Qwen2 MOE 57B

298 Pulls Updated 3 weeks ago

5c9d9bae8e97 · 41GB
{ "metadata": { "general.architecture": "qwen2moe", "general.file_type": 17, "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": "2024-06-07T17:06:12+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": 374370304, "shape": [ 3584, 64 ], "size": 374370304, "type": 0 }, { "name": "blk.0.attn_k.bias", "offset": 375287808, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.0.attn_k.weight", "offset": 375289856, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.0.attn_output.weight", "offset": 376551424, "shape": [ 3584, 3584 ], "size": 1261568, "type": 13 }, { "name": "blk.0.attn_q.bias", "offset": 385382400, "shape": [ 3584 ], "size": 8830976, "type": 0 }, { "name": "blk.0.attn_q.weight", "offset": 385396736, "shape": [ 3584, 3584 ], "size": 14336, "type": 13 }, { "name": "blk.0.attn_v.bias", "offset": 394227712, "shape": [ 512 ], "size": 8830976, "type": 0 }, { "name": "blk.0.attn_v.weight", "offset": 394229760, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.0.attn_norm.weight", "offset": 395735040, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.0.ffn_down_exps.weight", "offset": 395749376, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.0.ffn_gate_exps.weight", "offset": 877438976, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 13 }, { "name": "blk.0.ffn_up_exps.weight", "offset": 1281140736, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.0.ffn_down_shexp.weight", "offset": 1684842496, "shape": [ 20480, 3584 ], "size": 403701760, "type": 14 }, { "name": "blk.0.ffn_gate_shexp.weight", "offset": 1745053696, "shape": [ 3584, 20480 ], "size": 60211200, "type": 13 }, { "name": "blk.0.ffn_up_shexp.weight", "offset": 1795516416, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.0.ffn_gate_inp_shexp.weight", "offset": 1845979136, "shape": [ 3584 ], "size": 50462720, "type": 0 }, { "name": "blk.0.ffn_norm.weight", "offset": 1845993472, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.1.ffn_gate_inp.weight", "offset": 1846007808, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.1.attn_k.bias", "offset": 1846925312, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.1.attn_k.weight", "offset": 1846927360, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.1.attn_output.weight", "offset": 1848188928, "shape": [ 3584, 3584 ], "size": 1261568, "type": 13 }, { "name": "blk.1.attn_q.bias", "offset": 1857019904, "shape": [ 3584 ], "size": 8830976, "type": 0 }, { "name": "blk.1.attn_q.weight", "offset": 1857034240, "shape": [ 3584, 3584 ], "size": 14336, "type": 13 }, { "name": "blk.1.attn_v.bias", "offset": 1865865216, "shape": [ 512 ], "size": 8830976, "type": 0 }, { "name": "blk.1.attn_v.weight", "offset": 1865867264, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.1.attn_norm.weight", "offset": 1867372544, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.1.ffn_down_exps.weight", "offset": 1867386880, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.1.ffn_gate_exps.weight", "offset": 2349076480, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 13 }, { "name": "blk.1.ffn_up_exps.weight", "offset": 2752778240, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.1.ffn_down_shexp.weight", "offset": 3156480000, "shape": [ 20480, 3584 ], "size": 403701760, "type": 14 }, { "name": "blk.1.ffn_gate_shexp.weight", "offset": 3216691200, "shape": [ 3584, 20480 ], "size": 60211200, "type": 13 }, { "name": "blk.1.ffn_up_shexp.weight", "offset": 3267153920, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.1.ffn_gate_inp_shexp.weight", "offset": 3317616640, "shape": [ 3584 ], "size": 50462720, "type": 0 }, { "name": "blk.1.ffn_norm.weight", "offset": 3317630976, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.2.ffn_gate_inp.weight", "offset": 3317645312, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.2.attn_k.bias", "offset": 3318562816, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.2.attn_k.weight", "offset": 3318564864, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.2.attn_output.weight", "offset": 3319826432, "shape": [ 3584, 3584 ], "size": 1261568, "type": 13 }, { "name": "blk.2.attn_q.bias", "offset": 3328657408, "shape": [ 3584 ], "size": 8830976, "type": 0 }, { "name": "blk.2.attn_q.weight", "offset": 3328671744, "shape": [ 3584, 3584 ], "size": 14336, "type": 13 }, { "name": "blk.2.attn_v.bias", "offset": 3337502720, "shape": [ 512 ], "size": 8830976, "type": 0 }, { "name": "blk.2.attn_v.weight", "offset": 3337504768, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.2.attn_norm.weight", "offset": 3339010048, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.2.ffn_down_exps.weight", "offset": 3339024384, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.2.ffn_gate_exps.weight", "offset": 3820713984, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 13 }, { "name": "blk.2.ffn_up_exps.weight", "offset": 4224415744, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.2.ffn_down_shexp.weight", "offset": 4628117504, "shape": [ 20480, 3584 ], "size": 403701760, "type": 14 }, { "name": "blk.2.ffn_gate_shexp.weight", "offset": 4688328704, "shape": [ 3584, 20480 ], "size": 60211200, "type": 13 }, { "name": "blk.2.ffn_up_shexp.weight", "offset": 4738791424, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.2.ffn_gate_inp_shexp.weight", "offset": 4789254144, "shape": [ 3584 ], "size": 50462720, "type": 0 }, { "name": "blk.2.ffn_norm.weight", "offset": 4789268480, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.3.ffn_gate_inp.weight", "offset": 4789282816, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.3.attn_k.bias", "offset": 4790200320, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.3.attn_k.weight", "offset": 4790202368, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.3.attn_output.weight", "offset": 4791463936, "shape": [ 3584, 3584 ], "size": 1261568, "type": 13 }, { "name": "blk.3.attn_q.bias", "offset": 4800294912, "shape": [ 3584 ], "size": 8830976, "type": 0 }, { "name": "blk.3.attn_q.weight", "offset": 4800309248, "shape": [ 3584, 3584 ], "size": 14336, "type": 13 }, { "name": "blk.3.attn_v.bias", "offset": 4809140224, "shape": [ 512 ], "size": 8830976, "type": 0 }, { "name": "blk.3.attn_v.weight", "offset": 