Qwen2 MOE 57B

298 Pulls Updated 3 weeks ago

59a9e0577b00 · 47GB
{ "metadata": { "general.architecture": "qwen2moe", "general.file_type": 18, "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": "2024-06-07T15:15:52+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": 446691840, "shape": [ 3584, 64 ], "size": 446691840, "type": 0 }, { "name": "blk.0.attn_k.bias", "offset": 447609344, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.0.attn_k.weight", "offset": 447611392, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.0.attn_output.weight", "offset": 449116672, "shape": [ 3584, 3584 ], "size": 1505280, "type": 14 }, { "name": "blk.0.attn_q.bias", "offset": 459653632, "shape": [ 3584 ], "size": 10536960, "type": 0 }, { "name": "blk.0.attn_q.weight", "offset": 459667968, "shape": [ 3584, 3584 ], "size": 14336, "type": 14 }, { "name": "blk.0.attn_v.bias", "offset": 470204928, "shape": [ 512 ], "size": 10536960, "type": 0 }, { "name": "blk.0.attn_v.weight", "offset": 470206976, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.0.attn_norm.weight", "offset": 471712256, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.0.ffn_down_exps.weight", "offset": 471726592, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.0.ffn_gate_exps.weight", "offset": 953416192, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.0.ffn_up_exps.weight", "offset": 1435105792, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.0.ffn_down_shexp.weight", "offset": 1916795392, "shape": [ 20480, 3584 ], "size": 481689600, "type": 14 }, { "name": "blk.0.ffn_gate_shexp.weight", "offset": 1977006592, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.0.ffn_up_shexp.weight", "offset": 2037217792, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.0.ffn_gate_inp_shexp.weight", "offset": 2097428992, "shape": [ 3584 ], "size": 60211200, "type": 0 }, { "name": "blk.0.ffn_norm.weight", "offset": 2097443328, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.1.ffn_gate_inp.weight", "offset": 2097457664, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.1.attn_k.bias", "offset": 2098375168, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.1.attn_k.weight", "offset": 2098377216, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.1.attn_output.weight", "offset": 2099882496, "shape": [ 3584, 3584 ], "size": 1505280, "type": 14 }, { "name": "blk.1.attn_q.bias", "offset": 2110419456, "shape": [ 3584 ], "size": 10536960, "type": 0 }, { "name": "blk.1.attn_q.weight", "offset": 2110433792, "shape": [ 3584, 3584 ], "size": 14336, "type": 14 }, { "name": "blk.1.attn_v.bias", "offset": 2120970752, "shape": [ 512 ], "size": 10536960, "type": 0 }, { "name": "blk.1.attn_v.weight", "offset": 2120972800, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.1.attn_norm.weight", "offset": 2122478080, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.1.ffn_down_exps.weight", "offset": 2122492416, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.1.ffn_gate_exps.weight", "offset": 2604182016, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.1.ffn_up_exps.weight", "offset": 3085871616, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.1.ffn_down_shexp.weight", "offset": 3567561216, "shape": [ 20480, 3584 ], "size": 481689600, "type": 14 }, { "name": "blk.1.ffn_gate_shexp.weight", "offset": 3627772416, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.1.ffn_up_shexp.weight", "offset": 3687983616, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.1.ffn_gate_inp_shexp.weight", "offset": 3748194816, "shape": [ 3584 ], "size": 60211200, "type": 0 }, { "name": "blk.1.ffn_norm.weight", "offset": 3748209152, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.2.ffn_gate_inp.weight", "offset": 3748223488, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.2.attn_k.bias", "offset": 3749140992, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.2.attn_k.weight", "offset": 3749143040, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.2.attn_output.weight", "offset": 3750648320, "shape": [ 3584, 3584 ], "size": 1505280, "type": 14 }, { "name": "blk.2.attn_q.bias", "offset": 3761185280, "shape": [ 3584 ], "size": 10536960, "type": 0 }, { "name": "blk.2.attn_q.weight", "offset": 3761199616, "shape": [ 3584, 3584 ], "size": 14336, "type": 14 }, { "name": "blk.2.attn_v.bias", "offset": 3771736576, "shape": [ 512 ], "size": 10536960, "type": 0 }, { "name": "blk.2.attn_v.weight", "offset": 3771738624, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.2.attn_norm.weight", "offset": 3773243904, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.2.ffn_down_exps.weight", "offset": 3773258240, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.2.ffn_gate_exps.weight", "offset": 4254947840, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.2.ffn_up_exps.weight", "offset": 4736637440, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.2.ffn_down_shexp.weight", "offset": 5218327040, "shape": [ 20480, 3584 ], "size": 481689600, "type": 14 }, { "name": "blk.2.ffn_gate_shexp.weight", "offset": 5278538240, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.2.ffn_up_shexp.weight", "offset": 5338749440, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.2.ffn_gate_inp_shexp.weight", "offset": 5398960640, "shape": [ 3584 ], "size": 60211200, "type": 0 }, { "name": "blk.2.ffn_norm.weight", "offset": 5398974976, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.3.ffn_gate_inp.weight", "offset": 5398989312, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.3.attn_k.bias", "offset": 5399906816, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.3.attn_k.weight", "offset": 5399908864, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.3.attn_output.weight", "offset": 5401414144, "shape": [ 3584, 3584 ], "size": 1505280, "type": 14 }, { "name": "blk.3.attn_q.bias", "offset": 5411951104, "shape": [ 3584 ], "size": 10536960, "type": 0 }, { "name": "blk.3.attn_q.weight", "offset": 5411965440, "shape": [ 3584, 3584 ], "size": 14336, "type": 14 }, { "name": "blk.3.attn_v.bias", "offset": 5422502400, "shape": [ 512 ], "size": 10536960, "type": 0 }, { "name": "blk.3.attn_v.weight", "offset": 