_norm.weight", "offset": 4215427072, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.3.ffn_gate_inp.weight", "offset": 4215441408, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.3.attn_k.bias", "offset": 4216358912, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.3.attn_k.weight", "offset": 4216360960, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.3.attn_output.weight", "offset": 4217393152, "shape": [ 3584, 3584 ], "size": 1032192, "type": 12 }, { "name": "blk.3.attn_q.bias", "offset": 4224618496, "shape": [ 3584 ], "size": 7225344, "type": 0 }, { "name": "blk.3.attn_q.weight", "offset": 4224632832, "shape": [ 3584, 3584 ], "size": 14336, "type": 12 }, { "name": "blk.3.attn_v.bias", "offset": 4231858176, "shape": [ 512 ], "size": 7225344, "type": 0 }, { "name": "blk.3.attn_v.weight", "offset": 4231860224, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.3.attn_norm.weight", "offset": 4232892416, "shape": [ 3584 ], "size": 1032192, "type": 0 }, { "name": "blk.3.ffn_down_exps.weight", "offset": 4232906752, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 12 }, { "name": "blk.3.ffn_gate_exps.weight", "offset": 4563208192, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.3.ffn_up_exps.weight", "offset": 4893509632, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.3.ffn_down_shexp.weight", "offset": 5223811072, "shape": [ 20480, 3584 ], "size": 330301440, "type": 12 }, { "name": "blk.3.ffn_gate_shexp.weight", "offset": 5265098752, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.3.ffn_up_shexp.weight", "offset": 5306386432, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.3.ffn_gate_inp_shexp.weight", "offset": 5347674112, "shape": [ 3584 ], "size": 41287680, "type": 0 }, { "name": "blk.3.ffn_norm.weight", "offset": 5347688448, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.4.ffn_gate_inp.weight", "offset": 5347702784, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.4.attn_k.bias", "offset": 5348620288, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.4.attn_k.weight", "offset": 5348622336, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.4.attn_output.weight", "offset": 5349654528, "shape": [ 3584, 3584 ], "size": 1032192, "type": 12 }, { "name": "blk.4.attn_q.bias", "offset": 5356879872, "shape": [ 3584 ], "size": 7225344, "type": 0 }, { "name": "blk.4.attn_q.weight", "offset": 5356894208, "shape": [ 3584, 3584 ], "size": 14336, "type": 12 }, { "name": "blk.4.attn_v.bias", "offset": 5364119552, "shape": [ 512 ], "size": 7225344, "type": 0 }, { "name": "blk.4.attn_v.weight", "offset": 5364121600, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.4.attn_norm.weight", "offset": 5365153792, "shape": [ 3584 ], "size": 1032192, "type": 0 }, { "name": "blk.4.ffn_down_exps.weight", "offset": 5365168128, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 12 }, { "name": "blk.4.ffn_gate_exps.weight", "offset": 5695469568, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.4.ffn_up_exps.weight", "offset": 6025771008, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.4.ffn_down_shexp.weight", "offset": 6356072448, "shape": [ 20480, 3584 ], "size": 330301440, "type": 12 }, { "name": "blk.4.ffn_gate_shexp.weight", "offset": 6397360128, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.4.ffn_up_shexp.weight", "offset": 6438647808, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.4.ffn_gate_inp_shexp.weight", "offset": 6479935488, "shape": [ 3584 ], "size": 41287680, "type": 0 }, { "name": "blk.4.ffn_norm.weight", "offset": 6479949824, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.5.ffn_gate_inp.weight", "offset": 6479964160, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.5.attn_k.bias", "offset": 6480881664, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.5.attn_k.weight", "offset": 6480883712, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.5.attn_output.weight", "offset": 6481915904, "shape": [ 3584, 3584 ], "size": 1032192, "type": 12 }, { "name": "blk.5.attn_q.bias", "offset": 6489141248, "shape": [ 3584 ], "size": 7225344, "type": 0 }, { "name": "blk.5.attn_q.weight", "offset": 6489155584, "shape": [ 3584, 3584 ], "size": 14336, "type": 12 }, { "name": "blk.5.attn_v.bias", "offset": 6496380928, "shape": [ 512 ], "size": 7225344, "type": 0 }, { "name": "blk.5.attn_v.weight", "offset": 6496382976, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.5.attn_norm.weight", "offset": 6497888256, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.5.ffn_down_exps.weight", "offset": 6497902592, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.5.ffn_gate_exps.weight", "offset": 6979592192, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 12 }, { "name": "blk.5.ffn_up_exps.weight", "offset": 7309893632, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.5.ffn_down_shexp.weight", "offset": 7640195072, "shape": [ 20480, 3584 ], "size": 330301440, "type": 14 }, { "name": "blk.5.ffn_gate_shexp.weight", "offset": 7700406272, "shape": [ 3584, 20480 ], "size": 60211200, "type": 12 }, { "name": "blk.5.ffn_up_shexp.weight", "offset": 7741693952, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.5.ffn_gate_inp_shexp.weight", "offset": 7782981632, "shape": [ 3584 ], "size": 41287680, "type": 0 }, { "name": "blk.5.ffn_norm.weight", "offset": 7782995968, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.6.ffn_gate_inp.weight", "offset": 7783010304, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.6.attn_k.bias", "offset": 7783927808, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.6.attn_k.weight", "offset": 