4809142272, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.3.attn_norm.weight", "offset": 4810403840, "shape": [ 3584 ], "size": 1261568, "type": 0 }, { "name": "blk.3.ffn_down_exps.weight", "offset": 4810418176, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 13 }, { "name": "blk.3.ffn_gate_exps.weight", "offset": 5214119936, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.3.ffn_up_exps.weight", "offset": 5617821696, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.3.ffn_down_shexp.weight", "offset": 6021523456, "shape": [ 20480, 3584 ], "size": 403701760, "type": 13 }, { "name": "blk.3.ffn_gate_shexp.weight", "offset": 6071986176, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.3.ffn_up_shexp.weight", "offset": 6122448896, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.3.ffn_gate_inp_shexp.weight", "offset": 6172911616, "shape": [ 3584 ], "size": 50462720, "type": 0 }, { "name": "blk.3.ffn_norm.weight", "offset": 6172925952, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.4.ffn_gate_inp.weight", "offset": 6172940288, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.4.attn_k.bias", "offset": 6173857792, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.4.attn_k.weight", "offset": 6173859840, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.4.attn_output.weight", "offset": 6175121408, "shape": [ 3584, 3584 ], "size": 1261568, "type": 13 }, { "name": "blk.4.attn_q.bias", "offset": 6183952384, "shape": [ 3584 ], "size": 8830976, "type": 0 }, { "name": "blk.4.attn_q.weight", "offset": 6183966720, "shape": [ 3584, 3584 ], "size": 14336, "type": 13 }, { "name": "blk.4.attn_v.bias", "offset": 6192797696, "shape": [ 512 ], "size": 8830976, "type": 0 }, { "name": "blk.4.attn_v.weight", "offset": 6192799744, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.4.attn_norm.weight", "offset": 6194061312, "shape": [ 3584 ], "size": 1261568, "type": 0 }, { "name": "blk.4.ffn_down_exps.weight", "offset": 6194075648, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 13 }, { "name": "blk.4.ffn_gate_exps.weight", "offset": 6597777408, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.4.ffn_up_exps.weight", "offset": 7001479168, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.4.ffn_down_shexp.weight", "offset": 7405180928, "shape": [ 20480, 3584 ], "size": 403701760, "type": 13 }, { "name": "blk.4.ffn_gate_shexp.weight", "offset": 7455643648, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.4.ffn_up_shexp.weight", "offset": 7506106368, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.4.ffn_gate_inp_shexp.weight", "offset": 7556569088, "shape": [ 3584 ], "size": 50462720, "type": 0 }, { "name": "blk.4.ffn_norm.weight", "offset": 7556583424, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.5.ffn_gate_inp.weight", "offset": 7556597760, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.5.attn_k.bias", "offset": 7557515264, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.5.attn_k.weight", "offset": 7557517312, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.5.attn_output.weight", "offset": 7558778880, "shape": [ 3584, 3584 ], "size": 1261568, "type": 13 }, { "name": "blk.5.attn_q.bias", "offset": 7567609856, "shape": [ 3584 ], "size": 8830976, "type": 0 }, { "name": "blk.5.attn_q.weight", "offset": 7567624192, "shape": [ 3584, 3584 ], "size": 14336, "type": 13 }, { "name": "blk.5.attn_v.bias", "offset": 7576455168, "shape": [ 512 ], "size": 8830976, "type": 0 }, { "name": "blk.5.attn_v.weight", "offset": 7576457216, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.5.attn_norm.weight", "offset": 7577962496, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.5.ffn_down_exps.weight", "offset": 7577976832, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.5.ffn_gate_exps.weight", "offset": 8059666432, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 13 }, { "name": "blk.5.ffn_up_exps.weight", "offset": 8463368192, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.5.ffn_down_shexp.weight", "offset": 8867069952, "shape": [ 20480, 3584 ], "size": 403701760, "type": 14 }, { "name": "blk.5.ffn_gate_shexp.weight", "offset": 8927281152, "shape": [ 3584, 20480 ], "size": 60211200, "type": 13 }, { "name": "blk.5.ffn_up_shexp.weight", "offset": 8977743872, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.5.ffn_gate_inp_shexp.weight", "offset": 9028206592, "shape": [ 3584 ], "size": 50462720, "type": 0 }, { "name": "blk.5.ffn_norm.weight", "offset": 9028220928, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.6.ffn_gate_inp.weight", "offset": 9028235264, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.6.attn_k.bias", "offset": 9029152768, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.6.attn_k.weight", "offset": 9029154816, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.6.attn_output.weight", "offset": 9030416384, "shape": [ 3584, 3584 ], "size": 1261568, "type": 13 }, { "name": "blk.6.attn_q.bias", "offset": 9039247360, "shape": [ 3584 ], "size": 8830976, "type": 0 }, { "name": "blk.6.attn_q.weight", "offset": 9039261696, "shape": [ 3584, 3584 ], "size": 14336, "type": 13 }, { "name": "blk.6.attn_v.bias", "offset": 9048092672, "shape": [ 512 ], "size": 8830976, "type": 0 }, { "name": "blk.6.attn_v.weight", "offset": 9048094720, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.6.attn_norm.weight", "offset": 9049356288, "shape": [ 3584 ], "size": 1261568, "type": 0 }, { "name": "blk.6.ffn_down_exps.weight", "offset": 9049370624, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 13 }, { "name": "blk.6.ffn_gate_exps.weight", "offset": 9453072384, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.6.ffn_up_exps.weight", "offset": 9856774144, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.6.ffn_down_shexp.weight", "offset": 10260475904, "shape": [ 20480, 3584 ], "size": 403701760, "type": 13 }, { "name": "blk.6.ffn_gate_shexp.weight", "offset": 10310938624, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.6.ffn_up_shexp.weight", "offset": 10361401344, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.6.ffn_gate_inp_shexp.weight", "offset": 10411864064, "shape": [ 3584 ], "size": 50462720, "type": 0 }, { "name": "blk.6.ffn_norm.weight", "offset": 10411878400, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.7.ffn_gate_inp.weight", "offset": 