{"mask":0,"profile":"normal","fusions":{},"tensors":[{"name":"language_model.model.layers.0.linear_attn.in_proj_a.biases","shape":[1,40],"sha256":"3cc64281a64367b9cd3208a0690290c9f33d3e430f23fdc1629e912e4aebc646"},{"name":"language_model.model.layers.0.linear_attn.in_proj_a.scales","shape":[1,40],"sha256":"3cc64281a64367b9cd3208a0690290c9f33d3e430f23fdc1629e912e4aebc646"},{"name":"language_model.model.layers.0.linear_attn.in_proj_a.weight","shape":[1,320],"sha256":"3954880a15bd19c135403b7908b5dfe89f45914b48d9d7390d5c0b5721d828de"},{"name":"language_model.model.layers.0.linear_attn.in_proj_b.biases","shape":[1,40],"sha256":"0f2a0cf1884b62d37e48589848b2e621fbd9105f9ed398b08cd1a05563e12a6f"},{"name":"language_model.model.layers.0.linear_attn.in_proj_b.scales","shape":[1,40],"sha256":"0f2a0cf1884b62d37e48589848b2e621fbd9105f9ed398b08cd1a05563e12a6f"},{"name":"language_model.model.layers.0.linear_attn.in_proj_b.weight","shape":[1,320],"sha256":"ca845474d18d0fc0ae5d66e884ed3f933b1ee2c0c9af7c3c4b34a1416739639e"},{"name":"language_model.model.layers.0.linear_attn.in_proj_qkv.biases","shape":[5,40],"sha256":"fd85f811b5562e5bae2bc05832f1027a57a234a1df7d9e8f4d99416b931983c9"},{"name":"language_model.model.layers.0.linear_attn.in_proj_qkv.scales","shape":[5,40],"sha256":"fd85f811b5562e5bae2bc05832f1027a57a234a1df7d9e8f4d99416b931983c9"},{"name":"language_model.model.layers.0.linear_attn.in_proj_qkv.weight","shape":[5,320],"sha256":"e7955ba6c02e956caea42526136b0f41c29cc3066eefe8a2c6a71bed9dc9da11"},{"name":"language_model.model.layers.0.linear_attn.in_proj_z.biases","shape":[3,40],"sha256":"243eb49ade9062ffcac3214e640b24995402febcfd7a9aafdae8682d7cbb2cc8"},{"name":"language_model.model.layers.0.linear_attn.in_proj_z.scales","shape":[3,40],"sha256":"243eb49ade9062ffcac3214e640b24995402febcfd7a9aafdae8682d7cbb2cc8"},{"name":"language_model.model.layers.0.linear_attn.in_proj_z.weight","shape":[3,320],"sha256":"3b1cab4c5a92b13a4ca492b882ce350b36866dd6b246172046483aad9d82e357"},{"name":"language_model.model.layers.0.mlp.shared_expert.gate_proj.biases","shape":[4,40],"sha256":"765708c88ebadb8446fe8fac04f627a928498202c1e108a61fe816772e7460f7"},{"name":"language_model.model.layers.0.mlp.shared_expert.gate_proj.scales","shape":[4,40],"sha256":"765708c88ebadb8446fe8fac04f627a928498202c1e108a61fe816772e7460f7"},{"name":"language_model.model.layers.0.mlp.shared_expert.gate_proj.weight","shape":[4,320],"sha256":"102d250f8e3223ff4a07b32ae21da305982eeeafe25d569fb64d408ee205a699"},{"name":"language_model.model.layers.0.mlp.shared_expert.up_proj.biases","shape":[4,40],"sha256":"2f56a66287bb3cba50ca9b47df972ebaa483d83e6a9a74391ed044e54b0002c2"},{"name":"language_model.model.layers.0.mlp.shared_expert.up_proj.scales","shape":[4,40],"sha256":"2f56a66287bb3cba50ca9b47df972ebaa483d83e6a9a74391ed044e54b0002c2"},{"name":"language_model.model.layers.0.mlp.shared_expert.up_proj.weight","shape":[4,320],"sha256":"fafcd9dcd7459bcd6db2929be8a67f3b7ae0140f1446f240c7b83d2713575867"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gate_proj.biases","shape":[2,4,40],"sha256":"80dca76d4ead1253410b9c4352909882e73a90241ef0a0c7b28506f727b13c95"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gate_proj.scales","shape":[2,4,40],"sha256":"80dca76d4ead1253410b9c4352909882e73a90241ef0a0c7b28506f727b13c95"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gate_proj.weight","shape":[2,4,320],"sha256":"7506968c7bf5d98034f3d0d5122e8619b4c17c8938400528ddf94a7cabb7848b"},{"name":"language_model.model.layers.0.mlp.switch_mlp.up_proj.biases","shape":[2,4,40],"sha256":"79d157796e519f46fa701dbe0ae0136cef75da591467b58c6a31b46cdb04d8bb"},{"name":"language_model.model.layers.0.mlp.switch_mlp.up_proj.scales","shape":[2,4,40],"sha256":"79d157796e519f46fa701dbe0ae0136cef75da591467b58c6a31b46cdb04d8bb"},{"name":"language_model.model.layers.0.mlp.switch_mlp.up_proj.weight","shape":[2,4,320],"sha256":"074f9a181bd0604c53d2c54d74c272117fe237cd4b29503a944f95932c444fcb"},{"name":"language_model.model.layers.1.self_attn.indexer.index_qk_proj.biases","shape":[3,40],"sha256":"95f422d87acf791e984abd847ed88b7e7b0ea2d68c1551493460ca6ed70b1a04"},{"name":"language_model.model.layers.1.self_attn.indexer.index_qk_proj.scales","shape":[3,40],"sha256":"95f422d87acf791e984abd847ed88b7e7b0ea2d68c1551493460ca6ed70b1a04"},{"name":"language_model.model.layers.1.self_attn.indexer.index_qk_proj.weight","shape":[3,320],"sha256":"3de0965101509f3b7448fe48331a3d5cc03383edac337d98597a5c122046b50d"},{"name":"language_model.model.layers.1.self_attn.k_proj.biases","shape":[2,40],"sha256":"232a4c45122a0e17b33bcafa70e313d3cbcbac0436066caf6660d5bfdbc115f8"},{"name":"language_model.model.layers.1.self_attn.k_proj.scales","shape":[2,40],"sha256":"232a4c45122a0e17b33bcafa70e313d3cbcbac0436066caf6660d5bfdbc115f8"},{"name":"language_model.model.layers.1.self_attn.k_proj.weight","shape":[2,320],"sha256":"f7d11c32334014020edcd53479ba08c7235c7779fe7be62af8a25a3bdd56f315"},{"name":"language_model.model.layers.1.self_attn.q_proj.biases","shape":[5,40],"sha256":"3dbadbdc762991a12c532218f3b14845cee793cd01894d9a21b19e91991f8130"},{"name":"language_model.model.layers.1.self_attn.q_proj.scales","shape":[5,40],"sha256":"3dbadbdc762991a12c532218f3b14845cee793cd01894d9a21b19e91991f8130"},{"name":"language_model.model.layers.1.self_attn.q_proj.weight","shape":[5,320],"sha256":"56b2d930469ab03a73e4f24448aa4b9ad2a4b634df5f7498966f43a94ba55e73"},{"name":"language