7783929856, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.6.attn_output.weight", "offset": 7784962048, "shape": [ 3584, 3584 ], "size": 1032192, "type": 12 }, { "name": "blk.6.attn_q.bias", "offset": 7792187392, "shape": [ 3584 ], "size": 7225344, "type": 0 }, { "name": "blk.6.attn_q.weight", "offset": 7792201728, "shape": [ 3584, 3584 ], "size": 14336, "type": 12 }, { "name": "blk.6.attn_v.bias", "offset": 7799427072, "shape": [ 512 ], "size": 7225344, "type": 0 }, { "name": "blk.6.attn_v.weight", "offset": 7799429120, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.6.attn_norm.weight", "offset": 7800461312, "shape": [ 3584 ], "size": 1032192, "type": 0 }, { "name": "blk.6.ffn_down_exps.weight", "offset": 7800475648, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 12 }, { "name": "blk.6.ffn_gate_exps.weight", "offset": 8130777088, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.6.ffn_up_exps.weight", "offset": 8461078528, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.6.ffn_down_shexp.weight", "offset": 8791379968, "shape": [ 20480, 3584 ], "size": 330301440, "type": 12 }, { "name": "blk.6.ffn_gate_shexp.weight", "offset": 8832667648, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.6.ffn_up_shexp.weight", "offset": 8873955328, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.6.ffn_gate_inp_shexp.weight", "offset": 8915243008, "shape": [ 3584 ], "size": 41287680, "type": 0 }, { "name": "blk.6.ffn_norm.weight", "offset": 8915257344, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.7.ffn_gate_inp.weight", "offset": 8915271680, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.7.attn_k.bias", "offset": 8916189184, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.7.attn_k.weight", "offset": 8916191232, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.7.attn_output.weight", "offset": 8917223424, "shape": [ 3584, 3584 ], "size": 1032192, "type": 12 }, { "name": "blk.7.attn_q.bias", "offset": 8924448768, "shape": [ 3584 ], "size": 7225344, "type": 0 }, { "name": "blk.7.attn_q.weight", "offset": 8924463104, "shape": [ 3584, 3584 ], "size": 14336, "type": 12 }, { "name": "blk.7.attn_v.bias", "offset": 8931688448, "shape": [ 512 ], "size": 7225344, "type": 0 }, { "name": "blk.7.attn_v.weight", "offset": 8931690496, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.7.attn_norm.weight", "offset": 8932722688, "shape": [ 3584 ], "size": 1032192, "type": 0 }, { "name": "blk.7.ffn_down_exps.weight", "offset": 8932737024, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 12 }, { "name": "blk.7.ffn_gate_exps.weight", "offset": 9263038464, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.7.ffn_up_exps.weight", "offset": 9593339904, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.7.ffn_down_shexp.weight", "offset": 9923641344, "shape": [ 20480, 3584 ], "size": 330301440, "type": 12 }, { "name": "blk.7.ffn_gate_shexp.weight", "offset": 9964929024, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.7.ffn_up_shexp.weight", "offset": 10006216704, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.7.ffn_gate_inp_shexp.weight", "offset": 10047504384, "shape": [ 3584 ], "size": 41287680, "type": 0 }, { "name": "blk.7.ffn_norm.weight", "offset": 10047518720, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.8.ffn_gate_inp.weight", "offset": 10047533056, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.8.attn_k.bias", "offset": 10048450560, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.8.attn_k.weight", "offset": 10048452608, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.8.attn_output.weight", "offset": 10049484800, "shape": [ 3584, 3584 ], "size": 1032192, "type": 12 }, { "name": "blk.8.attn_q.bias", "offset": 10056710144, "shape": [ 3584 ], "size": 7225344, "type": 0 }, { "name": "blk.8.attn_q.weight", "offset": 10056724480, "shape": [ 3584, 3584 ], "size": 14336, "type": 12 }, { "name": "blk.8.attn_v.bias", "offset": 10063949824, "shape": [ 512 ], "size": 7225344, "type": 0 }, { "name": "blk.8.attn_v.weight", "offset": 10063951872, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.8.attn_norm.weight", "offset": 10065457152, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.8.ffn_down_exps.weight", "offset": 10065471488, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.8.ffn_gate_exps.weight", "offset": 10547161088, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 12 }, { "name": "blk.8.ffn_up_exps.weight", "offset": 10877462528, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.8.ffn_down_shexp.weight", "offset": 11207763968, "shape": [ 20480, 3584 ], "size": 330301440, "type": 14 }, { "name": "blk.8.ffn_gate_shexp.weight", "offset": 11267975168, "shape": [ 3584, 20480 ], "size": 60211200, "type": 12 }, { "name": "blk.8.ffn_up_shexp.weight", "offset": 11309262848, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.8.ffn_gate_inp_shexp.weight", "offset": 11350550528, "shape": [ 3584 ], "size": 41287680, "type": 0 }, { "name": "blk.8.ffn_norm.weight", "offset": 11350564864, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.9.ffn_gate_inp.weight", "offset": 11350579200, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.9.attn_k.bias", "offset": 11351496704, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.9.attn_k.weight", "offset": 11351498752, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.9.attn_output.weight", "offset": 11352530944, "shape": [ 3584, 3584 ], "size": 1032192, "type": 12 }, { "name": "blk.9.attn_q.bias", "offset": 11359756288, "shape": [ 3584 ], "size": 7225344, "type": 0 }, { "name": "blk.9.attn_q.weight", "offset": 11359770624, "shape": [ 3584, 3584 ], "size": 14336, "type": 