5422504448, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.3.attn_norm.weight", "offset": 5424009728, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.3.ffn_down_exps.weight", "offset": 5424024064, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.3.ffn_gate_exps.weight", "offset": 5905713664, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.3.ffn_up_exps.weight", "offset": 6387403264, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.3.ffn_down_shexp.weight", "offset": 6869092864, "shape": [ 20480, 3584 ], "size": 481689600, "type": 14 }, { "name": "blk.3.ffn_gate_shexp.weight", "offset": 6929304064, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.3.ffn_up_shexp.weight", "offset": 6989515264, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.3.ffn_gate_inp_shexp.weight", "offset": 7049726464, "shape": [ 3584 ], "size": 60211200, "type": 0 }, { "name": "blk.3.ffn_norm.weight", "offset": 7049740800, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.4.ffn_gate_inp.weight", "offset": 7049755136, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.4.attn_k.bias", "offset": 7050672640, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.4.attn_k.weight", "offset": 7050674688, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.4.attn_output.weight", "offset": 7052179968, "shape": [ 3584, 3584 ], "size": 1505280, "type": 14 }, { "name": "blk.4.attn_q.bias", "offset": 7062716928, "shape": [ 3584 ], "size": 10536960, "type": 0 }, { "name": "blk.4.attn_q.weight", "offset": 7062731264, "shape": [ 3584, 3584 ], "size": 14336, "type": 14 }, { "name": "blk.4.attn_v.bias", "offset": 7073268224, "shape": [ 512 ], "size": 10536960, "type": 0 }, { "name": "blk.4.attn_v.weight", "offset": 7073270272, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.4.attn_norm.weight", "offset": 7074775552, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.4.ffn_down_exps.weight", "offset": 7074789888, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.4.ffn_gate_exps.weight", "offset": 7556479488, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.4.ffn_up_exps.weight", "offset": 8038169088, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.4.ffn_down_shexp.weight", "offset": 8519858688, "shape": [ 20480, 3584 ], "size": 481689600, "type": 14 }, { "name": "blk.4.ffn_gate_shexp.weight", "offset": 8580069888, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.4.ffn_up_shexp.weight", "offset": 8640281088, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.4.ffn_gate_inp_shexp.weight", "offset": 8700492288, "shape": [ 3584 ], "size": 60211200, "type": 0 }, { "name": "blk.4.ffn_norm.weight", "offset": 8700506624, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.5.ffn_gate_inp.weight", "offset": 8700520960, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.5.attn_k.bias", "offset": 8701438464, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.5.attn_k.weight", "offset": 8701440512, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.5.attn_output.weight", "offset": 8702945792, "shape": [ 3584, 3584 ], "size": 1505280, "type": 14 }, { "name": "blk.5.attn_q.bias", "offset": 8713482752, "shape": [ 3584 ], "size": 10536960, "type": 0 }, { "name": "blk.5.attn_q.weight", "offset": 8713497088, "shape": [ 3584, 3584 ], "size": 14336, "type": 14 }, { "name": "blk.5.attn_v.bias", "offset": 8724034048, "shape": [ 512 ], "size": 10536960, "type": 0 }, { "name": "blk.5.attn_v.weight", "offset": 8724036096, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.5.attn_norm.weight", "offset": 8725541376, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.5.ffn_down_exps.weight", "offset": 8725555712, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.5.ffn_gate_exps.weight", "offset": 9207245312, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.5.ffn_up_exps.weight", "offset": 9688934912, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.5.ffn_down_shexp.weight", "offset": 10170624512, "shape": [ 20480, 3584 ], "size": 481689600, "type": 14 }, { "name": "blk.5.ffn_gate_shexp.weight", "offset": 10230835712, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.5.ffn_up_shexp.weight", "offset": 10291046912, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.5.ffn_gate_inp_shexp.weight", "offset": 10351258112, "shape": [ 3584 ], "size": 60211200, "type": 0 }, { "name": "blk.5.ffn_norm.weight", "offset": 10351272448, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.6.ffn_gate_inp.weight", "offset": 10351286784, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.6.attn_k.bias", "offset": 10352204288, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.6.attn_k.weight", "offset": 10352206336, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.6.attn_output.weight", "offset": 10353711616, "shape": [ 3584, 3584 ], "size": 1505280, "type": 14 }, { "name": "blk.6.attn_q.bias", "offset": 10364248576, "shape": [ 3584 ], "size": 10536960, "type": 0 }, { "name": "blk.6.attn_q.weight", "offset": 10364262912, "shape": [ 3584, 3584 ], "size": 14336, "type": 14 }, { "name": "blk.6.attn_v.bias", "offset": 10374799872, "shape": [ 512 ], "size": 10536960, "type": 0 }, { "name": "blk.6.attn_v.weight", "offset": 10374801920, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.6.attn_norm.weight", "offset": 10376307200, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.6.ffn_down_exps.weight", "offset": 10376321536, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.6.ffn_gate_exps.weight", "offset": 10858011136, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.6.ffn_up_exps.weight", "offset": 11339700736, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.6.ffn_down_shexp.weight", "offset": 11821390336, "shape": [ 20480, 3584 ], "size": 481689600, "type": 14 }, { "name": "blk.6.ffn_gate_shexp.weight", "offset": 11881601536, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.6.ffn_up_shexp.weight", "offset": 11941812736, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.6.ffn_gate_inp_shexp.weight", "offset": 12002023936, "shape": [ 3584 ], "size": 60211200, "type": 0 }, { "name": "blk.6.ffn_norm.weight", "offset": 12002038272, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.7.ffn_gate_inp.weight", "offset": 