_model.model.layers.1.self_attn.v_proj.biases","shape":[2,40],"sha256":"97d50c02e62d40b6049e08441573ea5c2850acd8175a9e78050360c50fee96e7"},{"name":"language_model.model.layers.1.self_attn.v_proj.scales","shape":[2,40],"sha256":"97d50c02e62d40b6049e08441573ea5c2850acd8175a9e78050360c50fee96e7"},{"name":"language_model.model.layers.1.self_attn.v_proj.weight","shape":[2,320],"sha256":"a8ba87d8b51862aa10ebf5c0f67f22b3f9a11991992e90911be9e707d706635a"}]} {"mask":1,"profile":"normal","fusions":{"language_model.model.layers.0.mlp.switch_mlp":{"bits":4,"group":64,"splits":[]},"language_model.model.layers.0.mlp.shared_expert":{"bits":4,"group":64,"splits":[]}},"tensors":[{"name":"language_model.model.layers.0.linear_attn.in_proj_a.biases","shape":[1,40],"sha256":"3cc64281a64367b9cd3208a0690290c9f33d3e430f23fdc1629e912e4aebc646"},{"name":"language_model.model.layers.0.linear_attn.in_proj_a.scales","shape":[1,40],"sha256":"3cc64281a64367b9cd3208a0690290c9f33d3e430f23fdc1629e912e4aebc646"},{"name":"language_model.model.layers.0.linear_attn.in_proj_a.weight","shape":[1,320],"sha256":"3954880a15bd19c135403b7908b5dfe89f45914b48d9d7390d5c0b5721d828de"},{"name":"language_model.model.layers.0.linear_attn.in_proj_b.biases","shape":[1,40],"sha256":"0f2a0cf1884b62d37e48589848b2e621fbd9105f9ed398b08cd1a05563e12a6f"},{"name":"language_model.model.layers.0.linear_attn.in_proj_b.scales","shape":[1,40],"sha256":"0f2a0cf1884b62d37e48589848b2e621fbd9105f9ed398b08cd1a05563e12a6f"},{"name":"language_model.model.layers.0.linear_attn.in_proj_b.weight","shape":[1,320],"sha256":"ca845474d18d0fc0ae5d66e884ed3f933b1ee2c0c9af7c3c4b34a1416739639e"},{"name":"language_model.model.layers.0.linear_attn.in_proj_qkv.biases","shape":[5,40],"sha256":"fd85f811b5562e5bae2bc05832f1027a57a234a1df7d9e8f4d99416b931983c9"},{"name":"language_model.model.layers.0.linear_attn.in_proj_qkv.scales","shape":[5,40],"sha256":"fd85f811b5562e5bae2bc05832f1027a57a234a1df7d9e8f4d99416b931983c9"},{"name":"language_model.model.layers.0.linear_attn.in_proj_qkv.weight","shape":[5,320],"sha256":"e7955ba6c02e956caea42526136b0f41c29cc3066eefe8a2c6a71bed9dc9da11"},{"name":"language_model.model.layers.0.linear_attn.in_proj_z.biases","shape":[3,40],"sha256":"243eb49ade9062ffcac3214e640b24995402febcfd7a9aafdae8682d7cbb2cc8"},{"name":"language_model.model.layers.0.linear_attn.in_proj_z.scales","shape":[3,40],"sha256":"243eb49ade9062ffcac3214e640b24995402febcfd7a9aafdae8682d7cbb2cc8"},{"name":"language_model.model.layers.0.linear_attn.in_proj_z.weight","shape":[3,320],"sha256":"3b1cab4c5a92b13a4ca492b882ce350b36866dd6b246172046483aad9d82e357"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_biases","shape":[8,40],"sha256":"ccc740c7994dd6367548fb81759a1916e3ed492b6c137b1337cdabe3ca453332"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_scales","shape":[8,40],"sha256":"ccc740c7994dd6367548fb81759a1916e3ed492b6c137b1337cdabe3ca453332"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_weight","shape":[8,320],"sha256":"393fc4f46b05750db834b2a79ccbeef674d7b073a73edd51e67510e177beccb2"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_biases","shape":[2,8,40],"sha256":"592f72b7046080a0c440832a296bf061ee56d889b0e75f3308774c1d7cfa1f99"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_scales","shape":[2,8,40],"sha256":"592f72b7046080a0c440832a296bf061ee56d889b0e75f3308774c1d7cfa1f99"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_weight","shape":[2,8,320],"sha256":"c59e7fcfc36b3d60bc29d59592c841efaf9434de2379190942f68625636abf17"},{"name":"language_model.model.layers.1.self_attn.indexer.index_qk_proj.biases","shape":[3,40],"sha256":"95f422d87acf791e984abd847ed88b7e7b0ea2d68c1551493460ca6ed70b1a04"},{"name":"language_model.model.layers.1.self_attn.indexer.index_qk_proj.scales","shape":[3,40],"sha256":"95f422d87acf791e984abd847ed88b7e7b0ea2d68c1551493460ca6ed70b1a04"},{"name":"language_model.model.layers.1.self_attn.indexer.index_qk_proj.weight","shape":[3,320],"sha256":"3de0965101509f3b7448fe48331a3d5cc03383edac337d98597a5c122046b50d"},{"name":"language_model.model.layers.1.self_attn.k_proj.biases","shape":[2,40],"sha256":"232a4c45122a0e17b33bcafa70e313d3cbcbac0436066caf6660d5bfdbc115f8"},{"name":"language_model.model.layers.1.self_attn.k_proj.scales","shape":[2,40],"sha256":"232a4c45122a0e17b33bcafa70e313d3cbcbac0436066caf6660d5bfdbc115f8"},{"name":"language_model.model.layers.1.self_attn.k_proj.weight","shape":[2,320],"sha256":"f7d11c32334014020edcd53479ba08c7235c7779fe7be62af8a25a3bdd56f315"},{"name":"language_model.model.layers.1.self_attn.q_proj.biases","shape":[5,40],"sha256":"3dbadbdc762991a12c532218f3b14845cee793cd01894d9a21b19e91991f8130"},{"name":"language_model.model.layers.1.self_attn.q_proj.scales","shape":[5,40],"sha256":"3dbadbdc762991a12c532218f3b14845cee793cd01894d9a21b19e91991f8130"},{"name":"language_model.model.layers.1.self_attn.q_proj.weight","shape":[5,320],"sha256":"56b2d930469ab03a73e4f24448aa4b9ad2a4b634df5f7498966f43a94ba55e73"},{"name":"language_model.model.layers.1.self_attn.v_proj.biases","shape":[2,40],"sha256":"97d50c02e62d40b6049e08441573ea5c2850acd8175a9e78050360c50fee96e7"},{"name":"language_model.model.layers.1.self_attn.v_proj.scales","shape":[2,40],"sha256":"97d50c02e62d40b6049e08441573ea5c2850acd8175a9e78050360c50fee96e7"},{"name":"language_model.model.layers.1.self_attn.v_proj.weight","shape":[2,320],"sha256":"a8ba87d8b51862aa10ebf5c0f67f22b3f9a11991992e90911be9