12 }, { "name": "blk.9.attn_v.bias", "offset": 11366995968, "shape": [ 512 ], "size": 7225344, "type": 0 }, { "name": "blk.9.attn_v.weight", "offset": 11366998016, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.10.ffn_gate_inp.weight", "offset": 11368030208, "shape": [ 3584, 64 ], "size": 1032192, "type": 0 }, { "name": "blk.10.attn_k.bias", "offset": 11368947712, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.10.attn_k.weight", "offset": 11368949760, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.10.attn_output.weight", "offset": 11369981952, "shape": [ 3584, 3584 ], "size": 1032192, "type": 12 }, { "name": "blk.10.attn_q.bias", "offset": 11377207296, "shape": [ 3584 ], "size": 7225344, "type": 0 }, { "name": "blk.10.attn_q.weight", "offset": 11377221632, "shape": [ 3584, 3584 ], "size": 14336, "type": 12 }, { "name": "blk.10.attn_v.bias", "offset": 11384446976, "shape": [ 512 ], "size": 7225344, "type": 0 }, { "name": "blk.10.attn_v.weight", "offset": 11384449024, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.9.attn_norm.weight", "offset": 11385481216, "shape": [ 3584 ], "size": 1032192, "type": 0 }, { "name": "blk.9.ffn_down_exps.weight", "offset": 11385495552, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 12 }, { "name": "blk.9.ffn_gate_exps.weight", "offset": 11715796992, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.9.ffn_up_exps.weight", "offset": 12046098432, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.9.ffn_down_shexp.weight", "offset": 12376399872, "shape": [ 20480, 3584 ], "size": 330301440, "type": 12 }, { "name": "blk.9.ffn_gate_shexp.weight", "offset": 12417687552, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.9.ffn_up_shexp.weight", "offset": 12458975232, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.9.ffn_gate_inp_shexp.weight", "offset": 12500262912, "shape": [ 3584 ], "size": 41287680, "type": 0 }, { "name": "blk.9.ffn_norm.weight", "offset": 12500277248, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.10.attn_norm.weight", "offset": 12500291584, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.10.ffn_down_exps.weight", "offset": 12500305920, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 12 }, { "name": "blk.10.ffn_gate_exps.weight", "offset": 12830607360, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.10.ffn_up_exps.weight", "offset": 13160908800, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.10.ffn_down_shexp.weight", "offset": 13491210240, "shape": [ 20480, 3584 ], "size": 330301440, "type": 12 }, { "name": "blk.10.ffn_gate_shexp.weight", "offset": 13532497920, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.10.ffn_up_shexp.weight", "offset": 13573785600, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.10.ffn_gate_inp_shexp.weight", "offset": 13615073280, "shape": [ 3584 ], "size": 41287680, "type": 0 }, { "name": "blk.10.ffn_norm.weight", "offset": 13615087616, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.11.ffn_gate_inp.weight", "offset": 13615101952, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.11.attn_k.bias", "offset": 13616019456, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.11.attn_k.weight", "offset": 13616021504, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.11.attn_output.weight", "offset": 13617053696, "shape": [ 3584, 3584 ], "size": 1032192, "type": 12 }, { "name": "blk.11.attn_q.bias", "offset": 13624279040, "shape": [ 3584 ], "size": 7225344, "type": 0 }, { "name": "blk.11.attn_q.weight", "offset": 13624293376, "shape": [ 3584, 3584 ], "size": 14336, "type": 12 }, { "name": "blk.11.attn_v.bias", "offset": 13631518720, "shape": [ 512 ], "size": 7225344, "type": 0 }, { "name": "blk.11.attn_v.weight", "offset": 13631520768, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.11.attn_norm.weight", "offset": 13633026048, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.11.ffn_down_exps.weight", "offset": 13633040384, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.11.ffn_gate_exps.weight", "offset": 14114729984, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 12 }, { "name": "blk.11.ffn_up_exps.weight", "offset": 14445031424, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.11.ffn_down_shexp.weight", "offset": 14775332864, "shape": [ 20480, 3584 ], "size": 330301440, "type": 14 }, { "name": "blk.11.ffn_gate_shexp.weight", "offset": 14835544064, "shape": [ 3584, 20480 ], "size": 60211200, "type": 12 }, { "name": "blk.11.ffn_up_shexp.weight", "offset": 14876831744, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.11.ffn_gate_inp_shexp.weight", "offset": 14918119424, "shape": [ 3584 ], "size": 41287680, "type": 0 }, { "name": "blk.11.ffn_norm.weight", "offset": 14918133760, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.12.ffn_gate_inp.weight", "offset": 14918148096, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.12.attn_k.bias", "offset": 14919065600, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.12.attn_k.weight", "offset": 14919067648, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.12.attn_output.weight", "offset": 14920099840, "shape": [ 3584, 3584 ], "size": 1032192, "type": 12 }, { "name": "blk.12.attn_q.bias", "offset": 14927325184, "shape": [ 3584 ], "size": 7225344, "type": 0 }, { "name": "blk.12.attn_q.weight", "offset": 14927339520, "shape": [ 3584, 3584 ], "size": 14336, "type": 12 }, { "name": "blk.12.attn_v.bias", "offset": 14934564864, "shape": [ 512 ], "size": 7225344, "type": 0 }, { "name": "blk.12.attn_v.weight", "offset": 14934566912, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.12.attn_norm.weight", "offset": 