10411892736, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.7.attn_k.bias", "offset": 10412810240, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.7.attn_k.weight", "offset": 10412812288, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.7.attn_output.weight", "offset": 10414073856, "shape": [ 3584, 3584 ], "size": 1261568, "type": 13 }, { "name": "blk.7.attn_q.bias", "offset": 10422904832, "shape": [ 3584 ], "size": 8830976, "type": 0 }, { "name": "blk.7.attn_q.weight", "offset": 10422919168, "shape": [ 3584, 3584 ], "size": 14336, "type": 13 }, { "name": "blk.7.attn_v.bias", "offset": 10431750144, "shape": [ 512 ], "size": 8830976, "type": 0 }, { "name": "blk.7.attn_v.weight", "offset": 10431752192, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.7.attn_norm.weight", "offset": 10433013760, "shape": [ 3584 ], "size": 1261568, "type": 0 }, { "name": "blk.7.ffn_down_exps.weight", "offset": 10433028096, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 13 }, { "name": "blk.7.ffn_gate_exps.weight", "offset": 10836729856, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.7.ffn_up_exps.weight", "offset": 11240431616, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.7.ffn_down_shexp.weight", "offset": 11644133376, "shape": [ 20480, 3584 ], "size": 403701760, "type": 13 }, { "name": "blk.7.ffn_gate_shexp.weight", "offset": 11694596096, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.7.ffn_up_shexp.weight", "offset": 11745058816, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.7.ffn_gate_inp_shexp.weight", "offset": 11795521536, "shape": [ 3584 ], "size": 50462720, "type": 0 }, { "name": "blk.7.ffn_norm.weight", "offset": 11795535872, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.8.ffn_gate_inp.weight", "offset": 11795550208, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.8.attn_k.bias", "offset": 11796467712, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.8.attn_k.weight", "offset": 11796469760, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.8.attn_output.weight", "offset": 11797731328, "shape": [ 3584, 3584 ], "size": 1261568, "type": 13 }, { "name": "blk.8.attn_q.bias", "offset": 11806562304, "shape": [ 3584 ], "size": 8830976, "type": 0 }, { "name": "blk.8.attn_q.weight", "offset": 11806576640, "shape": [ 3584, 3584 ], "size": 14336, "type": 13 }, { "name": "blk.8.attn_v.bias", "offset": 11815407616, "shape": [ 512 ], "size": 8830976, "type": 0 }, { "name": "blk.8.attn_v.weight", "offset": 11815409664, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.8.attn_norm.weight", "offset": 11816914944, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.8.ffn_down_exps.weight", "offset": 11816929280, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.8.ffn_gate_exps.weight", "offset": 12298618880, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 13 }, { "name": "blk.8.ffn_up_exps.weight", "offset": 12702320640, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.8.ffn_down_shexp.weight", "offset": 13106022400, "shape": [ 20480, 3584 ], "size": 403701760, "type": 14 }, { "name": "blk.8.ffn_gate_shexp.weight", "offset": 13166233600, "shape": [ 3584, 20480 ], "size": 60211200, "type": 13 }, { "name": "blk.8.ffn_up_shexp.weight", "offset": 13216696320, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.8.ffn_gate_inp_shexp.weight", "offset": 13267159040, "shape": [ 3584 ], "size": 50462720, "type": 0 }, { "name": "blk.8.ffn_norm.weight", "offset": 13267173376, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.9.ffn_gate_inp.weight", "offset": 13267187712, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.9.attn_k.bias", "offset": 13268105216, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.9.attn_k.weight", "offset": 13268107264, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.9.attn_output.weight", "offset": 13269368832, "shape": [ 3584, 3584 ], "size": 1261568, "type": 13 }, { "name": "blk.9.attn_q.bias", "offset": 13278199808, "shape": [ 3584 ], "size": 8830976, "type": 0 }, { "name": "blk.9.attn_q.weight", "offset": 13278214144, "shape": [ 3584, 3584 ], "size": 14336, "type": 13 }, { "name": "blk.9.attn_v.bias", "offset": 13287045120, "shape": [ 512 ], "size": 8830976, "type": 0 }, { "name": "blk.9.attn_v.weight", "offset": 13287047168, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.10.ffn_gate_inp.weight", "offset": 13288308736, "shape": [ 3584, 64 ], "size": 1261568, "type": 0 }, { "name": "blk.10.attn_k.bias", "offset": 13289226240, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.10.attn_k.weight", "offset": 13289228288, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.10.attn_output.weight", "offset": 13290489856, "shape": [ 3584, 3584 ], "size": 1261568, "type": 13 }, { "name": "blk.10.attn_q.bias", "offset": 13299320832, "shape": [ 3584 ], "size": 8830976, "type": 0 }, { "name": "blk.10.attn_q.weight", "offset": 13299335168, "shape": [ 3584, 3584 ], "size": 14336, "type": 13 }, { "name": "blk.10.attn_v.bias", "offset": 13308166144, "shape": [ 512 ], "size": 8830976, "type": 0 }, { "name": "blk.10.attn_v.weight", "offset": 13308168192, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.9.attn_norm.weight", "offset": 13309429760, "shape": [ 3584 ], "size": 1261568, "type": 0 }, { "name": "blk.9.ffn_down_exps.weight", "offset": 13309444096, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 13 }, { "name": "blk.9.ffn_gate_exps.weight", "offset": 13713145856, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.9.ffn_up_exps.weight", "offset": 14116847616, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.9.ffn_down_shexp.weight", "offset": 14520549376, "shape": [ 20480, 3584 ], "size": 403701760, "type": 13 }, { "name": "blk.9.ffn_gate_shexp.weight", "offset": 14571012096, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.9.ffn_up_shexp.weight", "offset": 14621474816, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.9.ffn_gate_inp_shexp.weight", "offset": 14671937536, "shape": [ 3584 ], "size": 50462720, "type": 0 }, { "name": "blk.9.ffn_norm.weight", "offset": 14671951872, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.10.attn_norm.weight", "offset": 14671966208, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.10.ffn_down_exps.weight", "offset": 14671980544, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 13 }, { "name": "blk.10.ffn_gate_exps.weight", "offset": 