12002052608, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.7.attn_k.bias", "offset": 12002970112, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.7.attn_k.weight", "offset": 12002972160, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.7.attn_output.weight", "offset": 12004477440, "shape": [ 3584, 3584 ], "size": 1505280, "type": 14 }, { "name": "blk.7.attn_q.bias", "offset": 12015014400, "shape": [ 3584 ], "size": 10536960, "type": 0 }, { "name": "blk.7.attn_q.weight", "offset": 12015028736, "shape": [ 3584, 3584 ], "size": 14336, "type": 14 }, { "name": "blk.7.attn_v.bias", "offset": 12025565696, "shape": [ 512 ], "size": 10536960, "type": 0 }, { "name": "blk.7.attn_v.weight", "offset": 12025567744, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.7.attn_norm.weight", "offset": 12027073024, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.7.ffn_down_exps.weight", "offset": 12027087360, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.7.ffn_gate_exps.weight", "offset": 12508776960, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.7.ffn_up_exps.weight", "offset": 12990466560, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.7.ffn_down_shexp.weight", "offset": 13472156160, "shape": [ 20480, 3584 ], "size": 481689600, "type": 14 }, { "name": "blk.7.ffn_gate_shexp.weight", "offset": 13532367360, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.7.ffn_up_shexp.weight", "offset": 13592578560, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.7.ffn_gate_inp_shexp.weight", "offset": 13652789760, "shape": [ 3584 ], "size": 60211200, "type": 0 }, { "name": "blk.7.ffn_norm.weight", "offset": 13652804096, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.8.ffn_gate_inp.weight", "offset": 13652818432, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.8.attn_k.bias", "offset": 13653735936, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.8.attn_k.weight", "offset": 13653737984, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.8.attn_output.weight", "offset": 13655243264, "shape": [ 3584, 3584 ], "size": 1505280, "type": 14 }, { "name": "blk.8.attn_q.bias", "offset": 13665780224, "shape": [ 3584 ], "size": 10536960, "type": 0 }, { "name": "blk.8.attn_q.weight", "offset": 13665794560, "shape": [ 3584, 3584 ], "size": 14336, "type": 14 }, { "name": "blk.8.attn_v.bias", "offset": 13676331520, "shape": [ 512 ], "size": 10536960, "type": 0 }, { "name": "blk.8.attn_v.weight", "offset": 13676333568, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.8.attn_norm.weight", "offset": 13677838848, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.8.ffn_down_exps.weight", "offset": 13677853184, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.8.ffn_gate_exps.weight", "offset": 14159542784, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.8.ffn_up_exps.weight", "offset": 14641232384, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.8.ffn_down_shexp.weight", "offset": 15122921984, "shape": [ 20480, 3584 ], "size": 481689600, "type": 14 }, { "name": "blk.8.ffn_gate_shexp.weight", "offset": 15183133184, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.8.ffn_up_shexp.weight", "offset": 15243344384, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.8.ffn_gate_inp_shexp.weight", "offset": 15303555584, "shape": [ 3584 ], "size": 60211200, "type": 0 }, { "name": "blk.8.ffn_norm.weight", "offset": 15303569920, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.9.ffn_gate_inp.weight", "offset": 15303584256, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.9.attn_k.bias", "offset": 15304501760, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.9.attn_k.weight", "offset": 15304503808, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.9.attn_output.weight", "offset": 15306009088, "shape": [ 3584, 3584 ], "size": 1505280, "type": 14 }, { "name": "blk.9.attn_q.bias", "offset": 15316546048, "shape": [ 3584 ], "size": 10536960, "type": 0 }, { "name": "blk.9.attn_q.weight", "offset": 15316560384, "shape": [ 3584, 3584 ], "size": 14336, "type": 14 }, { "name": "blk.9.attn_v.bias", "offset": 15327097344, "shape": [ 512 ], "size": 10536960, "type": 0 }, { "name": "blk.9.attn_v.weight", "offset": 15327099392, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.10.ffn_gate_inp.weight", "offset": 15328604672, "shape": [ 3584, 64 ], "size": 1505280, "type": 0 }, { "name": "blk.10.attn_k.bias", "offset": 15329522176, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.10.attn_k.weight", "offset": 15329524224, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.10.attn_output.weight", "offset": 15331029504, "shape": [ 3584, 3584 ], "size": 1505280, "type": 14 }, { "name": "blk.10.attn_q.bias", "offset": 15341566464, "shape": [ 3584 ], "size": 10536960, "type": 0 }, { "name": "blk.10.attn_q.weight", "offset": 15341580800, "shape": [ 3584, 3584 ], "size": 14336, "type": 14 }, { "name": "blk.10.attn_v.bias", "offset": 15352117760, "shape": [ 512 ], "size": 10536960, "type": 0 }, { "name": "blk.10.attn_v.weight", "offset": 15352119808, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.9.attn_norm.weight", "offset": 15353625088, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.9.ffn_down_exps.weight", "offset": 15353639424, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.9.ffn_gate_exps.weight", "offset": 15835329024, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.9.ffn_up_exps.weight", "offset": 16317018624, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.9.ffn_down_shexp.weight", "offset": 16798708224, "shape": [ 20480, 3584 ], "size": 481689600, "type": 14 }, { "name": "blk.9.ffn_gate_shexp.weight", "offset": 16858919424, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.9.ffn_up_shexp.weight", "offset": 16919130624, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.9.ffn_gate_inp_shexp.weight", "offset": 16979341824, "shape": [ 3584 ], "size": 60211200, "type": 0 }, { "name": "blk.9.ffn_norm.weight", "offset": 16979356160, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.10.attn_norm.weight", "offset": 16979370496, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.10.ffn_down_exps.weight", "offset": 16979384832, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.10.ffn_gate_exps.weight", "offset": 