14935599104, "shape": [ 3584 ], "size": 1032192, "type": 0 }, { "name": "blk.12.ffn_down_exps.weight", "offset": 14935613440, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 12 }, { "name": "blk.12.ffn_gate_exps.weight", "offset": 15265914880, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.12.ffn_up_exps.weight", "offset": 15596216320, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.12.ffn_down_shexp.weight", "offset": 15926517760, "shape": [ 20480, 3584 ], "size": 330301440, "type": 12 }, { "name": "blk.12.ffn_gate_shexp.weight", "offset": 15967805440, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.12.ffn_up_shexp.weight", "offset": 16009093120, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.12.ffn_gate_inp_shexp.weight", "offset": 16050380800, "shape": [ 3584 ], "size": 41287680, "type": 0 }, { "name": "blk.12.ffn_norm.weight", "offset": 16050395136, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.13.ffn_gate_inp.weight", "offset": 16050409472, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.13.attn_k.bias", "offset": 16051326976, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.13.attn_k.weight", "offset": 16051329024, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.13.attn_output.weight", "offset": 16052361216, "shape": [ 3584, 3584 ], "size": 1032192, "type": 12 }, { "name": "blk.13.attn_q.bias", "offset": 16059586560, "shape": [ 3584 ], "size": 7225344, "type": 0 }, { "name": "blk.13.attn_q.weight", "offset": 16059600896, "shape": [ 3584, 3584 ], "size": 14336, "type": 12 }, { "name": "blk.13.attn_v.bias", "offset": 16066826240, "shape": [ 512 ], "size": 7225344, "type": 0 }, { "name": "blk.13.attn_v.weight", "offset": 16066828288, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.13.attn_norm.weight", "offset": 16067860480, "shape": [ 3584 ], "size": 1032192, "type": 0 }, { "name": "blk.13.ffn_down_exps.weight", "offset": 16067874816, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 12 }, { "name": "blk.13.ffn_gate_exps.weight", "offset": 16398176256, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.13.ffn_up_exps.weight", "offset": 16728477696, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.13.ffn_down_shexp.weight", "offset": 17058779136, "shape": [ 20480, 3584 ], "size": 330301440, "type": 12 }, { "name": "blk.13.ffn_gate_shexp.weight", "offset": 17100066816, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.13.ffn_up_shexp.weight", "offset": 17141354496, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.13.ffn_gate_inp_shexp.weight", "offset": 17182642176, "shape": [ 3584 ], "size": 41287680, "type": 0 }, { "name": "blk.13.ffn_norm.weight", "offset": 17182656512, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.14.ffn_gate_inp.weight", "offset": 17182670848, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.14.attn_k.bias", "offset": 17183588352, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.14.attn_k.weight", "offset": 17183590400, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.14.attn_output.weight", "offset": 17184622592, "shape": [ 3584, 3584 ], "size": 1032192, "type": 12 }, { "name": "blk.14.attn_q.bias", "offset": 17191847936, "shape": [ 3584 ], "size": 7225344, "type": 0 }, { "name": "blk.14.attn_q.weight", "offset": 17191862272, "shape": [ 3584, 3584 ], "size": 14336, "type": 12 }, { "name": "blk.14.attn_v.bias", "offset": 17199087616, "shape": [ 512 ], "size": 7225344, "type": 0 }, { "name": "blk.14.attn_v.weight", "offset": 17199089664, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.14.attn_norm.weight", "offset": 17200594944, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.14.ffn_down_exps.weight", "offset": 17200609280, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.14.ffn_gate_exps.weight", "offset": 17682298880, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 12 }, { "name": "blk.14.ffn_up_exps.weight", "offset": 18012600320, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.14.ffn_down_shexp.weight", "offset": 18342901760, "shape": [ 20480, 3584 ], "size": 330301440, "type": 14 }, { "name": "blk.14.ffn_gate_shexp.weight", "offset": 18403112960, "shape": [ 3584, 20480 ], "size": 60211200, "type": 12 }, { "name": "blk.14.ffn_up_shexp.weight", "offset": 18444400640, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.14.ffn_gate_inp_shexp.weight", "offset": 18485688320, "shape": [ 3584 ], "size": 41287680, "type": 0 }, { "name": "blk.14.ffn_norm.weight", "offset": 18485702656, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.15.ffn_gate_inp.weight", "offset": 18485716992, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.15.attn_k.bias", "offset": 18486634496, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.15.attn_k.weight", "offset": 18486636544, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.15.attn_output.weight", "offset": 18487668736, "shape": [ 3584, 3584 ], "size": 1032192, "type": 12 }, { "name": "blk.15.attn_q.bias", "offset": 18494894080, "shape": [ 3584 ], "size": 7225344, "type": 0 }, { "name": "blk.15.attn_q.weight", "offset": 18494908416, "shape": [ 3584, 3584 ], "size": 14336, "type": 12 }, { "name": "blk.15.attn_v.bias", "offset": 18502133760, "shape": [ 512 ], "size": 7225344, "type": 0 }, { "name": "blk.15.attn_v.weight", "offset": 18502135808, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.15.attn_norm.weight", "offset": 18503168000, "shape": [ 3584 ], "size": 1032192, "type": 0 }, { "name": "blk.15.ffn_down_exps.weight", "offset": 18503182336, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 12 }, { "name": "blk.15.ffn_gate_exps.weight", "offset": 