15075682304, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.10.ffn_up_exps.weight", "offset": 15479384064, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.10.ffn_down_shexp.weight", "offset": 15883085824, "shape": [ 20480, 3584 ], "size": 403701760, "type": 13 }, { "name": "blk.10.ffn_gate_shexp.weight", "offset": 15933548544, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.10.ffn_up_shexp.weight", "offset": 15984011264, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.10.ffn_gate_inp_shexp.weight", "offset": 16034473984, "shape": [ 3584 ], "size": 50462720, "type": 0 }, { "name": "blk.10.ffn_norm.weight", "offset": 16034488320, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.11.ffn_gate_inp.weight", "offset": 16034502656, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.11.attn_k.bias", "offset": 16035420160, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.11.attn_k.weight", "offset": 16035422208, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.11.attn_output.weight", "offset": 16036683776, "shape": [ 3584, 3584 ], "size": 1261568, "type": 13 }, { "name": "blk.11.attn_q.bias", "offset": 16045514752, "shape": [ 3584 ], "size": 8830976, "type": 0 }, { "name": "blk.11.attn_q.weight", "offset": 16045529088, "shape": [ 3584, 3584 ], "size": 14336, "type": 13 }, { "name": "blk.11.attn_v.bias", "offset": 16054360064, "shape": [ 512 ], "size": 8830976, "type": 0 }, { "name": "blk.11.attn_v.weight", "offset": 16054362112, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.11.attn_norm.weight", "offset": 16055867392, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.11.ffn_down_exps.weight", "offset": 16055881728, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.11.ffn_gate_exps.weight", "offset": 16537571328, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 13 }, { "name": "blk.11.ffn_up_exps.weight", "offset": 16941273088, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.11.ffn_down_shexp.weight", "offset": 17344974848, "shape": [ 20480, 3584 ], "size": 403701760, "type": 14 }, { "name": "blk.11.ffn_gate_shexp.weight", "offset": 17405186048, "shape": [ 3584, 20480 ], "size": 60211200, "type": 13 }, { "name": "blk.11.ffn_up_shexp.weight", "offset": 17455648768, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.11.ffn_gate_inp_shexp.weight", "offset": 17506111488, "shape": [ 3584 ], "size": 50462720, "type": 0 }, { "name": "blk.11.ffn_norm.weight", "offset": 17506125824, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.12.ffn_gate_inp.weight", "offset": 17506140160, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.12.attn_k.bias", "offset": 17507057664, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.12.attn_k.weight", "offset": 17507059712, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.12.attn_output.weight", "offset": 17508321280, "shape": [ 3584, 3584 ], "size": 1261568, "type": 13 }, { "name": "blk.12.attn_q.bias", "offset": 17517152256, "shape": [ 3584 ], "size": 8830976, "type": 0 }, { "name": "blk.12.attn_q.weight", "offset": 17517166592, "shape": [ 3584, 3584 ], "size": 14336, "type": 13 }, { "name": "blk.12.attn_v.bias", "offset": 17525997568, "shape": [ 512 ], "size": 8830976, "type": 0 }, { "name": "blk.12.attn_v.weight", "offset": 17525999616, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.12.attn_norm.weight", "offset": 17527261184, "shape": [ 3584 ], "size": 1261568, "type": 0 }, { "name": "blk.12.ffn_down_exps.weight", "offset": 17527275520, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 13 }, { "name": "blk.12.ffn_gate_exps.weight", "offset": 17930977280, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.12.ffn_up_exps.weight", "offset": 18334679040, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.12.ffn_down_shexp.weight", "offset": 18738380800, "shape": [ 20480, 3584 ], "size": 403701760, "type": 13 }, { "name": "blk.12.ffn_gate_shexp.weight", "offset": 18788843520, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.12.ffn_up_shexp.weight", "offset": 18839306240, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.12.ffn_gate_inp_shexp.weight", "offset": 18889768960, "shape": [ 3584 ], "size": 50462720, "type": 0 }, { "name": "blk.12.ffn_norm.weight", "offset": 18889783296, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.13.ffn_gate_inp.weight", "offset": 18889797632, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.13.attn_k.bias", "offset": 18890715136, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.13.attn_k.weight", "offset": 18890717184, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.13.attn_output.weight", "offset": 18891978752, "shape": [ 3584, 3584 ], "size": 1261568, "type": 13 }, { "name": "blk.13.attn_q.bias", "offset": 18900809728, "shape": [ 3584 ], "size": 8830976, "type": 0 }, { "name": "_gate_inp.weight\u0002\u0000\u0000\u0000", "offset": 18900824064, "shape": [ 3584, 3584 ], "size": 14336, "type": 13 }, { "name": "blk.13.attn_v.bias", "offset": 18909655040, "shape": [ 512 ], "size": 8830976, "type": 0 }, { "name": "blk.13.attn_v.weight", "offset": 18909657088, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.13.attn_norm.weight", "offset": 18910918656, "shape": [ 3584 ], "size": 1261568, "type": 0 }, { "name": "blk.13.ffn_down_exps.weight", "offset": 18910932992, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 13 }, { "name": "blk.13.ffn_gate_exps.weight", "offset": 19314634752, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.13.ffn_up_exps.weight", "offset": 19718336512, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.13.ffn_down_shexp.weight", "offset": 20122038272, "shape": [ 20480, 3584 ], "size": 403701760, "type": 13 }, { "name": "blk.13.ffn_gate_shexp.weight", "offset": 20172500992, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.13.ffn_up_shexp.weight", "offset": 20222963712, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.13.ffn_gate_inp_shexp.weight", "offset": 20273426432, "shape": [ 3584 ], "size": 50462720, "type": 0 }, { "name": "blk.13.ffn_norm.weight", "offset": 20273440768, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.14.ffn_gate_inp.weight", "offset": 20273455104, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.14.attn_k.bias", "offset": 20274372608, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.14.attn_k.weight", "offset": 