17461074432, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.10.ffn_up_exps.weight", "offset": 17942764032, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.10.ffn_down_shexp.weight", "offset": 18424453632, "shape": [ 20480, 3584 ], "size": 481689600, "type": 14 }, { "name": "blk.10.ffn_gate_shexp.weight", "offset": 18484664832, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.10.ffn_up_shexp.weight", "offset": 18544876032, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.10.ffn_gate_inp_shexp.weight", "offset": 18605087232, "shape": [ 3584 ], "size": 60211200, "type": 0 }, { "name": "blk.10.ffn_norm.weight", "offset": 18605101568, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.11.ffn_gate_inp.weight", "offset": 18605115904, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.11.attn_k.bias", "offset": 18606033408, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.11.attn_k.weight", "offset": 18606035456, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.11.attn_output.weight", "offset": 18607540736, "shape": [ 3584, 3584 ], "size": 1505280, "type": 14 }, { "name": "blk.11.attn_q.bias", "offset": 18618077696, "shape": [ 3584 ], "size": 10536960, "type": 0 }, { "name": "blk.11.attn_q.weight", "offset": 18618092032, "shape": [ 3584, 3584 ], "size": 14336, "type": 14 }, { "name": "blk.11.attn_v.bias", "offset": 18628628992, "shape": [ 512 ], "size": 10536960, "type": 0 }, { "name": "blk.11.attn_v.weight", "offset": 18628631040, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.11.attn_norm.weight", "offset": 18630136320, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.11.ffn_down_exps.weight", "offset": 18630150656, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.11.ffn_gate_exps.weight", "offset": 19111840256, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.11.ffn_up_exps.weight", "offset": 19593529856, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.11.ffn_down_shexp.weight", "offset": 20075219456, "shape": [ 20480, 3584 ], "size": 481689600, "type": 14 }, { "name": "blk.11.ffn_gate_shexp.weight", "offset": 20135430656, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.11.ffn_up_shexp.weight", "offset": 20195641856, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.11.ffn_gate_inp_shexp.weight", "offset": 20255853056, "shape": [ 3584 ], "size": 60211200, "type": 0 }, { "name": "blk.11.ffn_norm.weight", "offset": 20255867392, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.12.ffn_gate_inp.weight", "offset": 20255881728, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.12.attn_k.bias", "offset": 20256799232, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.12.attn_k.weight", "offset": 20256801280, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.12.attn_output.weight", "offset": 20258306560, "shape": [ 3584, 3584 ], "size": 1505280, "type": 14 }, { "name": "blk.12.attn_q.bias", "offset": 20268843520, "shape": [ 3584 ], "size": 10536960, "type": 0 }, { "name": "blk.12.attn_q.weight", "offset": 20268857856, "shape": [ 3584, 3584 ], "size": 14336, "type": 14 }, { "name": "blk.12.attn_v.bias", "offset": 20279394816, "shape": [ 512 ], "size": 10536960, "type": 0 }, { "name": "blk.12.attn_v.weight", "offset": 20279396864, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.12.attn_norm.weight", "offset": 20280902144, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.12.ffn_down_exps.weight", "offset": 20280916480, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.12.ffn_gate_exps.weight", "offset": 20762606080, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.12.ffn_up_exps.weight", "offset": 21244295680, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.12.ffn_down_shexp.weight", "offset": 21725985280, "shape": [ 20480, 3584 ], "size": 481689600, "type": 14 }, { "name": "blk.12.ffn_gate_shexp.weight", "offset": 21786196480, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.12.ffn_up_shexp.weight", "offset": 21846407680, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.12.ffn_gate_inp_shexp.weight", "offset": 21906618880, "shape": [ 3584 ], "size": 60211200, "type": 0 }, { "name": "blk.12.ffn_norm.weight", "offset": 21906633216, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.13.ffn_gate_inp.weight", "offset": 21906647552, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.13.attn_k.bias", "offset": 21907565056, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.13.attn_k.weight", "offset": 21907567104, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.13.attn_output.weight", "offset": 21909072384, "shape": [ 3584, 3584 ], "size": 1505280, "type": 14 }, { "name": "blk.13.attn_q.bias", "offset": 21919609344, "shape": [ 3584 ], "size": 10536960, "type": 0 }, { "name": "_gate_inp.weight\u0002\u0000\u0000\u0000", "offset": 21919623680, "shape": [ 3584, 3584 ], "size": 14336, "type": 14 }, { "name": "blk.13.attn_v.bias", "offset": 21930160640, "shape": [ 512 ], "size": 10536960, "type": 0 }, { "name": "blk.13.attn_v.weight", "offset": 21930162688, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.13.attn_norm.weight", "offset": 21931667968, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.13.ffn_down_exps.weight", "offset": 21931682304, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.13.ffn_gate_exps.weight", "offset": 22413371904, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.13.ffn_up_exps.weight", "offset": 22895061504, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.13.ffn_down_shexp.weight", "offset": 23376751104, "shape": [ 20480, 3584 ], "size": 481689600, "type": 14 }, { "name": "blk.13.ffn_gate_shexp.weight", "offset": 23436962304, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.13.ffn_up_shexp.weight", "offset": 23497173504, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.13.ffn_gate_inp_shexp.weight", "offset": 23557384704, "shape": [ 3584 ], "size": 60211200, "type": 0 }, { "name": "blk.13.ffn_norm.weight", "offset": 23557399040, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.14.ffn_gate_inp.weight", "offset": 23557413376, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.14.attn_k.bias", "offset": 