18833483776, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.15.ffn_up_exps.weight", "offset": 19163785216, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.15.ffn_down_shexp.weight", "offset": 19494086656, "shape": [ 20480, 3584 ], "size": 330301440, "type": 12 }, { "name": "blk.15.ffn_gate_shexp.weight", "offset": 19535374336, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.15.ffn_up_shexp.weight", "offset": 19576662016, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.15.ffn_gate_inp_shexp.weight", "offset": 19617949696, "shape": [ 3584 ], "size": 41287680, "type": 0 }, { "name": "blk.15.ffn_norm.weight", "offset": 19617964032, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.16.ffn_gate_inp.weight", "offset": 19617978368, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.16.attn_k.bias", "offset": 19618895872, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.16.attn_k.weight", "offset": 19618897920, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.16.attn_output.weight", "offset": 19619930112, "shape": [ 3584, 3584 ], "size": 1032192, "type": 12 }, { "name": "blk.16.attn_q.bias", "offset": 19627155456, "shape": [ 3584 ], "size": 7225344, "type": 0 }, { "name": "blk.16.attn_q.weight", "offset": 19627169792, "shape": [ 3584, 3584 ], "size": 14336, "type": 12 }, { "name": "blk.16.attn_v.bias", "offset": 19634395136, "shape": [ 512 ], "size": 7225344, "type": 0 }, { "name": "blk.16.attn_v.weight", "offset": 19634397184, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.16.attn_norm.weight", "offset": 19635429376, "shape": [ 3584 ], "size": 1032192, "type": 0 }, { "name": "blk.16.ffn_down_exps.weight", "offset": 19635443712, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 12 }, { "name": "blk.16.ffn_gate_exps.weight", "offset": 19965745152, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.16.ffn_up_exps.weight", "offset": 20296046592, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.16.ffn_down_shexp.weight", "offset": 20626348032, "shape": [ 20480, 3584 ], "size": 330301440, "type": 12 }, { "name": "blk.16.ffn_gate_shexp.weight", "offset": 20667635712, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.16.ffn_up_shexp.weight", "offset": 20708923392, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.16.ffn_gate_inp_shexp.weight", "offset": 20750211072, "shape": [ 3584 ], "size": 41287680, "type": 0 }, { "name": "blk.16.ffn_norm.weight", "offset": 20750225408, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.17.ffn_gate_inp.weight", "offset": 20750239744, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.17.attn_k.bias", "offset": 20751157248, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.17.attn_k.weight", "offset": 20751159296, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.17.attn_output.weight", "offset": 20752191488, "shape": [ 3584, 3584 ], "size": 1032192, "type": 12 }, { "name": "blk.17.attn_q.bias", "offset": 20759416832, "shape": [ 3584 ], "size": 7225344, "type": 0 }, { "name": "blk.17.attn_q.weight", "offset": 20759431168, "shape": [ 3584, 3584 ], "size": 14336, "type": 12 }, { "name": "blk.17.attn_v.bias", "offset": 20766656512, "shape": [ 512 ], "size": 7225344, "type": 0 }, { "name": "blk.17.attn_v.weight", "offset": 20766658560, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.17.attn_norm.weight", "offset": 20768163840, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.17.ffn_down_exps.weight", "offset": 20768178176, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.17.ffn_gate_exps.weight", "offset": 21249867776, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 12 }, { "name": "blk.17.ffn_up_exps.weight", "offset": 21580169216, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.17.ffn_down_shexp.weight", "offset": 21910470656, "shape": [ 20480, 3584 ], "size": 330301440, "type": 14 }, { "name": "blk.17.ffn_gate_shexp.weight", "offset": 21970681856, "shape": [ 3584, 20480 ], "size": 60211200, "type": 12 }, { "name": "blk.17.ffn_up_shexp.weight", "offset": 22011969536, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.17.ffn_gate_inp_shexp.weight", "offset": 22053257216, "shape": [ 3584 ], "size": 41287680, "type": 0 }, { "name": "blk.17.ffn_norm.weight", "offset": 22053271552, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.18.ffn_gate_inp.weight", "offset": 22053285888, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.18.attn_k.bias", "offset": 22054203392, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.18.attn_k.weight", "offset": 22054205440, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.18.attn_output.weight", "offset": 22055237632, "shape": [ 3584, 3584 ], "size": 1032192, "type": 12 }, { "name": "blk.18.attn_q.bias", "offset": 22062462976, "shape": [ 3584 ], "size": 7225344, "type": 0 }, { "name": "blk.18.attn_q.weight", "offset": 22062477312, "shape": [ 3584, 3584 ], "size": 14336, "type": 12 }, { "name": "blk.18.attn_v.bias", "offset": 22069702656, "shape": [ 512 ], "size": 7225344, "type": 0 }, { "name": "blk.18.attn_v.weight", "offset": 22069704704, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.18.attn_norm.weight", "offset": 22070736896, "shape": [ 3584 ], "size": 1032192, "type": 0 }, { "name": "blk.18.ffn_down_exps.weight", "offset": 22070751232, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 12 }, { "name": "blk.18.ffn_gate_exps.weight", "offset": 22401052672, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.18.ffn_up_exps.weight", "offset": 22731354112, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.18.ffn_down_shexp.weight", "offset": 23061655552, "shape": [ 20480, 3584 ], "size": 330301440, "type": 12 }, { "name": "blk.18.ffn_gate_shexp.weight", "offset": 23102943232, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.18.ffn_up_shexp.weight", "offset": 23144230912, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.18.ffn_gate_inp_shexp.weight", "offset": 23185518592, "shape": [ 3584 ], "size": 41287680, "type": 0 }, { "name": "blk.18.ffn_norm.weight", "offset": 23185532928, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.19.ffn_gate_inp.weight", "offset": 23185547264, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.19.attn_k.bias", "offset": 23186464768, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.19.attn_k.weight", "offset": 23186466816, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.19.attn_output.weight", "offset": 23187499008, "shape": [ 3584, 3584 ], "size": 1032192, "type": 12 }, { "name": "blk.19.attn_q.bias", "offset": 23194724352, "shape": [ 3584 ], "size": 7225344, "type": 0 }, { "name": "blk.19.attn_q.weight", "offset": 23194738688, "shape": [ 3584, 3584 ], "size": 14336, "type": 12 }, { "name": "blk.19.attn_v.bias", "offset": 23201964032, "shape": [ 512 ], "size": 7225344, "type": 0 }, { "name": "blk.19.attn_v.weight", "offset": 23201966080, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.19.attn_norm.weight", "offset": 23202998272, "shape": [ 3584 ], "size": 1032192, "type": 0 }, { "name": "blk.19.ffn_down_exps.weight", "offset": 23203012608, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 12 }, { "name": "blk.19.ffn_gate_exps.weight", "offset": 23533314048, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.19.ffn_up_exps.weight", "offset": 23863615488, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.19.ffn_down_shexp.weight", "offset": 24193916928, "shape": [ 20480, 3584 ], "size": 330301440, "type": 12 }, { "name": "blk.19.ffn_gate_shexp.weight", "offset": 24235204608, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.19.ffn_up_shexp.weight", "offset": 24276492288, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.19.ffn_gate_inp_shexp.weight", "offset": 24317779968, "shape": [ 3584 ], "size": 41287680, "type": 0 }, { "name": "blk.19.ffn_norm.weight", "offset": 24317794304, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.20.ffn_gate_inp.weight", "offset": 24317808640, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.20.attn_k.bias", "offset": 24318726144, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.20.attn_k.weight", "offset": 24318728192, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.20.attn_output.weight", "offset": 24319760384, "shape": [ 3584, 3584 ], "size": 1032192, "type": 12 }, { "name": "blk.20.attn_q.bias", "offset": 24326985728, "shape": [ 3584 ], "size": 7225344, "type": 0 }, { "name": "blk.20.attn_q.weight", "offset": 24327000064, "shape": [ 3584, 3584 ], "size": 14336, "type": 12 }, { "name": "blk.20.attn_v.bias", "offset": 24334225408, "shape": [ 512 ], "size": 7225344, "type": 0 }, { "name": "blk.20.attn_v.weight", "offset": 24334227456, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.20.attn_norm.weight", "offset": 24335732736, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.20.ffn_down_exps.weight", "offset": 24335747072, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.20.ffn_gate_exps.weight", "offset": 24817436672, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 12 }, { "name": "blk.20.ffn_up_exps.weight", "offset": 25147738112, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.20.ffn_down_shexp.weight", "offset": 25478039552, "shape": [ 20480, 3584 ], "size": 330301440, "type": 14 }, { "name": "blk.20.ffn_gate_shexp.weight", "offset": 25538250752, "shape": [ 3584, 20480 ], "size": 60211200, "type": 12 }, { "name": "blk.20.ffn_up_shexp.weight", "offset": 25579538432, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.20.ffn_gate_inp_shexp.weight", "offset": 25620826112, "shape": [ 3584 ], "size": 41287680, "type": 0 }, { "name": "blk.20.ffn_norm.weight", "offset": 25620840448, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.21.ffn_gate_inp.weight", "offset": 25620854784, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.21.attn_k.bias", "offset": 25621772288, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.21.attn_k.weight", "offset": 25621774336, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.21.attn_output.weight", "offset": 25622806528, "shape": [ 3584, 3584 ], "size": 1032192, "type": 12 }, { "name": "blk.21.attn_q.bias", "offset": 25630031872, "shape": [ 3584 ], "size": 7225344, "type": 0 }, { "name": "blk.21.attn_q.weight", "offset": 25630046208, "shape": [ 3584, 3584 ], "size": 14336, "type": 12 }, { "name": "blk.21.attn_v.bias", "offset": 25637271552, "shape": [ 512 ], "size": 7225344, "type": 0 }, { "name": "blk.21.attn_v.weight", "offset": 25637273600, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.21.attn_norm.weight", "offset": 25638305792, "shape": [ 3584 ], "size": 1032192, "type": 0 }, { "name": "blk.21.ffn_down_exps.weight", "offset": 25638320128, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 12 }, { "name": "blk.21.ffn_gate_exps.weight", "offset": 25968621568, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.21.ffn_up_exps.weight", "offset": 26298923008, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.21.ffn_down_shexp.weight", "offset": 26629224448, "shape": [ 20480, 3584 ], "size": 330301440, "type": 12 }, { "name": "blk.21.ffn_gate_shexp.weight", "offset": 26670512128, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.21.ffn_up_shexp.weight", "offset": 26711799808, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.21.ffn_gate_inp_shexp.weight", "offset": 