20274374656, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.14.attn_output.weight", "offset": 20275636224, "shape": [ 3584, 3584 ], "size": 1261568, "type": 13 }, { "name": "blk.14.attn_q.bias", "offset": 20284467200, "shape": [ 3584 ], "size": 8830976, "type": 0 }, { "name": "blk.14.attn_q.weight", "offset": 20284481536, "shape": [ 3584, 3584 ], "size": 14336, "type": 13 }, { "name": "blk.14.attn_v.bias", "offset": 20293312512, "shape": [ 512 ], "size": 8830976, "type": 0 }, { "name": "blk.14.attn_v.weight", "offset": 20293314560, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.14.attn_norm.weight", "offset": 20294819840, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.14.ffn_down_exps.weight", "offset": 20294834176, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.14.ffn_gate_exps.weight", "offset": 20776523776, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 13 }, { "name": "blk.14.ffn_up_exps.weight", "offset": 21180225536, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.14.ffn_down_shexp.weight", "offset": 21583927296, "shape": [ 20480, 3584 ], "size": 403701760, "type": 14 }, { "name": "blk.14.ffn_gate_shexp.weight", "offset": 21644138496, "shape": [ 3584, 20480 ], "size": 60211200, "type": 13 }, { "name": "blk.14.ffn_up_shexp.weight", "offset": 21694601216, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.14.ffn_gate_inp_shexp.weight", "offset": 21745063936, "shape": [ 3584 ], "size": 50462720, "type": 0 }, { "name": "blk.14.ffn_norm.weight", "offset": 21745078272, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.15.ffn_gate_inp.weight", "offset": 21745092608, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.15.attn_k.bias", "offset": 21746010112, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.15.attn_k.weight", "offset": 21746012160, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.15.attn_output.weight", "offset": 21747273728, "shape": [ 3584, 3584 ], "size": 1261568, "type": 13 }, { "name": "blk.15.attn_q.bias", "offset": 21756104704, "shape": [ 3584 ], "size": 8830976, "type": 0 }, { "name": "blk.15.attn_q.weight", "offset": 21756119040, "shape": [ 3584, 3584 ], "size": 14336, "type": 13 }, { "name": "blk.15.attn_v.bias", "offset": 21764950016, "shape": [ 512 ], "size": 8830976, "type": 0 }, { "name": "blk.15.attn_v.weight", "offset": 21764952064, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.15.attn_norm.weight", "offset": 21766213632, "shape": [ 3584 ], "size": 1261568, "type": 0 }, { "name": "blk.15.ffn_down_exps.weight", "offset": 21766227968, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 13 }, { "name": "blk.15.ffn_gate_exps.weight", "offset": 22169929728, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.15.ffn_up_exps.weight", "offset": 22573631488, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.15.ffn_down_shexp.weight", "offset": 22977333248, "shape": [ 20480, 3584 ], "size": 403701760, "type": 13 }, { "name": "blk.15.ffn_gate_shexp.weight", "offset": 23027795968, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.15.ffn_up_shexp.weight", "offset": 23078258688, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.15.ffn_gate_inp_shexp.weight", "offset": 23128721408, "shape": [ 3584 ], "size": 50462720, "type": 0 }, { "name": "blk.15.ffn_norm.weight", "offset": 23128735744, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.16.ffn_gate_inp.weight", "offset": 23128750080, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.16.attn_k.bias", "offset": 23129667584, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.16.attn_k.weight", "offset": 23129669632, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.16.attn_output.weight", "offset": 23130931200, "shape": [ 3584, 3584 ], "size": 1261568, "type": 13 }, { "name": "blk.16.attn_q.bias", "offset": 23139762176, "shape": [ 3584 ], "size": 8830976, "type": 0 }, { "name": "blk.16.attn_q.weight", "offset": 23139776512, "shape": [ 3584, 3584 ], "size": 14336, "type": 13 }, { "name": "blk.16.attn_v.bias", "offset": 23148607488, "shape": [ 512 ], "size": 8830976, "type": 0 }, { "name": "blk.16.attn_v.weight", "offset": 23148609536, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.16.attn_norm.weight", "offset": 23149871104, "shape": [ 3584 ], "size": 1261568, "type": 0 }, { "name": "blk.16.ffn_down_exps.weight", "offset": 23149885440, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 13 }, { "name": "blk.16.ffn_gate_exps.weight", "offset": 23553587200, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.16.ffn_up_exps.weight", "offset": 23957288960, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.16.ffn_down_shexp.weight", "offset": 24360990720, "shape": [ 20480, 3584 ], "size": 403701760, "type": 13 }, { "name": "blk.16.ffn_gate_shexp.weight", "offset": 24411453440, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.16.ffn_up_shexp.weight", "offset": 24461916160, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.16.ffn_gate_inp_shexp.weight", "offset": 24512378880, "shape": [ 3584 ], "size": 50462720, "type": 0 }, { "name": "blk.16.ffn_norm.weight", "offset": 24512393216, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.17.ffn_gate_inp.weight", "offset": 24512407552, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.17.attn_k.bias", "offset": 24513325056, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.17.attn_k.weight", "offset": 24513327104, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.17.attn_output.weight", "offset": 24514588672, "shape": [ 3584, 3584 ], "size": 1261568, "type": 13 }, { "name": "blk.17.attn_q.bias", "offset": 24523419648, "shape": [ 3584 ], "size": 8830976, "type": 0 }, { "name": "blk.17.attn_q.weight", "offset": 24523433984, "shape": [ 3584, 3584 ], "size": 14336, "type": 13 }, { "name": "blk.17.attn_v.bias", "offset": 24532264960, "shape": [ 512 ], "size": 8830976, "type": 0 }, { "name": "blk.17.attn_v.weight", "offset": 24532267008, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.17.attn_norm.weight", "offset": 24533772288, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.17.ffn_down_exps.weight", "offset": 24533786624, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.17.ffn_gate_exps.weight", "offset": 25015476224, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 13 }, { "name": "blk.17.ffn_up_exps.weight", "offset": 25419177984, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.17.ffn_down_shexp.weight", "offset": 25822879744, "shape": [ 20480, 3584 ], "size": 403701760, "type": 14 }, { "name": "blk.17.ffn_gate_shexp.weight", "offset": 25883090944, "shape": [ 3584, 20480 ], "size": 60211200, "type": 13 }, { "name": "blk.17.ffn_up_shexp.weight", "offset": 25933553664, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.17.ffn_gate_inp_shexp.weight", "offset": 25984016384, "shape": [ 3584 ], "size": 50462720, "type": 0 }, { "name": "blk.17.ffn_norm.weight", "offset": 25984030720, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.18.ffn_gate_inp.weight", "offset": 25984045056, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.18.attn_k.bias", "offset": 25984962560, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.18.attn_k.weight", "offset": 25984964608, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.18.attn_output.weight", "offset": 25986226176, "shape": [ 3584, 3584 ], "size": 1261568, "type": 13 }, { "name": "blk.18.attn_q.bias", "offset": 25995057152, "shape": [ 3584 ], "size": 8830976, "type": 0 }, { "name": "blk.18.attn_q.weight", "offset": 25995071488, "shape": [ 3584, 3584 ], "size": 14336, "type": 13 }, { "name": "blk.18.attn_v.bias", "offset": 26003902464, "shape": [ 512 ], "size": 8830976, "type": 0 }, { "name": "blk.18.attn_v.weight", "offset": 26003904512, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.18.attn_norm.weight", "offset": 26005166080, "shape": [ 3584 ], "size": 1261568, "type": 0 }, { "name": "blk.18.ffn_down_exps.weight", "offset": 26005180416, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 13 }, { "name": "blk.18.ffn_gate_exps.weight", "offset": 26408882176, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.18.ffn_up_exps.weight", "offset": 26812583936, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.18.ffn_down_shexp.weight", "offset": 27216285696, "shape": [ 20480, 3584 ], "size": 403701760, "type": 13 }, { "name": "blk.18.ffn_gate_shexp.weight", "offset": 27266748416, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.18.ffn_up_shexp.weight", "offset": 27317211136, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.18.ffn_gate_inp_shexp.weight", "offset": 27367673856, "shape": [ 3584 ], "size": 50462720, "type": 0 }, { "name": "blk.18.ffn_norm.weight", "offset": 27367688192, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.19.ffn_gate_inp.weight", "offset": 27367702528, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.19.attn_k.bias", "offset": 27368620032, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.19.attn_k.weight", "offset": 27368622080, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.19.attn_output.weight", "offset": 27369883648, "shape": [ 3584, 3584 ], "size": 1261568, "type": 13 }, { "name": "blk.19.attn_q.bias", "offset": 27378714624, "shape": [ 3584 ], "size": 8830976, "type": 0 }, { "name": "blk.19.attn_q.weight", "offset": 27378728960, "shape": [ 3584, 3584 ], "size": 14336, "type": 13 }, { "name": "blk.19.attn_v.bias", "offset": 27387559936, "shape": [ 512 ], "size": 8830976, "type": 0 }, { "name": "blk.19.attn_v.weight", "offset": 27387561984, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.19.attn_norm.weight", "offset": 27388823552, "shape": [ 3584 ], "size": 1261568, "type": 0 }, { "name": "blk.19.ffn_down_exps.weight", "offset": 27388837888, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 13 }, { "name": "blk.19.ffn_gate_exps.weight", "offset": 27792539648, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.19.ffn_up_exps.weight", "offset": 28196241408, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.19.ffn_down_shexp.weight", "offset": 28599943168, "shape": [ 20480, 3584 ], "size": 403701760, "type": 13 }, { "name": "blk.19.ffn_gate_shexp.weight", "offset": 28650405888, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.19.ffn_up_shexp.weight", "offset": 28700868608, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.19.ffn_gate_inp_shexp.weight", "offset": 28751331328, "shape": [ 3584 ], "size": 50462720, "type": 0 }, { "name": "blk.19.ffn_norm.weight", "offset": 28751345664, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.20.ffn_gate_inp.weight", "offset": 28751360000, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.20.attn_k.bias", "offset": 28752277504, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.20.attn_k.weight", "offset": 28752279552, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.20.attn_output.weight", "offset": 28753541120, "shape": [ 3584, 3584 ], "size": 1261568, "type": 13 }, { "name": "blk.20.attn_q.bias", "offset": 28762372096, "shape": [ 3584 ], "size": 8830976, "type": 0 }, { "name": "blk.20.attn_q.weight", "offset": 28762386432, "shape": [ 3584, 3584 ], "size": 14336, "type": 13 }, { "name": "blk.20.attn_v.bias", "offset": 28771217408, "shape": [ 512 ], "size": 8830976, "type": 0 }, { "name": "blk.20.attn_v.weight", "offset": 28771219456, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.20.attn_norm.weight", "offset": 28772724736, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.20.ffn_down_exps.weight", "offset": 28772739072, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.20.ffn_gate_exps.weight", "offset": 29254428672, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 13 }, { "name": "blk.20.ffn_up_exps.weight", "offset": 29658130432, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.20.ffn_down_shexp.weight", "offset": 30061832192, "shape": [ 20480, 3584 ], "size": 403701760, "type": 14 }, { "name": "blk.20.ffn_gate_shexp.weight", "offset": 30122043392, "shape": [ 3584, 20480 ], "size": 60211200, "type": 13 }, { "name": "blk.20.ffn_up_shexp.weight", "offset": 30172506112, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.20.ffn_gate_inp_shexp.weight", "offset": 30222968832, "shape": [ 3584 ], "size": 50462720, "type": 0 }, { "name": "blk.20.ffn_norm.weight", "offset": 30222983168, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.21.ffn_gate_inp.weight", "offset": 30222997504, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.21.attn_k.bias", "offset": 30223915008, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.21.attn_k.weight", "offset": 30223917056, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.21.attn_output.weight", "offset": 