e707d706635a"}]} {"mask":2,"profile":"normal","fusions":{"language_model.model.layers.0.linear_attn.in_proj_fused":{"bits":4,"group":64,"splits":[5,8,9]}},"tensors":[{"name":"language_model.model.layers.0.linear_attn.in_proj_fused.biases","shape":[10,40],"sha256":"5a2483da6433a2e53182a5f3acdfb6f6ea3646947527a87211354bbcee15dfd5"},{"name":"language_model.model.layers.0.linear_attn.in_proj_fused.scales","shape":[10,40],"sha256":"5a2483da6433a2e53182a5f3acdfb6f6ea3646947527a87211354bbcee15dfd5"},{"name":"language_model.model.layers.0.linear_attn.in_proj_fused.weight","shape":[10,320],"sha256":"84703ee405db83d0cd5f823950a6f244a727432729299a4138e12a3c7f244335"},{"name":"language_model.model.layers.0.mlp.shared_expert.gate_proj.biases","shape":[4,40],"sha256":"765708c88ebadb8446fe8fac04f627a928498202c1e108a61fe816772e7460f7"},{"name":"language_model.model.layers.0.mlp.shared_expert.gate_proj.scales","shape":[4,40],"sha256":"765708c88ebadb8446fe8fac04f627a928498202c1e108a61fe816772e7460f7"},{"name":"language_model.model.layers.0.mlp.shared_expert.gate_proj.weight","shape":[4,320],"sha256":"102d250f8e3223ff4a07b32ae21da305982eeeafe25d569fb64d408ee205a699"},{"name":"language_model.model.layers.0.mlp.shared_expert.up_proj.biases","shape":[4,40],"sha256":"2f56a66287bb3cba50ca9b47df972ebaa483d83e6a9a74391ed044e54b0002c2"},{"name":"language_model.model.layers.0.mlp.shared_expert.up_proj.scales","shape":[4,40],"sha256":"2f56a66287bb3cba50ca9b47df972ebaa483d83e6a9a74391ed044e54b0002c2"},{"name":"language_model.model.layers.0.mlp.shared_expert.up_proj.weight","shape":[4,320],"sha256":"fafcd9dcd7459bcd6db2929be8a67f3b7ae0140f1446f240c7b83d2713575867"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gate_proj.biases","shape":[2,4,40],"sha256":"80dca76d4ead1253410b9c4352909882e73a90241ef0a0c7b28506f727b13c95"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gate_proj.scales","shape":[2,4,40],"sha256":"80dca76d4ead1253410b9c4352909882e73a90241ef0a0c7b28506f727b13c95"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gate_proj.weight","shape":[2,4,320],"sha256":"7506968c7bf5d98034f3d0d5122e8619b4c17c8938400528ddf94a7cabb7848b"},{"name":"language_model.model.layers.0.mlp.switch_mlp.up_proj.biases","shape":[2,4,40],"sha256":"79d157796e519f46fa701dbe0ae0136cef75da591467b58c6a31b46cdb04d8bb"},{"name":"language_model.model.layers.0.mlp.switch_mlp.up_proj.scales","shape":[2,4,40],"sha256":"79d157796e519f46fa701dbe0ae0136cef75da591467b58c6a31b46cdb04d8bb"},{"name":"language_model.model.layers.0.mlp.switch_mlp.up_proj.weight","shape":[2,4,320],"sha256":"074f9a181bd0604c53d2c54d74c272117fe237cd4b29503a944f95932c444fcb"},{"name":"language_model.model.layers.1.self_attn.indexer.index_qk_proj.biases","shape":[3,40],"sha256":"95f422d87acf791e984abd847ed88b7e7b0ea2d68c1551493460ca6ed70b1a04"},{"name":"language_model.model.layers.1.self_attn.indexer.index_qk_proj.scales","shape":[3,40],"sha256":"95f422d87acf791e984abd847ed88b7e7b0ea2d68c1551493460ca6ed70b1a04"},{"name":"language_model.model.layers.1.self_attn.indexer.index_qk_proj.weight","shape":[3,320],"sha256":"3de0965101509f3b7448fe48331a3d5cc03383edac337d98597a5c122046b50d"},{"name":"language_model.model.layers.1.self_attn.k_proj.biases","shape":[2,40],"sha256":"232a4c45122a0e17b33bcafa70e313d3cbcbac0436066caf6660d5bfdbc115f8"},{"name":"language_model.model.layers.1.self_attn.k_proj.scales","shape":[2,40],"sha256":"232a4c45122a0e17b33bcafa70e313d3cbcbac0436066caf6660d5bfdbc115f8"},{"name":"language_model.model.layers.1.self_attn.k_proj.weight","shape":[2,320],"sha256":"f7d11c32334014020edcd53479ba08c7235c7779fe7be62af8a25a3bdd56f315"},{"name":"language_model.model.layers.1.self_attn.q_proj.biases","shape":[5,40],"sha256":"3dbadbdc762991a12c532218f3b14845cee793cd01894d9a21b19e91991f8130"},{"name":"language_model.model.layers.1.self_attn.q_proj.scales","shape":[5,40],"sha256":"3dbadbdc762991a12c532218f3b14845cee793cd01894d9a21b19e91991f8130"},{"name":"language_model.model.layers.1.self_attn.q_proj.weight","shape":[5,320],"sha256":"56b2d930469ab03a73e4f24448aa4b9ad2a4b634df5f7498966f43a94ba55e73"},{"name":"language_model.model.layers.1.self_attn.v_proj.biases","shape":[2,40],"sha256":"97d50c02e62d40b6049e08441573ea5c2850acd8175a9e78050360c50fee96e7"},{"name":"language_model.model.layers.1.self_attn.v_proj.scales","shape":[2,40],"sha256":"97d50c02e62d40b6049e08441573ea5c2850acd8175a9e78050360c50fee96e7"},{"name":"language_model.model.layers.1.self_attn.v_proj.weight","shape":[2,320],"sha256":"a8ba87d8b51862aa10ebf5c0f67f22b3f9a11991992e90911be9e707d706635a"}]} {"mask":3,"profile":"normal","fusions":{"language_model.model.layers.0.mlp.switch_mlp":{"bits":4,"group":64,"splits":[]},"language_model.model.layers.0.mlp.shared_expert":{"bits":4,"group":64,"splits":[]},"language_model.model.layers.0.linear_attn.in_proj_fused":{"bits":4,"group":64,"splits":[5,8,9]}},"tensors":[{"name":"language_model.model.layers.0.linear_attn.in_proj_fused.biases","shape":[10,40],"sha256":"5a2483da6433a2e53182a5f3acdfb6f6ea3646947527a87211354bbcee15dfd5"},{"name":"language_model.model.layers.0.linear_attn.in_proj_fused.scales","shape":[10,40],"sha256":"5a2483da6433a2e53182a5f3acdfb6f6ea3646947527a87211354bbcee15dfd5"},{"name":"language_model.model.layers.0.linear_attn.in_proj_fused.weight","shape":[10,320],"sha256":"84703ee405db83d0cd5f823950a6f244a727432729299a4138e12a3c7f244335"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_biases","