26753087488, "shape": [ 3584 ], "size": 41287680, "type": 0 }, { "name": "blk.21.ffn_norm.weight", "offset": 26753101824, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.22.ffn_gate_inp.weight", "offset": 26753116160, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.22.attn_k.bias", "offset": 26754033664, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.22.attn_k.weight", "offset": 26754035712, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.22.attn_output.weight", "offset": 26755067904, "shape": [ 3584, 3584 ], "size": 1032192, "type": 12 }, { "name": "blk.22.attn_q.bias", "offset": 26762293248, "shape": [ 3584 ], "size": 7225344, "type": 0 }, { "name": "blk.22.attn_q.weight", "offset": 26762307584, "shape": [ 3584, 3584 ], "size": 14336, "type": 12 }, { "name": "blk.22.attn_v.bias", "offset": 26769532928, "shape": [ 512 ], "size": 7225344, "type": 0 }, { "name": "blk.22.attn_v.weight", "offset": 26769534976, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.22.attn_norm.weight", "offset": 26770567168, "shape": [ 3584 ], "size": 1032192, "type": 0 }, { "name": "blk.22.ffn_down_exps.weight", "offset": 26770581504, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 12 }, { "name": "blk.22.ffn_gate_exps.weight", "offset": 27100882944, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.22.ffn_up_exps.weight", "offset": 27431184384, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.22.ffn_down_shexp.weight", "offset": 27761485824, "shape": [ 20480, 3584 ], "size": 330301440, "type": 12 }, { "name": "blk.22.ffn_gate_shexp.weight", "offset": 27802773504, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.22.ffn_up_shexp.weight", "offset": 27844061184, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.22.ffn_gate_inp_shexp.weight", "offset": 27885348864, "shape": [ 3584 ], "size": 41287680, "type": 0 }, { "name": "blk.22.ffn_norm.weight", "offset": 27885363200, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.23.ffn_gate_inp.weight", "offset": 27885377536, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.23.attn_k.bias", "offset": 27886295040, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.23.attn_k.weight", "offset": 27886297088, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.23.attn_output.weight", "offset": 27887329280, "shape": [ 3584, 3584 ], "size": 1032192, "type": 12 }, { "name": "blk.23.attn_q.bias", "offset": 27894554624, "shape": [ 3584 ], "size": 7225344, "type": 0 }, { "name": "blk.23.attn_q.weight", "offset": 27894568960, "shape": [ 3584, 3584 ], "size": 14336, "type": 12 }, { "name": "blk.23.attn_v.bias", "offset": 27901794304, "shape": [ 512 ], "size": 7225344, "type": 0 }, { "name": "blk.23.attn_v.weight", "offset": 27901796352, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.23.attn_norm.weight", "offset": 27903301632, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.23.ffn_down_exps.weight", "offset": 27903315968, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.23.ffn_gate_exps.weight", "offset": 28385005568, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 12 }, { "name": "blk.23.ffn_up_exps.weight", "offset": 28715307008, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.23.ffn_down_shexp.weight", "offset": 29045608448, "shape": [ 20480, 3584 ], "size": 330301440, "type": 14 }, { "name": "blk.23.ffn_gate_shexp.weight", "offset": 29105819648, "shape": [ 3584, 20480 ], "size": 60211200, "type": 12 }, { "name": "blk.23.ffn_up_shexp.weight", "offset": 29147107328, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.23.ffn_gate_inp_shexp.weight", "offset": 29188395008, "shape": [ 3584 ], "size": 41287680, "type": 0 }, { "name": "blk.23.ffn_norm.weight", "offset": 29188409344, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.24.ffn_gate_inp.weight", "offset": 29188423680, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.24.attn_k.bias", "offset": 29189341184, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.24.attn_k.weight", "offset": 29189343232, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.24.attn_output.weight", "offset": 29190375424, "shape": [ 3584, 3584 ], "size": 1032192, "type": 12 }, { "name": "blk.24.attn_q.bias", "offset": 29197600768, "shape": [ 3584 ], "size": 7225344, "type": 0 }, { "name": "blk.24.attn_q.weight", "offset": 29197615104, "shape": [ 3584, 3584 ], "size": 14336, "type": 12 }, { "name": "blk.24.attn_v.bias", "offset": 29204840448, "shape": [ 512 ], "size": 7225344, "type": 0 }, { "name": "blk.24.attn_v.weight", "offset": 29204842496, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.24.attn_norm.weight", "offset": 29206347776, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.24.ffn_down_exps.weight", "offset": 29206362112, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.24.ffn_gate_exps.weight", "offset": 29688051712, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 12 }, { "name": "blk.24.ffn_up_exps.weight", "offset": 30018353152, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.24.ffn_down_shexp.weight", "offset": 30348654592, "shape": [ 20480, 3584 ], "size": 330301440, "type": 14 }, { "name": "blk.24.ffn_gate_shexp.weight", "offset": 30408865792, "shape": [ 3584, 20480 ], "size": 60211200, "type": 12 }, { "name": "blk.24.ffn_up_shexp.weight", "offset": 30450153472, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.24.ffn_gate_inp_shexp.weight", "offset": 30491441152, "shape": [ 3584 ], "size": 41287680, "type": 0 }, { "name": "blk.24.ffn_norm.weight", "offset": 30491455488, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.25.ffn_gate_inp.weight", "offset": 