30225178624, "shape": [ 3584, 3584 ], "size": 1261568, "type": 13 }, { "name": "blk.21.attn_q.bias", "offset": 30234009600, "shape": [ 3584 ], "size": 8830976, "type": 0 }, { "name": "blk.21.attn_q.weight", "offset": 30234023936, "shape": [ 3584, 3584 ], "size": 14336, "type": 13 }, { "name": "blk.21.attn_v.bias", "offset": 30242854912, "shape": [ 512 ], "size": 8830976, "type": 0 }, { "name": "blk.21.attn_v.weight", "offset": 30242856960, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.21.attn_norm.weight", "offset": 30244118528, "shape": [ 3584 ], "size": 1261568, "type": 0 }, { "name": "blk.21.ffn_down_exps.weight", "offset": 30244132864, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 13 }, { "name": "blk.21.ffn_gate_exps.weight", "offset": 30647834624, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.21.ffn_up_exps.weight", "offset": 31051536384, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.21.ffn_down_shexp.weight", "offset": 31455238144, "shape": [ 20480, 3584 ], "size": 403701760, "type": 13 }, { "name": "blk.21.ffn_gate_shexp.weight", "offset": 31505700864, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.21.ffn_up_shexp.weight", "offset": 31556163584, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.21.ffn_gate_inp_shexp.weight", "offset": 31606626304, "shape": [ 3584 ], "size": 50462720, "type": 0 }, { "name": "blk.21.ffn_norm.weight", "offset": 31606640640, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.22.ffn_gate_inp.weight", "offset": 31606654976, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.22.attn_k.bias", "offset": 31607572480, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.22.attn_k.weight", "offset": 31607574528, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.22.attn_output.weight", "offset": 31608836096, "shape": [ 3584, 3584 ], "size": 1261568, "type": 13 }, { "name": "blk.22.attn_q.bias", "offset": 31617667072, "shape": [ 3584 ], "size": 8830976, "type": 0 }, { "name": "blk.22.attn_q.weight", "offset": 31617681408, "shape": [ 3584, 3584 ], "size": 14336, "type": 13 }, { "name": "blk.22.attn_v.bias", "offset": 31626512384, "shape": [ 512 ], "size": 8830976, "type": 0 }, { "name": "blk.22.attn_v.weight", "offset": 31626514432, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.22.attn_norm.weight", "offset": 31627776000, "shape": [ 3584 ], "size": 1261568, "type": 0 }, { "name": "blk.22.ffn_down_exps.weight", "offset": 31627790336, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 13 }, { "name": "blk.22.ffn_gate_exps.weight", "offset": 32031492096, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.22.ffn_up_exps.weight", "offset": 32435193856, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.22.ffn_down_shexp.weight", "offset": 32838895616, "shape": [ 20480, 3584 ], "size": 403701760, "type": 13 }, { "name": "blk.22.ffn_gate_shexp.weight", "offset": 32889358336, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.22.ffn_up_shexp.weight", "offset": 32939821056, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.22.ffn_gate_inp_shexp.weight", "offset": 32990283776, "shape": [ 3584 ], "size": 50462720, "type": 0 }, { "name": "blk.22.ffn_norm.weight", "offset": 32990298112, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.23.ffn_gate_inp.weight", "offset": 32990312448, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.23.attn_k.bias", "offset": 32991229952, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.23.attn_k.weight", "offset": 32991232000, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.23.attn_output.weight", "offset": 32992493568, "shape": [ 3584, 3584 ], "size": 1261568, "type": 13 }, { "name": "blk.23.attn_q.bias", "offset": 33001324544, "shape": [ 3584 ], "size": 8830976, "type": 0 }, { "name": "blk.23.attn_q.weight", "offset": 33001338880, "shape": [ 3584, 3584 ], "size": 14336, "type": 13 }, { "name": "blk.23.attn_v.bias", "offset": 33010169856, "shape": [ 512 ], "size": 8830976, "type": 0 }, { "name": "blk.23.attn_v.weight", "offset": 33010171904, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.23.attn_norm.weight", "offset": 33011677184, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.23.ffn_down_exps.weight", "offset": 33011691520, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.23.ffn_gate_exps.weight", "offset": 33493381120, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 13 }, { "name": "blk.23.ffn_up_exps.weight", "offset": 33897082880, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.23.ffn_down_shexp.weight", "offset": 34300784640, "shape": [ 20480, 3584 ], "size": 403701760, "type": 14 }, { "name": "blk.23.ffn_gate_shexp.weight", "offset": 34360995840, "shape": [ 3584, 20480 ], "size": 60211200, "type": 13 }, { "name": "blk.23.ffn_up_shexp.weight", "offset": 34411458560, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.23.ffn_gate_inp_shexp.weight", "offset": 34461921280, "shape": [ 3584 ], "size": 50462720, "type": 0 }, { "name": "blk.23.ffn_norm.weight", "offset": 34461935616, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.24.ffn_gate_inp.weight", "offset": 34461949952, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.24.attn_k.bias", "offset": 34462867456, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.24.attn_k.weight", "offset": 34462869504, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.24.attn_output.weight", "offset": 34464131072, "shape": [ 3584, 3584 ], "size": 1261568, "type": 13 }, { "name": "blk.24.attn_q.bias", "offset": 34472962048, "shape": [ 3584 ], "size": 8830976, "type": 0 }, { "name": "blk.24.attn_q.weight", "offset": 34472976384, "shape": [ 3584, 3584 ], "size": 14336, "type": 13 }, { "name": "blk.24.attn_v.bias", "offset": 34481807360, "shape": [ 512 ], "size": 8830976, "type": 0 }, { "name": "blk.24.attn_v.weight", "offset": 34481809408, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.24.attn_norm.weight", "offset": 34483314688, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.24.ffn_down_exps.weight", "offset": 34483329024, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.24.ffn_gate_exps.weight", "offset": 34965018624, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 13 }, { "name": "blk.24.ffn_up_exps.weight", "offset": 35368720384, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.24.ffn_down_shexp.weight", "offset": 