shape":[8,40],"sha256":"ccc740c7994dd6367548fb81759a1916e3ed492b6c137b1337cdabe3ca453332"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_scales","shape":[8,40],"sha256":"ccc740c7994dd6367548fb81759a1916e3ed492b6c137b1337cdabe3ca453332"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_weight","shape":[8,320],"sha256":"393fc4f46b05750db834b2a79ccbeef674d7b073a73edd51e67510e177beccb2"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_biases","shape":[2,8,40],"sha256":"592f72b7046080a0c440832a296bf061ee56d889b0e75f3308774c1d7cfa1f99"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_scales","shape":[2,8,40],"sha256":"592f72b7046080a0c440832a296bf061ee56d889b0e75f3308774c1d7cfa1f99"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_weight","shape":[2,8,320],"sha256":"c59e7fcfc36b3d60bc29d59592c841efaf9434de2379190942f68625636abf17"},{"name":"language_model.model.layers.1.self_attn.indexer.index_qk_proj.biases","shape":[3,40],"sha256":"95f422d87acf791e984abd847ed88b7e7b0ea2d68c1551493460ca6ed70b1a04"},{"name":"language_model.model.layers.1.self_attn.indexer.index_qk_proj.scales","shape":[3,40],"sha256":"95f422d87acf791e984abd847ed88b7e7b0ea2d68c1551493460ca6ed70b1a04"},{"name":"language_model.model.layers.1.self_attn.indexer.index_qk_proj.weight","shape":[3,320],"sha256":"3de0965101509f3b7448fe48331a3d5cc03383edac337d98597a5c122046b50d"},{"name":"language_model.model.layers.1.self_attn.k_proj.biases","shape":[2,40],"sha256":"232a4c45122a0e17b33bcafa70e313d3cbcbac0436066caf6660d5bfdbc115f8"},{"name":"language_model.model.layers.1.self_attn.k_proj.scales","shape":[2,40],"sha256":"232a4c45122a0e17b33bcafa70e313d3cbcbac0436066caf6660d5bfdbc115f8"},{"name":"language_model.model.layers.1.self_attn.k_proj.weight","shape":[2,320],"sha256":"f7d11c32334014020edcd53479ba08c7235c7779fe7be62af8a25a3bdd56f315"},{"name":"language_model.model.layers.1.self_attn.q_proj.biases","shape":[5,40],"sha256":"3dbadbdc762991a12c532218f3b14845cee793cd01894d9a21b19e91991f8130"},{"name":"language_model.model.layers.1.self_attn.q_proj.scales","shape":[5,40],"sha256":"3dbadbdc762991a12c532218f3b14845cee793cd01894d9a21b19e91991f8130"},{"name":"language_model.model.layers.1.self_attn.q_proj.weight","shape":[5,320],"sha256":"56b2d930469ab03a73e4f24448aa4b9ad2a4b634df5f7498966f43a94ba55e73"},{"name":"language_model.model.layers.1.self_attn.v_proj.biases","shape":[2,40],"sha256":"97d50c02e62d40b6049e08441573ea5c2850acd8175a9e78050360c50fee96e7"},{"name":"language_model.model.layers.1.self_attn.v_proj.scales","shape":[2,40],"sha256":"97d50c02e62d40b6049e08441573ea5c2850acd8175a9e78050360c50fee96e7"},{"name":"language_model.model.layers.1.self_attn.v_proj.weight","shape":[2,320],"sha256":"a8ba87d8b51862aa10ebf5c0f67f22b3f9a11991992e90911be9e707d706635a"}]} {"mask":4,"profile":"normal","fusions":{"language_model.model.layers.1.self_attn.qkv_fused":{"bits":4,"group":64,"splits":[5,7,9]}},"tensors":[{"name":"language_model.model.layers.0.linear_attn.in_proj_a.biases","shape":[1,40],"sha256":"3cc64281a64367b9cd3208a0690290c9f33d3e430f23fdc1629e912e4aebc646"},{"name":"language_model.model.layers.0.linear_attn.in_proj_a.scales","shape":[1,40],"sha256":"3cc64281a64367b9cd3208a0690290c9f33d3e430f23fdc1629e912e4aebc646"},{"name":"language_model.model.layers.0.linear_attn.in_proj_a.weight","shape":[1,320],"sha256":"3954880a15bd19c135403b7908b5dfe89f45914b48d9d7390d5c0b5721d828de"},{"name":"language_model.model.layers.0.linear_attn.in_proj_b.biases","shape":[1,40],"sha256":"0f2a0cf1884b62d37e48589848b2e621fbd9105f9ed398b08cd1a05563e12a6f"},{"name":"language_model.model.layers.0.linear_attn.in_proj_b.scales","shape":[1,40],"sha256":"0f2a0cf1884b62d37e48589848b2e621fbd9105f9ed398b08cd1a05563e12a6f"},{"name":"language_model.model.layers.0.linear_attn.in_proj_b.weight","shape":[1,320],"sha256":"ca845474d18d0fc0ae5d66e884ed3f933b1ee2c0c9af7c3c4b34a1416739639e"},{"name":"language_model.model.layers.0.linear_attn.in_proj_qkv.biases","shape":[5,40],"sha256":"fd85f811b5562e5bae2bc05832f1027a57a234a1df7d9e8f4d99416b931983c9"},{"name":"language_model.model.layers.0.linear_attn.in_proj_qkv.scales","shape":[5,40],"sha256":"fd85f811b5562e5bae2bc05832f1027a57a234a1df7d9e8f4d99416b931983c9"},{"name":"language_model.model.layers.0.linear_attn.in_proj_qkv.weight","shape":[5,320],"sha256":"e7955ba6c02e956caea42526136b0f41c29cc3066eefe8a2c6a71bed9dc9da11"},{"name":"language_model.model.layers.0.linear_attn.in_proj_z.biases","shape":[3,40],"sha256":"243eb49ade9062ffcac3214e640b24995402febcfd7a9aafdae8682d7cbb2cc8"},{"name":"language_model.model.layers.0.linear_attn.in_proj_z.scales","shape":[3,40],"sha256":"243eb49ade9062ffcac3214e640b24995402febcfd7a9aafdae8682d7cbb2cc8"},{"name":"language_model.model.layers.0.linear_attn.in_proj_z.weight","shape":[3,320],"sha256":"3b1cab4c5a92b13a4ca492b882ce350b36866dd6b246172046483aad9d82e357"},{"name":"language_model.model.layers.0.mlp.shared_expert.gate_proj.biases","shape":[4,40],"sha256":"765708c88ebadb8446fe8fac04f627a928498202c1e108a61fe816772e7460f7"},{"name":"language_model.model.layers.0.mlp.shared_expert.gate_proj.scales","shape":[4,40],"sha256":"765708c88ebadb8446fe8fac04f627a928498202c1e108a61fe816772e7460f7"},{"name":"language_model.model.layers.0.mlp.shared_expert.gate_proj.weight","shape":[4,320],"sha256":"102d250f8e3223ff4a07b32ae21da305982eeeafe25d569fb64d408ee205a699"},{"name":"language_model.model.layers.0.mlp.shared_expert.up_proj.biases","