23558330880, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.14.attn_k.weight", "offset": 23558332928, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.14.attn_output.weight", "offset": 23559838208, "shape": [ 3584, 3584 ], "size": 1505280, "type": 14 }, { "name": "blk.14.attn_q.bias", "offset": 23570375168, "shape": [ 3584 ], "size": 10536960, "type": 0 }, { "name": "blk.14.attn_q.weight", "offset": 23570389504, "shape": [ 3584, 3584 ], "size": 14336, "type": 14 }, { "name": "blk.14.attn_v.bias", "offset": 23580926464, "shape": [ 512 ], "size": 10536960, "type": 0 }, { "name": "blk.14.attn_v.weight", "offset": 23580928512, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.14.attn_norm.weight", "offset": 23582433792, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.14.ffn_down_exps.weight", "offset": 23582448128, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.14.ffn_gate_exps.weight", "offset": 24064137728, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.14.ffn_up_exps.weight", "offset": 24545827328, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.14.ffn_down_shexp.weight", "offset": 25027516928, "shape": [ 20480, 3584 ], "size": 481689600, "type": 14 }, { "name": "blk.14.ffn_gate_shexp.weight", "offset": 25087728128, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.14.ffn_up_shexp.weight", "offset": 25147939328, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.14.ffn_gate_inp_shexp.weight", "offset": 25208150528, "shape": [ 3584 ], "size": 60211200, "type": 0 }, { "name": "blk.14.ffn_norm.weight", "offset": 25208164864, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.15.ffn_gate_inp.weight", "offset": 25208179200, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.15.attn_k.bias", "offset": 25209096704, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.15.attn_k.weight", "offset": 25209098752, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.15.attn_output.weight", "offset": 25210604032, "shape": [ 3584, 3584 ], "size": 1505280, "type": 14 }, { "name": "blk.15.attn_q.bias", "offset": 25221140992, "shape": [ 3584 ], "size": 10536960, "type": 0 }, { "name": "blk.15.attn_q.weight", "offset": 25221155328, "shape": [ 3584, 3584 ], "size": 14336, "type": 14 }, { "name": "blk.15.attn_v.bias", "offset": 25231692288, "shape": [ 512 ], "size": 10536960, "type": 0 }, { "name": "blk.15.attn_v.weight", "offset": 25231694336, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.15.attn_norm.weight", "offset": 25233199616, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.15.ffn_down_exps.weight", "offset": 25233213952, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.15.ffn_gate_exps.weight", "offset": 25714903552, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.15.ffn_up_exps.weight", "offset": 26196593152, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.15.ffn_down_shexp.weight", "offset": 26678282752, "shape": [ 20480, 3584 ], "size": 481689600, "type": 14 }, { "name": "blk.15.ffn_gate_shexp.weight", "offset": 26738493952, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.15.ffn_up_shexp.weight", "offset": 26798705152, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.15.ffn_gate_inp_shexp.weight", "offset": 26858916352, "shape": [ 3584 ], "size": 60211200, "type": 0 }, { "name": "blk.15.ffn_norm.weight", "offset": 26858930688, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.16.ffn_gate_inp.weight", "offset": 26858945024, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.16.attn_k.bias", "offset": 26859862528, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.16.attn_k.weight", "offset": 26859864576, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.16.attn_output.weight", "offset": 26861369856, "shape": [ 3584, 3584 ], "size": 1505280, "type": 14 }, { "name": "blk.16.attn_q.bias", "offset": 26871906816, "shape": [ 3584 ], "size": 10536960, "type": 0 }, { "name": "blk.16.attn_q.weight", "offset": 26871921152, "shape": [ 3584, 3584 ], "size": 14336, "type": 14 }, { "name": "blk.16.attn_v.bias", "offset": 26882458112, "shape": [ 512 ], "size": 10536960, "type": 0 }, { "name": "blk.16.attn_v.weight", "offset": 26882460160, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.16.attn_norm.weight", "offset": 26883965440, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.16.ffn_down_exps.weight", "offset": 26883979776, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.16.ffn_gate_exps.weight", "offset": 27365669376, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.16.ffn_up_exps.weight", "offset": 27847358976, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.16.ffn_down_shexp.weight", "offset": 28329048576, "shape": [ 20480, 3584 ], "size": 481689600, "type": 14 }, { "name": "blk.16.ffn_gate_shexp.weight", "offset": 28389259776, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.16.ffn_up_shexp.weight", "offset": 28449470976, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.16.ffn_gate_inp_shexp.weight", "offset": 28509682176, "shape": [ 3584 ], "size": 60211200, "type": 0 }, { "name": "blk.16.ffn_norm.weight", "offset": 28509696512, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.17.ffn_gate_inp.weight", "offset": 28509710848, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.17.attn_k.bias", "offset": 28510628352, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.17.attn_k.weight", "offset": 28510630400, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.17.attn_output.weight", "offset": 28512135680, "shape": [ 3584, 3584 ], "size": 1505280, "type": 14 }, { "name": "blk.17.attn_q.bias", "offset": 28522672640, "shape": [ 3584 ], "size": 10536960, "type": 0 }, { "name": "blk.17.attn_q.weight", "offset": 28522686976, "shape": [ 3584, 3584 ], "size": 14336, "type": 14 }, { "name": "blk.17.attn_v.bias", "offset": 28533223936, "shape": [ 512 ], "size": 10536960, "type": 0 }, { "name": "blk.17.attn_v.weight", "offset": 28533225984, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.17.attn_norm.weight", "offset": 28534731264, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.17.ffn_down_exps.weight", "offset": 28534745600, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.17.ffn_gate_exps.weight", "offset": 