35772422144, "shape": [ 20480, 3584 ], "size": 403701760, "type": 14 }, { "name": "blk.24.ffn_gate_shexp.weight", "offset": 35832633344, "shape": [ 3584, 20480 ], "size": 60211200, "type": 13 }, { "name": "blk.24.ffn_up_shexp.weight", "offset": 35883096064, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.24.ffn_gate_inp_shexp.weight", "offset": 35933558784, "shape": [ 3584 ], "size": 50462720, "type": 0 }, { "name": "blk.24.ffn_norm.weight", "offset": 35933573120, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.25.ffn_gate_inp.weight", "offset": 35933587456, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.25.attn_k.bias", "offset": 35934504960, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.25.attn_k.weight", "offset": 35934507008, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.25.attn_output.weight", "offset": 35935768576, "shape": [ 3584, 3584 ], "size": 1261568, "type": 13 }, { "name": "blk.25.attn_q.bias", "offset": 35944599552, "shape": [ 3584 ], "size": 8830976, "type": 0 }, { "name": "blk.25.attn_q.weight", "offset": 35944613888, "shape": [ 3584, 3584 ], "size": 14336, "type": 13 }, { "name": "blk.25.attn_v.bias", "offset": 35953444864, "shape": [ 512 ], "size": 8830976, "type": 0 }, { "name": "blk.25.attn_v.weight", "offset": 35953446912, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.25.attn_norm.weight", "offset": 35954952192, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.25.ffn_down_exps.weight", "offset": 35954966528, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.25.ffn_gate_exps.weight", "offset": 36436656128, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 13 }, { "name": "blk.25.ffn_up_exps.weight", "offset": 36840357888, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.25.ffn_down_shexp.weight", "offset": 37244059648, "shape": [ 20480, 3584 ], "size": 403701760, "type": 14 }, { "name": "blk.25.ffn_gate_shexp.weight", "offset": 37304270848, "shape": [ 3584, 20480 ], "size": 60211200, "type": 13 }, { "name": "blk.25.ffn_up_shexp.weight", "offset": 37354733568, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.25.ffn_gate_inp_shexp.weight", "offset": 37405196288, "shape": [ 3584 ], "size": 50462720, "type": 0 }, { "name": "blk.25.ffn_norm.weight", "offset": 37405210624, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.26.ffn_gate_inp.weight", "offset": 37405224960, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.26.attn_k.bias", "offset": 37406142464, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.26.attn_k.weight", "offset": 37406144512, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.26.attn_output.weight", "offset": 37407406080, "shape": [ 3584, 3584 ], "size": 1261568, "type": 13 }, { "name": "blk.26.attn_q.bias", "offset": 37416237056, "shape": [ 3584 ], "size": 8830976, "type": 0 }, { "name": "blk.26.attn_q.weight", "offset": 37416251392, "shape": [ 3584, 3584 ], "size": 14336, "type": 13 }, { "name": "blk.26.attn_v.bias", "offset": 37425082368, "shape": [ 512 ], "size": 8830976, "type": 0 }, { "name": "blk.26.attn_v.weight", "offset": 37425084416, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "blk.26.attn_norm.weight", "offset": 37426589696, "shape": [ 3584 ], "size": 1505280, "type": 0 }, { "name": "blk.26.ffn_down_exps.weight", "offset": 37426604032, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.26.ffn_gate_exps.weight", "offset": 37908293632, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 13 }, { "name": "blk.26.ffn_up_exps.weight", "offset": 38311995392, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.26.ffn_down_shexp.weight", "offset": 38715697152, "shape": [ 20480, 3584 ], "size": 403701760, "type": 14 }, { "name": "blk.26.ffn_gate_shexp.weight", "offset": 38775908352, "shape": [ 3584, 20480 ], "size": 60211200, "type": 13 }, { "name": "blk.26.ffn_up_shexp.weight", "offset": 38826371072, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.26.ffn_gate_inp_shexp.weight", "offset": 38876833792, "shape": [ 3584 ], "size": 50462720, "type": 0 }, { "name": "blk.26.ffn_norm.weight", "offset": 38876848128, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "blk.27.ffn_gate_inp.weight", "offset": 38876862464, "shape": [ 3584, 64 ], "size": 14336, "type": 0 }, { "name": "blk.27.attn_k.bias", "offset": 38877779968, "shape": [ 512 ], "size": 917504, "type": 0 }, { "name": "blk.27.attn_k.weight", "offset": 38877782016, "shape": [ 3584, 512 ], "size": 2048, "type": 13 }, { "name": "blk.27.attn_output.weight", "offset": 38879043584, "shape": [ 3584, 3584 ], "size": 1261568, "type": 13 }, { "name": "blk.27.attn_q.bias", "offset": 38887874560, "shape": [ 3584 ], "size": 8830976, "type": 0 }, { "name": "blk.27.attn_q.weight", "offset": 38887888896, "shape": [ 3584, 3584 ], "size": 14336, "type": 13 }, { "name": "blk.27.attn_v.bias", "offset": 38896719872, "shape": [ 512 ], "size": 8830976, "type": 0 }, { "name": "blk.27.attn_v.weight", "offset": 38896721920, "shape": [ 3584, 512 ], "size": 2048, "type": 14 }, { "name": "output.weight", "offset": 38898227200, "shape": [ 3584, 151936 ], "size": 1505280, "type": 14 }, { "name": "blk.27.attn_norm.weight", "offset": 39344919040, "shape": [ 3584 ], "size": 446691840, "type": 0 }, { "name": "blk.27.ffn_down_exps.weight", "offset": 39344933376, "shape": [ 2560, 3584, 64 ], "size": 14336, "type": 14 }, { "name": "blk.27.ffn_gate_exps.weight", "offset": 39826622976, "shape": [ 3584, 2560, 64 ], "size": 481689600, "type": 13 }, { "name": "blk.27.ffn_up_exps.weight", "offset": 40230324736, "shape": [ 3584, 2560, 64 ], "size": 403701760, "type": 13 }, { "name": "blk.27.ffn_down_shexp.weight", "offset": 40634026496, "shape": [ 20480, 3584 ], "size": 403701760, "type": 14 }, { "name": "blk.27.ffn_gate_shexp.weight", "offset": 40694237696, "shape": [ 3584, 20480 ], "size": 60211200, "type": 13 }, { "name": "blk.27.ffn_up_shexp.weight", "offset": 40744700416, "shape": [ 3584, 20480 ], "size": 50462720, "type": 13 }, { "name": "blk.27.ffn_gate_inp_shexp.weight", "offset": 40795163136, "shape": [ 3584 ], "size": 50462720, "type": 0 }, { "name": "blk.27.ffn_norm.weight", "offset": 40795177472, "shape": [ 3584 ], "size": 14336, "type": 0 }, { "name": "output_norm.weight", "offset": 40795191808, "shape": [ 3584 ], "size": 14336, "type": 0 } ], "version": 3 }