shape":[4,40],"sha256":"2f56a66287bb3cba50ca9b47df972ebaa483d83e6a9a74391ed044e54b0002c2"},{"name":"language_model.model.layers.0.mlp.shared_expert.up_proj.scales","shape":[4,40],"sha256":"2f56a66287bb3cba50ca9b47df972ebaa483d83e6a9a74391ed044e54b0002c2"},{"name":"language_model.model.layers.0.mlp.shared_expert.up_proj.weight","shape":[4,320],"sha256":"fafcd9dcd7459bcd6db2929be8a67f3b7ae0140f1446f240c7b83d2713575867"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gate_proj.biases","shape":[2,4,40],"sha256":"80dca76d4ead1253410b9c4352909882e73a90241ef0a0c7b28506f727b13c95"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gate_proj.scales","shape":[2,4,40],"sha256":"80dca76d4ead1253410b9c4352909882e73a90241ef0a0c7b28506f727b13c95"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gate_proj.weight","shape":[2,4,320],"sha256":"7506968c7bf5d98034f3d0d5122e8619b4c17c8938400528ddf94a7cabb7848b"},{"name":"language_model.model.layers.0.mlp.switch_mlp.up_proj.biases","shape":[2,4,40],"sha256":"79d157796e519f46fa701dbe0ae0136cef75da591467b58c6a31b46cdb04d8bb"},{"name":"language_model.model.layers.0.mlp.switch_mlp.up_proj.scales","shape":[2,4,40],"sha256":"79d157796e519f46fa701dbe0ae0136cef75da591467b58c6a31b46cdb04d8bb"},{"name":"language_model.model.layers.0.mlp.switch_mlp.up_proj.weight","shape":[2,4,320],"sha256":"074f9a181bd0604c53d2c54d74c272117fe237cd4b29503a944f95932c444fcb"},{"name":"language_model.model.layers.1.self_attn.qkv_fused.biases","shape":[12,40],"sha256":"cf540511bc52e64fe93a6cbcfc075af24e29f0ae5124482fb982d406bfbcfb7d"},{"name":"language_model.model.layers.1.self_attn.qkv_fused.scales","shape":[12,40],"sha256":"cf540511bc52e64fe93a6cbcfc075af24e29f0ae5124482fb982d406bfbcfb7d"},{"name":"language_model.model.layers.1.self_attn.qkv_fused.weight","shape":[12,320],"sha256":"4200990ccbbcd1a186b7e02ddb7978e75e212d03fd4e219de6ea7e627f12334d"}]} {"mask":5,"profile":"normal","fusions":{"language_model.model.layers.0.mlp.switch_mlp":{"bits":4,"group":64,"splits":[]},"language_model.model.layers.0.mlp.shared_expert":{"bits":4,"group":64,"splits":[]},"language_model.model.layers.1.self_attn.qkv_fused":{"bits":4,"group":64,"splits":[5,7,9]}},"tensors":[{"name":"language_model.model.layers.0.linear_attn.in_proj_a.biases","shape":[1,40],"sha256":"3cc64281a64367b9cd3208a0690290c9f33d3e430f23fdc1629e912e4aebc646"},{"name":"language_model.model.layers.0.linear_attn.in_proj_a.scales","shape":[1,40],"sha256":"3cc64281a64367b9cd3208a0690290c9f33d3e430f23fdc1629e912e4aebc646"},{"name":"language_model.model.layers.0.linear_attn.in_proj_a.weight","shape":[1,320],"sha256":"3954880a15bd19c135403b7908b5dfe89f45914b48d9d7390d5c0b5721d828de"},{"name":"language_model.model.layers.0.linear_attn.in_proj_b.biases","shape":[1,40],"sha256":"0f2a0cf1884b62d37e48589848b2e621fbd9105f9ed398b08cd1a05563e12a6f"},{"name":"language_model.model.layers.0.linear_attn.in_proj_b.scales","shape":[1,40],"sha256":"0f2a0cf1884b62d37e48589848b2e621fbd9105f9ed398b08cd1a05563e12a6f"},{"name":"language_model.model.layers.0.linear_attn.in_proj_b.weight","shape":[1,320],"sha256":"ca845474d18d0fc0ae5d66e884ed3f933b1ee2c0c9af7c3c4b34a1416739639e"},{"name":"language_model.model.layers.0.linear_attn.in_proj_qkv.biases","shape":[5,40],"sha256":"fd85f811b5562e5bae2bc05832f1027a57a234a1df7d9e8f4d99416b931983c9"},{"name":"language_model.model.layers.0.linear_attn.in_proj_qkv.scales","shape":[5,40],"sha256":"fd85f811b5562e5bae2bc05832f1027a57a234a1df7d9e8f4d99416b931983c9"},{"name":"language_model.model.layers.0.linear_attn.in_proj_qkv.weight","shape":[5,320],"sha256":"e7955ba6c02e956caea42526136b0f41c29cc3066eefe8a2c6a71bed9dc9da11"},{"name":"language_model.model.layers.0.linear_attn.in_proj_z.biases","shape":[3,40],"sha256":"243eb49ade9062ffcac3214e640b24995402febcfd7a9aafdae8682d7cbb2cc8"},{"name":"language_model.model.layers.0.linear_attn.in_proj_z.scales","shape":[3,40],"sha256":"243eb49ade9062ffcac3214e640b24995402febcfd7a9aafdae8682d7cbb2cc8"},{"name":"language_model.model.layers.0.linear_attn.in_proj_z.weight","shape":[3,320],"sha256":"3b1cab4c5a92b13a4ca492b882ce350b36866dd6b246172046483aad9d82e357"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_biases","shape":[8,40],"sha256":"ccc740c7994dd6367548fb81759a1916e3ed492b6c137b1337cdabe3ca453332"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_scales","shape":[8,40],"sha256":"ccc740c7994dd6367548fb81759a1916e3ed492b6c137b1337cdabe3ca453332"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_weight","shape":[8,320],"sha256":"393fc4f46b05750db834b2a79ccbeef674d7b073a73edd51e67510e177beccb2"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_biases","shape":[2,8,40],"sha256":"592f72b7046080a0c440832a296bf061ee56d889b0e75f3308774c1d7cfa1f99"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_scales","shape":[2,8,40],"sha256":"592f72b7046080a0c440832a296bf061ee56d889b0e75f3308774c1d7cfa1f99"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_weight","shape":[2,8,320],"sha256":"c59e7fcfc36b3d60bc29d59592c841efaf9434de2379190942f68625636abf17"},{"name":"language_model.model.layers.1.self_attn.qkv_fused.biases","shape":[12,40],"sha256":"cf540511bc52e64fe93a6cbcfc075af24e29f0ae5124482fb982d406bfbcfb7d"},{"name":"language_model.model.layers.1.self_attn.qkv_fused.scales","shape":[12,40],"sha256":"cf540511bc52e64fe93a6cbcfc075af24e29f0ae5124482fb982d406bfbcfb7d"},{"name":"language_model.model.layers.1.self_attn.qkv_fused.weight","shape":[12,320],"sha256":"4200990ccbbcd1a186b7e02ddb7978e75e212d03fd4e219de6ea7e627f12334d"}]} {"mask":6,"profile":"normal","fusions":{"language_model.model.layers.0.linear_attn.in_proj_fused":{"bits":4,"group":64,"splits":[5,8,9]},"language_model.model.layers.1.self_attn.qkv_fused":{"bits":4,"group":64,"splits":[5,7,9]}},"tensors":[{"name":"language_model.model.layers.0.linear_attn.in_proj_fused.biases","shape":[10,40],"sha256":"5a2483da6433a2e53182a5f3acdfb6f6ea3646947527a87211354bbcee15dfd5"},{"name":"language_model.model.layers.0.linear_attn.in_proj_fused.scales","shape":[10,40],"sha256":"5a2483da6433a2e53182a5f3acdfb6f6ea3646947527a87211354bbcee15dfd5"},{"name":"language_model.model.layers.0.linear_attn.in_proj_fused.weight","shape":[10,320],"sha256":"84703ee405db83d0cd5f823950a6f244a727432729299a4138e12a3c7f244335"},{"name":"language_model.model.layers.0.mlp.shared_expert.gate_proj.biases","shape":[4,40],"sha256":"765708c88ebadb8446fe8fac04f627a928498202c1e108a61fe816772e7460f7"},{"name":"language_model.model.layers.0.mlp.shared_expert.gate_proj.scales","shape":[4,40],"sha256":"765708c88ebadb8446fe8fac04f627a928498202c1e108a61fe816772e7460f7"},{"name":"language_model.model.layers.0.mlp.shared_expert.gate_proj.weight","shape":[4,320],"sha256":"102d250f8e3223ff4a07b32ae21da305982eeeafe25d569fb64d408ee205a699"},{"name":"language_model.model.layers.0.mlp.shared_expert.up_proj.biases","shape":[4,40],"sha256":"2f56a66287bb3cba50ca9b47df972ebaa483d83e6a9a74391ed044e54b0002c2"},{"name":"language_model.model.layers.0.mlp.shared_expert.up_proj.scales","shape":[4,40],"sha256":"2f56a66287bb3cba50ca9b47df972ebaa483d83e6a9a74391ed044e54b0002c2"},{"name":"language_model.model.layers.0.mlp.shared_expert.up_proj.weight","shape":[4,320],"sha256":"fafcd9dcd7459bcd6db2929be8a67f3b7ae0140f1446f240c7b83d2713575867"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gate_proj.biases","shape":[2,4,40],"sha256":"80dca76d4ead1253410b9c4352909882e73a90241ef0a0c7b28506f727b13c95"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gate_proj.scales","shape":[2,4,40],"sha256":"80dca76d4ead1253410b9c4352909882e73a90241ef0a0c7b28506f727b13c95"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gate_proj.weight","shape":[2,4,320],"sha256":"7506968c7bf5d98034f3d0d5122e8619b4c17c8938400528ddf94a7cabb7848b"},{"name":"language_model.model.layers.0.mlp.switch_mlp.up_proj.biases","shape":[2,4,40],"sha256":"79d157796e519f46fa701dbe0ae0136cef75da591467b58c6a31b46cdb04d8bb"},{"name":"language_model.model.layers.0.mlp.switch_mlp.up_proj.scales","shape":[2,4,40],"sha256":"79d157796e519f46fa701dbe0ae0136cef75da591467b58c6a31b46cdb04d8bb"},{"name":"language_model.model.layers.0.mlp.switch_mlp.up_proj.weight","shape":[2,4,320],"sha256":"074f9a181bd0604c53d2c54d74c272117fe237cd4b29503a944f95932c444fcb"},{"name":"language_model.model.layers.1.self_attn.qkv_fused.biases","shape":[12,40],"sha256":"cf540511bc52e64fe93a6cbcfc075af24e29f0ae5124482fb982d406bfbcfb7d"},{"name":"language_model.model.layers.1.self_attn.qkv_fused.scales","shape":[12,40],"sha256":"cf540511bc52e64fe93a6cbcfc075af24e29f0ae5124482fb982d406bfbcfb7d"},{"name":"language_model.model.layers.1.self_attn.qkv_fused.weight","shape":[12,320],"sha256":"4200990ccbbcd1a186b7e02ddb7978e75e212d03fd4e219de6ea7e627f12334d"}]} {"mask":7,"profile":"normal","fusions":{"language_model.model.layers.0.mlp.switch_mlp":{"bits":4,"group":64,"splits":[]},"language_model.model.layers.0.mlp.shared_expert":{"bits":4,"group":64,"splits":[]},"language_model.model.layers.0.linear_attn.in_proj_fused":{"bits":4,"group":64,"splits":[5,8,9]},"language_model.model.layers.1.self_attn.qkv_fused":{"bits":4,"group":64,"splits":[5,7,9]}},"tensors":[{"name":"language_model.model.layers.0.linear_attn.in_proj_fused.biases","shape":[10,40],"sha256":"5a2483da6433a2e53182a5f3acdfb6f6ea3646947527a87211354bbcee15dfd5"},{"name":"language_model.model.layers.0.linear_attn.in_proj_fused.scales","shape":[10,40],"sha256":"5a2483da6433a2e53182a5f3acdfb6f6ea3646947527a87211354bbcee15dfd5"},{"name":"language_model.model.layers.0.linear_attn.in_proj_fused.weight","shape":[10,320],"sha256":"84703ee405db83d0cd5f823950a6f244a727432729299a4138e12a3c7f244335"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_biases","shape":[8,40],"sha256":"ccc740c7994dd6367548fb81759a1916e3ed492b6c137b1337cdabe3ca453332"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_scales","shape":[8,40],"sha256":"ccc740c7994dd6367548fb81759a1916e3ed492b6c137b1337cdabe3ca453332"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_weight","shape":[8,320],"sha256":"393fc4f46b05750db834b2a79ccbeef674d7b073a73edd51e67510e177beccb2"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_biases","shape":[2,8,40],"sha256":"592f72b7046080a0c440832a296bf061ee56d889b0e75f3308774c1d7cfa1f99"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_scales","shape":[2,8,40],"sha256":"592f72b7046080a0c440832a296bf061ee56d889b0e75f3308774c1d7cfa1f99"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_weight","shape":[2,8,320],"sha256":"c59e7fcfc36b3d60bc29d59592c841efaf9434de2379190942f68625636abf17"},{"name":"language_model.model.layers.1.self_attn.qkv_fused.biases","shape":[12,40],"sha256":"cf540511bc52e64fe93a6cbcfc075af24e29f0ae5124482fb982d406bfbcfb7d"},{"name":"language_model.model.layers.1.self_attn.qkv_fused.scales","shape":[12,40],"sha256":"cf540511bc52e64fe93a6cbcfc075af24e29f0ae5124482fb982d406bfbcfb7d"},{"name":"language_model.model.layers.1.self_attn.qkv_fused.weight","shape":[12,320],"sha256":"4200990ccbbcd1a186b7e02ddb7978e75e212d03fd4e219de6ea7e627f12334d"}]} {"mask":7,"profile":"qsa_bias","fusions":{"language_model.model.layers.0.mlp.switch_mlp":{"bits":4,"group":64,"splits":[]},"language_model.model.layers.0.mlp.shared_expert":{"bits":4,"group":64,"splits":[]},"language_model.model.layers.0.linear_attn.in_proj_fused":{"bits":4,"group":64,"splits":[5,8,9]}},"tensors":[{"name":"language_model.model.layers.0.linear_attn.in_proj_fused.biases","shape":[10,40],"sha256":"5a2483da6433a2e53182a5f3acdfb6f6ea3646947527a87211354bbcee15dfd5"},{"name":"language_model.model.layers.0.linear_attn.in_proj_fused.scales","shape":[10,40],"sha256":"5a2483da6433a2e53182a5f3acdfb6f6ea3646947527a87211354bbcee15dfd5"},{"name":"language_model.model.layers.0.linear_attn.in_proj_fused.weight","shape":[10,320],"sha256":"84703ee405db83d0cd5f823950a6f244a727432729299a4138e12a3c7f244335"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_biases","shape":[8,40],"sha256":"ccc740c7994dd6367548fb81759a1916e3ed492b6c137b1337cdabe3ca453332"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_scales","shape":[8,40],"sha256":"ccc740c7994dd6367548fb81759a1916e3ed492b6c137b1337cdabe3ca453332"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_weight","shape":[8,320],"sha256":"393fc4f46b05750db834b2a79ccbeef674d7b073a73edd51e67510e177beccb2"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_biases","shape":[2,8,40],"sha256":"592f72b7046080a0c440832a296bf061ee56d889b0e75f3308774c1d7cfa1f99"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_scales","shape":[2,8,40],"sha256":"592f72b7046080a0c440832a296bf061ee56d889b0e75f3308774c1d7cfa1f99"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_weight","shape":[2,8,320],"sha256":"c59e7fcfc36b3d60bc29d59592c841efaf9434de2379190942f68625636abf17"},{"name":"language_model.model.layers.1.self_attn.indexer.index_qk_proj.biases","shape":[3,40],"sha256":"95f422d87acf791e984abd847ed88b7e7b0ea2d68c1551493460ca6ed70b1a04"},{"name":"language_model.model.layers.1.self_attn.indexer.index_qk_proj.scales","shape":[3,40],"sha256":"95f422d87acf791e984abd847ed88b7e7b0ea2d68c1551493460ca6ed70b1a04"},{"name":"language_model.model.layers.1.self_attn.indexer.index_qk_proj.weight","shape":[3,320],"sha256":"3de0965101509f3b7448fe48331a3d5cc03383edac337d98597a5c122046b50d"},{"name":"language_model.model.layers.1.self_attn.k_proj.biases","shape":[2,40],"sha256":"232a4c45122a0e17b33bcafa70e313d3cbcbac0436066caf6660d5bfdbc115f8"},{"name":"language_model.model.layers.1.self_attn.k_proj.scales","shape":[2,40],"sha256":"232a4c45122a0e17b33bcafa70e313d3cbcbac0436066caf6660d5bfdbc115f8"},{"name":"language_model.model.layers.1.self_attn.k_proj.weight","shape":[2,320],"sha256":"f7d11c32334014020edcd53479ba08c7235c7779fe7be62af8a25a3bdd56f315"},{"name":"language_model.model.layers.1.self_attn.q_proj.bias","shape":[5],"sha256":"de47c9b27eb8d300dbb5f2c353e632c393262cf06340c4fa7f1b40c4cbd36f90"},{"name":"language_model.model.layers.1.self_attn.q_proj.biases","shape":[5,40],"sha256":"3dbadbdc762991a12c532218f3b14845cee793cd01894d9a21b19e91991f8130"},{"name":"language_model.model.layers.1.self_attn.q_proj.scales","shape":[5,40],"sha256":"3dbadbdc762991a12c532218f3b14845cee793cd01894d9a21b19e91991f8130"},{"name":"language_model.model.layers.1.self_attn.q_proj.weight","shape":[5,320],"sha256":"56b2d930469ab03a73e4f24448aa4b9ad2a4b634df5f7498966f43a94ba55e73"},{"name":"language_model.model.layers.1.self_attn.v_proj.biases","shape":[2,40],"sha256":"97d50c02e62d40b6049e08441573ea5c2850acd8175a9e78050360c50fee96e7"},{"name":"language_model.model.layers.1.self_attn.v_proj.scales","shape":[2,40],"sha256":"97d50c02e62d40b6049e08441573ea5c2850acd8175a9e78050360c50fee96e7"},{"name":"language_model.model.layers.1.self_attn.v_proj.weight","shape":[2,320],"sha256":"a8ba87d8b51862aa10ebf5c0f67f22b3f9a11991992e90911be9e707d706635a"}]} {"mask":7,"profile":"indexer_mixed","fusions":{"language_model.model.layers.0.mlp.switch_mlp":{"bits":4,"group":64,"splits":[]},"language_model.model.layers.0.mlp.shared_expert":{"bits":4,"group":64,"splits":[]},"language_model.model.layers.0.linear_attn.in_proj_fused":{"bits":4,"group":64,"splits":[5,8,9]},"language_model.model.layers.1.self_attn.qkv_fused":{"bits":4,"group":64,"splits":[5,7]}},"tensors":[{"name":"language_model.model.layers.0.linear_attn.in_proj_fused.biases","shape":[10,40],"sha256":"5a2483da6433a2e53182a5f3acdfb6f6ea3646947527a87211354bbcee15dfd5"},{"name":"language_model.model.layers.0.linear_attn.in_proj_fused.scales","shape":[10,40],"sha256":"5a2483da6433a2e53182a5f3acdfb6f6ea3646947527a87211354bbcee15dfd5"},{"name":"language_model.model.layers.0.linear_attn.in_proj_fused.weight","shape":[10,320],"sha256":"84703ee405db83d0cd5f823950a6f244a727432729299a4138e12a3c7f244335"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_biases","shape":[8,40],"sha256":"ccc740c7994dd6367548fb81759a1916e3ed492b6c137b1337cdabe3ca453332"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_scales","shape":[8,40],"sha256":"ccc740c7994dd6367548fb81759a1916e3ed492b6c137b1337cdabe3ca453332"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_weight","shape":[8,320],"sha256":"393fc4f46b05750db834b2a79ccbeef674d7b073a73edd51e67510e177beccb2"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_biases","shape":[2,8,40],"sha256":"592f72b7046