29016435200, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.17.ffn_up_exps.weight", "offset": 29498124800, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.17.ffn_down_shexp.weight", "offset": 29979814400, "shape": [ 20480, 3584 ], "size": 481689600, "type": 14 }, { "name": "blk.17.ffn_gate_shexp.weight", "offset": 30040025600, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.17.ffn_up_shexp.weight", "offset": 30100236800, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.17.ffn_gate_inp_shexp.weight", "offset": 30160448000, "shape": [ 3584 ], "size": 60211200, "type": 0 }, { "name": "blk.17.ffn_norm.weight", "offset": 30160462336, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.18.ffn_gate_inp.weight", "offset": 30160476672, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.18.attn_k.bias", "offset": 30161394176, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.18.attn_k.weight", "offset": 30161396224, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.18.attn_output.weight", "offset": 30162901504, "shape": [ 3584, 3584 ], "size": 1505280, "type": 14 }, { "name": "blk.18.attn_q.bias", "offset": 30173438464, "shape": [ 3584 ], "size": 10536960, "type": 0 }, { "name": "blk.18.attn_q.weight", "offset": 30173452800, "shape": [ 3584, 3584 ], "size": 14336, "type": 14 }, { "name": "blk.18.attn_v.bias", "offset": 30183989760, "shape": [ 512 ], "size": 10536960, "type": 0 }, { "name": "blk.18.attn_v.weight", "offset": 30183991808, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.18.attn_norm.weight", "offset": 30185497088, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.18.ffn_down_exps.weight", "offset": 30185511424, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.18.ffn_gate_exps.weight", "offset": 30667201024, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.18.ffn_up_exps.weight", "offset": 31148890624, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.18.ffn_down_shexp.weight", "offset": 31630580224, "shape": [ 20480, 3584 ], "size": 481689600, "type": 14 }, { "name": "blk.18.ffn_gate_shexp.weight", "offset": 31690791424, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.18.ffn_up_shexp.weight", "offset": 31751002624, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.18.ffn_gate_inp_shexp.weight", "offset": 31811213824, "shape": [ 3584 ], "size": 60211200, "type": 0 }, { "name": "blk.18.ffn_norm.weight", "offset": 31811228160, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.19.ffn_gate_inp.weight", "offset": 31811242496, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.19.attn_k.bias", "offset": 31812160000, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.19.attn_k.weight", "offset": 31812162048, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.19.attn_output.weight", "offset": 31813667328, "shape": [ 3584, 3584 ], "size": 1505280, "type": 14 }, { "name": "blk.19.attn_q.bias", "offset": 31824204288, "shape": [ 3584 ], "size": 10536960, "type": 0 }, { "name": "blk.19.attn_q.weight", "offset": 31824218624, "shape": [ 3584, 3584 ], "size": 14336, "type": 14 }, { "name": "blk.19.attn_v.bias", "offset": 31834755584, "shape": [ 512 ], "size": 10536960, "type": 0 }, { "name": "blk.19.attn_v.weight", "offset": 31834757632, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.19.attn_norm.weight", "offset": 31836262912, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.19.ffn_down_exps.weight", "offset": 31836277248, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.19.ffn_gate_exps.weight", "offset": 32317966848, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.19.ffn_up_exps.weight", "offset": 32799656448, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.19.ffn_down_shexp.weight", "offset": 33281346048, "shape": [ 20480, 3584 ], "size": 481689600, "type": 14 }, { "name": "blk.19.ffn_gate_shexp.weight", "offset": 33341557248, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.19.ffn_up_shexp.weight", "offset": 33401768448, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.19.ffn_gate_inp_shexp.weight", "offset": 33461979648, "shape": [ 3584 ], "size": 60211200, "type": 0 }, { "name": "blk.19.ffn_norm.weight", "offset": 33461993984, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.20.ffn_gate_inp.weight", "offset": 33462008320, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.20.attn_k.bias", "offset": 33462925824, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.20.attn_k.weight", "offset": 33462927872, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.20.attn_output.weight", "offset": 33464433152, "shape": [ 3584, 3584 ], "size": 1505280, "type": 14 }, { "name": "blk.20.attn_q.bias", "offset": 33474970112, "shape": [ 3584 ], "size": 10536960, "type": 0 }, { "name": "blk.20.attn_q.weight", "offset": 33474984448, "shape": [ 3584, 3584 ], "size": 14336, "type": 14 }, { "name": "blk.20.attn_v.bias", "offset": 33485521408, "shape": [ 512 ], "size": 10536960, "type": 0 }, { "name": "blk.20.attn_v.weight", "offset": 33485523456, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.20.attn_norm.weight", "offset": 33487028736, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.20.ffn_down_exps.weight", "offset": 33487043072, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.20.ffn_gate_exps.weight", "offset": 33968732672, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.20.ffn_up_exps.weight", "offset": 34450422272, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.20.ffn_down_shexp.weight", "offset": 34932111872, "shape": [ 20480, 3584 ], "size": 481689600, "type": 14 }, { "name": "blk.20.ffn_gate_shexp.weight", "offset": 34992323072, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.20.ffn_up_shexp.weight", "offset": 35052534272, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.20.ffn_gate_inp_shexp.weight", "offset": 35112745472, "shape": [ 3584 ], "size": 60211200, "type": 0 }, { "name": "blk.20.ffn_norm.weight", "offset": 35112759808, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "CE\u0019\ufffdMXeM\ufffd\u0001\ufffd\u0019\ufffd\u001f\ufffd\u0003\ufffdxw\ufffd\ufffdue\ufffd\ufffd\u0014", "offset": 35112774144, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.21.attn_k.bias", "offset": 35113691648, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.21.attn_k.weight", "offset": 