30491469824, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.25.attn_k.bias", "offset": 30492387328, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.25.attn_k.weight", "offset": 30492389376, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.25.attn_output.weight", "offset": 30493421568, "shape": [ 3584, 3584 ], "size": 1032192, "type": 12 }, { "name": "blk.25.attn_q.bias", "offset": 30500646912, "shape": [ 3584 ], "size": 7225344, "type": 0 }, { "name": "blk.25.attn_q.weight", "offset": 30500661248, "shape": [ 3584, 3584 ], "size": 14336, "type": 12 }, { "name": "blk.25.attn_v.bias", "offset": 30507886592, "shape": [ 512 ], "size": 7225344, "type": 0 }, { "name": "blk.25.attn_v.weight", "offset": 30507888640, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.25.attn_norm.weight", "offset": 30509393920, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.25.ffn_down_exps.weight", "offset": 30509408256, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.25.ffn_gate_exps.weight", "offset": 30991097856, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 12 }, { "name": "blk.25.ffn_up_exps.weight", "offset": 31321399296, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.25.ffn_down_shexp.weight", "offset": 31651700736, "shape": [ 20480, 3584 ], "size": 330301440, "type": 14 }, { "name": "blk.25.ffn_gate_shexp.weight", "offset": 31711911936, "shape": [ 3584, 20480 ], "size": 60211200, "type": 12 }, { "name": "blk.25.ffn_up_shexp.weight", "offset": 31753199616, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.25.ffn_gate_inp_shexp.weight", "offset": 31794487296, "shape": [ 3584 ], "size": 41287680, "type": 0 }, { "name": "blk.25.ffn_norm.weight", "offset": 31794501632, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.26.ffn_gate_inp.weight", "offset": 31794515968, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.26.attn_k.bias", "offset": 31795433472, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.26.attn_k.weight", "offset": 31795435520, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.26.attn_output.weight", "offset": 31796467712, "shape": [ 3584, 3584 ], "size": 1032192, "type": 12 }, { "name": "blk.26.attn_q.bias", "offset": 31803693056, "shape": [ 3584 ], "size": 7225344, "type": 0 }, { "name": "blk.26.attn_q.weight", "offset": 31803707392, "shape": [ 3584, 3584 ], "size": 14336, "type": 12 }, { "name": "blk.26.attn_v.bias", "offset": 31810932736, "shape": [ 512 ], "size": 7225344, "type": 0 }, { "name": "blk.26.attn_v.weight", "offset": 31810934784, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.26.attn_norm.weight", "offset": 31812440064, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.26.ffn_down_exps.weight", "offset": 31812454400, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.26.ffn_gate_exps.weight", "offset": 32294144000, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 12 }, { "name": "blk.26.ffn_up_exps.weight", "offset": 32624445440, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.26.ffn_down_shexp.weight", "offset": 32954746880, "shape": [ 20480, 3584 ], "size": 330301440, "type": 14 }, { "name": "blk.26.ffn_gate_shexp.weight", "offset": 33014958080, "shape": [ 3584, 20480 ], "size": 60211200, "type": 12 }, { "name": "blk.26.ffn_up_shexp.weight", "offset": 33056245760, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.26.ffn_gate_inp_shexp.weight", "offset": 33097533440, "shape": [ 3584 ], "size": 41287680, "type": 0 }, { "name": "blk.26.ffn_norm.weight", "offset": 33097547776, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.27.ffn_gate_inp.weight", "offset": 33097562112, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.27.attn_k.bias", "offset": 33098479616, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.27.attn_k.weight", "offset": 33098481664, "shape": [ 3584, 512 ], "size": 2048, "type": 12 }, { "name": "blk.27.attn_output.weight", "offset": 33099513856, "shape": [ 3584, 3584 ], "size": 1032192, "type": 12 }, { "name": "blk.27.attn_q.bias", "offset": 33106739200, "shape": [ 3584 ], "size": 7225344, "type": 0 }, { "name": "blk.27.attn_q.weight", "offset": 33106753536, "shape": [ 3584, 3584 ], "size": 14336, "type": 12 }, { "name": "blk.27.attn_v.bias", "offset": 33113978880, "shape": [ 512 ], "size": 7225344, "type": 0 }, { "name": "blk.27.attn_v.weight", "offset": 33113980928, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "output.weight", "offset": 33115486208, "shape": [ 3584, 151936 ], "size": 1505280, "type": 14 }, { "name": "blk.27.attn_norm.weight", "offset": 33562178048, "shape": [ 3584 ], "size": 446691840, "type": 0 }, { "name": "blk.27.ffn_down_exps.weight", "offset": 33562192384, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.27.ffn_gate_exps.weight", "offset": 34043881984, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 12 }, { "name": "blk.27.ffn_up_exps.weight", "offset": 34374183424, "shape": [ 3584, 2560, 64 ], "size": 330301440, "type": 12 }, { "name": "blk.27.ffn_down_shexp.weight", "offset": 34704484864, "shape": [ 20480, 3584 ], "size": 330301440, "type": 14 }, { "name": "blk.27.ffn_gate_shexp.weight", "offset": 34764696064, "shape": [ 3584, 20480 ], "size": 60211200, "type": 12 }, { "name": "blk.27.ffn_up_shexp.weight", "offset": 34805983744, "shape": [ 3584, 20480 ], "size": 41287680, "type": 12 }, { "name": "blk.27.ffn_gate_inp_shexp.weight", "offset": 34847271424, "shape": [ 3584 ], "size": 41287680, "type": 0 }, { "name": "blk.27.ffn_norm.weight", "offset": 34847285760, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "output_norm.weight", "offset": 34847300096, "shape": [ 3584 ], "size": 14336, "type": 0 } ], "version": 3 }