35113693696, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.21.attn_output.weight", "offset": 35115198976, "shape": [ 3584, 3584 ], "size": 1505280, "type": 14 }, { "name": "blk.21.attn_q.bias", "offset": 35125735936, "shape": [ 3584 ], "size": 10536960, "type": 0 }, { "name": "blk.21.attn_q.weight", "offset": 35125750272, "shape": [ 3584, 3584 ], "size": 14336, "type": 14 }, { "name": "blk.21.attn_v.bias", "offset": 35136287232, "shape": [ 512 ], "size": 10536960, "type": 0 }, { "name": "blk.21.attn_v.weight", "offset": 35136289280, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.21.attn_norm.weight", "offset": 35137794560, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.21.ffn_down_exps.weight", "offset": 35137808896, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.21.ffn_gate_exps.weight", "offset": 35619498496, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.21.ffn_up_exps.weight", "offset": 36101188096, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.21.ffn_down_shexp.weight", "offset": 36582877696, "shape": [ 20480, 3584 ], "size": 481689600, "type": 14 }, { "name": "blk.21.ffn_gate_shexp.weight", "offset": 36643088896, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.21.ffn_up_shexp.weight", "offset": 36703300096, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.21.ffn_gate_inp_shexp.weight", "offset": 36763511296, "shape": [ 3584 ], "size": 60211200, "type": 0 }, { "name": "blk.21.ffn_norm.weight", "offset": 36763525632, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.22.ffn_gate_inp.weight", "offset": 36763539968, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.22.attn_k.bias", "offset": 36764457472, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.22.attn_k.weight", "offset": 36764459520, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.22.attn_output.weight", "offset": 36765964800, "shape": [ 3584, 3584 ], "size": 1505280, "type": 14 }, { "name": "blk.22.attn_q.bias", "offset": 36776501760, "shape": [ 3584 ], "size": 10536960, "type": 0 }, { "name": "blk.22.attn_q.weight", "offset": 36776516096, "shape": [ 3584, 3584 ], "size": 14336, "type": 14 }, { "name": "blk.22.attn_v.bias", "offset": 36787053056, "shape": [ 512 ], "size": 10536960, "type": 0 }, { "name": "blk.22.attn_v.weight", "offset": 36787055104, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.22.attn_norm.weight", "offset": 36788560384, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.22.ffn_down_exps.weight", "offset": 36788574720, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.22.ffn_gate_exps.weight", "offset": 37270264320, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.22.ffn_up_exps.weight", "offset": 37751953920, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.22.ffn_down_shexp.weight", "offset": 38233643520, "shape": [ 20480, 3584 ], "size": 481689600, "type": 14 }, { "name": "blk.22.ffn_gate_shexp.weight", "offset": 38293854720, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.22.ffn_up_shexp.weight", "offset": 38354065920, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.22.ffn_gate_inp_shexp.weight", "offset": 38414277120, "shape": [ 3584 ], "size": 60211200, "type": 0 }, { "name": "blk.22.ffn_norm.weight", "offset": 38414291456, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.23.ffn_gate_inp.weight", "offset": 38414305792, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.23.attn_k.bias", "offset": 38415223296, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.23.attn_k.weight", "offset": 38415225344, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.23.attn_output.weight", "offset": 38416730624, "shape": [ 3584, 3584 ], "size": 1505280, "type": 14 }, { "name": "blk.23.attn_q.bias", "offset": 38427267584, "shape": [ 3584 ], "size": 10536960, "type": 0 }, { "name": "blk.23.attn_q.weight", "offset": 38427281920, "shape": [ 3584, 3584 ], "size": 14336, "type": 14 }, { "name": "blk.23.attn_v.bias", "offset": 38437818880, "shape": [ 512 ], "size": 10536960, "type": 0 }, { "name": "blk.23.attn_v.weight", "offset": 38437820928, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.23.attn_norm.weight", "offset": 38439326208, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.23.ffn_down_exps.weight", "offset": 38439340544, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.23.ffn_gate_exps.weight", "offset": 38921030144, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.23.ffn_up_exps.weight", "offset": 39402719744, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.23.ffn_down_shexp.weight", "offset": 39884409344, "shape": [ 20480, 3584 ], "size": 481689600, "type": 14 }, { "name": "blk.23.ffn_gate_shexp.weight", "offset": 39944620544, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.23.ffn_up_shexp.weight", "offset": 40004831744, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.23.ffn_gate_inp_shexp.weight", "offset": 40065042944, "shape": [ 3584 ], "size": 60211200, "type": 0 }, { "name": "blk.23.ffn_norm.weight", "offset": 40065057280, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.24.ffn_gate_inp.weight", "offset": 40065071616, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.24.attn_k.bias", "offset": 40065989120, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.24.attn_k.weight", "offset": 40065991168, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.24.attn_output.weight", "offset": 40067496448, "shape": [ 3584, 3584 ], "size": 1505280, "type": 14 }, { "name": "blk.24.attn_q.bias", "offset": 40078033408, "shape": [ 3584 ], "size": 10536960, "type": 0 }, { "name": "blk.24.attn_q.weight", "offset": 40078047744, "shape": [ 3584, 3584 ], "size": 14336, "type": 14 }, { "name": "blk.24.attn_v.bias", "offset": 40088584704, "shape": [ 512 ], "size": 10536960, "type": 0 }, { "name": "blk.24.attn_v.weight", "offset": 40088586752, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.24.attn_norm.weight", "offset": 40090092032, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.24.ffn_down_exps.weight", "offset": 40090106368, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.24.ffn_gate_exps.weight", "offset": 40571795968, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.24.ffn_up_exps.weight", "offset": 41053485568, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.24.ffn_down_shexp.weight", "offset": 41535175168, "shape": [ 20480, 3584 ], "size": 481689600, "type": 14 }, { "name": "blk.24.ffn_gate_shexp.weight", "offset": 41595386368, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.24.ffn_up_shexp.weight", "offset": 41655597568, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.24.ffn_gate_inp_shexp.weight", "offset": 41715808768, "shape": [ 3584 ], "size": 60211200, "type": 0 }, { "name": "blk.24.ffn_norm.weight", "offset": 41715823104, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.25.ffn_gate_inp.weight", "offset": 41715837440, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.25.attn_k.bias", "offset": 41716754944, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.25.attn_k.weight", "offset": 41716756992, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.25.attn_output.weight", "offset": 41718262272, "shape": [ 3584, 3584 ], "size": 1505280, "type": 14 }, { "name": "blk.25.attn_q.bias", "offset": 41728799232, "shape": [ 3584 ], "size": 10536960, "type": 0 }, { "name": "blk.25.attn_q.weight", "offset": 41728813568, "shape": [ 3584, 3584 ], "size": 14336, "type": 14 }, { "name": "blk.25.attn_v.bias", "offset": 41739350528, "shape": [ 512 ], "size": 10536960, "type": 0 }, { "name": "blk.25.attn_v.weight", "offset": 41739352576, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.25.attn_norm.weight", "offset": 41740857856, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.25.ffn_down_exps.weight", "offset": 41740872192, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.25.ffn_gate_exps.weight", "offset": 42222561792, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.25.ffn_up_exps.weight", "offset": 42704251392, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.25.ffn_down_shexp.weight", "offset": 43185940992, "shape": [ 20480, 3584 ], "size": 481689600, "type": 14 }, { "name": "blk.25.ffn_gate_shexp.weight", "offset": 43246152192, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.25.ffn_up_shexp.weight", "offset": 43306363392, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.25.ffn_gate_inp_shexp.weight", "offset": 43366574592, "shape": [ 3584 ], "size": 60211200, "type": 0 }, { "name": "blk.25.ffn_norm.weight", "offset": 43366588928, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.26.ffn_gate_inp.weight", "offset": 43366603264, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.26.attn_k.bias", "offset": 43367520768, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.26.attn_k.weight", "offset": 43367522816, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.26.attn_output.weight", "offset": 43369028096, "shape": [ 3584, 3584 ], "size": 1505280, "type": 14 }, { "name": "blk.26.attn_q.bias", "offset": 43379565056, "shape": [ 3584 ], "size": 10536960, "type": 0 }, { "name": "blk.26.attn_q.weight", "offset": 43379579392, "shape": [ 3584, 3584 ], "size": 14336, "type": 14 }, { "name": "blk.26.attn_v.bias", "offset": 43390116352, "shape": [ 512 ], "size": 10536960, "type": 0 }, { "name": "blk.26.attn_v.weight", "offset": 43390118400, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.26.attn_norm.weight", "offset": 43391623680, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.26.ffn_down_exps.weight", "offset": 43391638016, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.26.ffn_gate_exps.weight", "offset": 43873327616, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.26.ffn_up_exps.weight", "offset": 44355017216, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.26.ffn_down_shexp.weight", "offset": 44836706816, "shape": [ 20480, 3584 ], "size": 481689600, "type": 14 }, { "name": "blk.26.ffn_gate_shexp.weight", "offset": 44896918016, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.26.ffn_up_shexp.weight", "offset": 44957129216, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.26.ffn_gate_inp_shexp.weight", "offset": 45017340416, "shape": [ 3584 ], "size": 60211200, "type": 0 }, { "name": "blk.26.ffn_norm.weight", "offset": 45017354752, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.27.ffn_gate_inp.weight", "offset": 45017369088, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.27.attn_k.bias", "offset": 45018286592, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.27.attn_k.weight", "offset": 45018288640, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.27.attn_output.weight", "offset": 45019793920, "shape": [ 3584, 3584 ], "size": 1505280, "type": 14 }, { "name": "blk.27.attn_q.bias", "offset": 45030330880, "shape": [ 3584 ], "size": 10536960, "type": 0 }, { "name": "blk.27.attn_q.weight", "offset": 45030345216, "shape": [ 3584, 3584 ], "size": 14336, "type": 14 }, { "name": "blk.27.attn_v.bias", "offset": 45040882176, "shape": [ 512 ], "size": 10536960, "type": 0 }, { "name": "blk.27.attn_v.weight", "offset": 45040884224, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "output.weight", "offset": 45042389504, "shape": [ 3584, 151936 ], "size": 1505280, "type": 14 }, { "name": "blk.27.attn_norm.weight", "offset": 45489081344, "shape": [ 3584 ], "size": 446691840, "type": 0 }, { "name": "blk.27.ffn_down_exps.weight", "offset": 45489095680, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.27.ffn_gate_exps.weight", "offset": 45970785280, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.27.ffn_up_exps.weight", "offset": 46452474880, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 14 }, { "name": "blk.27.ffn_down_shexp.weight", "offset": 46934164480, "shape": [ 20480, 3584 ], "size": 481689600, "type": 14 }, { "name": "blk.27.ffn_gate_shexp.weight", "offset": 46994375680, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.27.ffn_up_shexp.weight", "offset": 47054586880, "shape": [ 3584, 20480 ], "size": 60211200, "type": 14 }, { "name": "blk.27.ffn_gate_inp_shexp.weight", "offset": 47114798080, "shape": [ 3584 ], "size": 60211200, "type": 0 }, { "name": "blk.27.ffn_norm.weight", "offset": 47114812416, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "output_norm.weight", "offset": 47114826752, "shape": [ 3584 ], "size": 14336, "type": 0 } ], "version": 3 }