080a0c440832a296bf061ee56d889b0e75f3308774c1d7cfa1f99"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_scales","shape":[2,8,40],"sha256":"592f72b7046080a0c440832a296bf061ee56d889b0e75f3308774c1d7cfa1f99"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_weight","shape":[2,8,320],"sha256":"c59e7fcfc36b3d60bc29d59592c841efaf9434de2379190942f68625636abf17"},{"name":"language_model.model.layers.1.self_attn.indexer.index_qk_proj.biases","shape":[3,40],"sha256":"95f422d87acf791e984abd847ed88b7e7b0ea2d68c1551493460ca6ed70b1a04"},{"name":"language_model.model.layers.1.self_attn.indexer.index_qk_proj.scales","shape":[3,40],"sha256":"95f422d87acf791e984abd847ed88b7e7b0ea2d68c1551493460ca6ed70b1a04"},{"name":"language_model.model.layers.1.self_attn.indexer.index_qk_proj.weight","shape":[3,640],"sha256":"5d66d71c3d3e2ca1f88145ba9c56d9e36f01a60b010f3968d54ba6a694fcfb59"},{"name":"language_model.model.layers.1.self_attn.qkv_fused.biases","shape":[9,40],"sha256":"7842994a9311147878aa9815eeab8feb8ce0958cd893b576ff3c3c9895ec02db"},{"name":"language_model.model.layers.1.self_attn.qkv_fused.scales","shape":[9,40],"sha256":"7842994a9311147878aa9815eeab8feb8ce0958cd893b576ff3c3c9895ec02db"},{"name":"language_model.model.layers.1.self_attn.qkv_fused.weight","shape":[9,320],"sha256":"cd9c264e5527c297097b2e7cfb16fbeb5069092138cb60ac47cc7b85478a7e4d"}]} {"mask":7,"profile":"qkv_mixed","fusions":{"language_model.model.layers.0.mlp.switch_mlp":{"bits":4,"group":64,"splits":[]},"language_model.model.layers.0.mlp.shared_expert":{"bits":4,"group":64,"splits":[]},"language_model.model.layers.0.linear_attn.in_proj_fused":{"bits":4,"group":64,"splits":[5,8,9]}},"tensors":[{"name":"language_model.model.layers.0.linear_attn.in_proj_fused.biases","shape":[10,40],"sha256":"5a2483da6433a2e53182a5f3acdfb6f6ea3646947527a87211354bbcee15dfd5"},{"name":"language_model.model.layers.0.linear_attn.in_proj_fused.scales","shape":[10,40],"sha256":"5a2483da6433a2e53182a5f3acdfb6f6ea3646947527a87211354bbcee15dfd5"},{"name":"language_model.model.layers.0.linear_attn.in_proj_fused.weight","shape":[10,320],"sha256":"84703ee405db83d0cd5f823950a6f244a727432729299a4138e12a3c7f244335"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_biases","shape":[8,40],"sha256":"ccc740c7994dd6367548fb81759a1916e3ed492b6c137b1337cdabe3ca453332"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_scales","shape":[8,40],"sha256":"ccc740c7994dd6367548fb81759a1916e3ed492b6c137b1337cdabe3ca453332"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_weight","shape":[8,320],"sha256":"393fc4f46b05750db834b2a79ccbeef674d7b073a73edd51e67510e177beccb2"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_biases","shape":[2,8,40],"sha256":"592f72b7046080a0c440832a296bf061ee56d889b0e75f3308774c1d7cfa1f99"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_scales","shape":[2,8,40],"sha256":"592f72b7046080a0c440832a296bf061ee56d889b0e75f3308774c1d7cfa1f99"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_weight","shape":[2,8,320],"sha256":"c59e7fcfc36b3d60bc29d59592c841efaf9434de2379190942f68625636abf17"},{"name":"language_model.model.layers.1.self_attn.indexer.index_qk_proj.biases","shape":[3,40],"sha256":"95f422d87acf791e984abd847ed88b7e7b0ea2d68c1551493460ca6ed70b1a04"},{"name":"language_model.model.layers.1.self_attn.indexer.index_qk_proj.scales","shape":[3,40],"sha256":"95f422d87acf791e984abd847ed88b7e7b0ea2d68c1551493460ca6ed70b1a04"},{"name":"language_model.model.layers.1.self_attn.indexer.index_qk_proj.weight","shape":[3,320],"sha256":"3de0965101509f3b7448fe48331a3d5cc03383edac337d98597a5c122046b50d"},{"name":"language_model.model.layers.1.self_attn.k_proj.biases","shape":[2,40],"sha256":"232a4c45122a0e17b33bcafa70e313d3cbcbac0436066caf6660d5bfdbc115f8"},{"name":"language_model.model.layers.1.self_attn.k_proj.scales","shape":[2,40],"sha256":"232a4c45122a0e17b33bcafa70e313d3cbcbac0436066caf6660d5bfdbc115f8"},{"name":"language_model.model.layers.1.self_attn.k_proj.weight","shape":[2,640],"sha256":"620d3bcfabb09531befc6d79df95d7fcd26f5342f1af24289302e5d9029358be"},{"name":"language_model.model.layers.1.self_attn.q_proj.biases","shape":[5,40],"sha256":"3dbadbdc762991a12c532218f3b14845cee793cd01894d9a21b19e91991f8130"},{"name":"language_model.model.layers.1.self_attn.q_proj.scales","shape":[5,40],"sha256":"3dbadbdc762991a12c532218f3b14845cee793cd01894d9a21b19e91991f8130"},{"name":"language_model.model.layers.1.self_attn.q_proj.weight","shape":[5,320],"sha256":"56b2d930469ab03a73e4f24448aa4b9ad2a4b634df5f7498966f43a94ba55e73"},{"name":"language_model.model.layers.1.self_attn.v_proj.biases","shape":[2,40],"sha256":"97d50c02e62d40b6049e08441573ea5c2850acd8175a9e78050360c50fee96e7"},{"name":"language_model.model.layers.1.self_attn.v_proj.scales","shape":[2,40],"sha256":"97d50c02e62d40b6049e08441573ea5c2850acd8175a9e78050360c50fee96e7"},{"name":"language_model.model.layers.1.self_attn.v_proj.weight","shape":[2,320],"sha256":"a8ba87d8b51862aa10ebf5c0f67f22b3f9a11991992e90911be9e707d706635a"}]} {"mask":7,"profile":"gdn_mixed","fusions":{"language_model.model.layers.0.mlp.switch_mlp":{"bits":4,"group":64,"splits":[]},"language_model.model.layers.0.mlp.shared_expert":{"bits":4,"group":64,"splits":[]},"language_model.model.layers.1.self_attn.qkv_fused":{"bits":4,"group":64,"splits":[5,7,9]}},"tensors":[{"name":"language_model.model.layers.0.linear_attn.in_proj_a.biases","shape":[1,40],"sha256":"3cc64281a64367b9cd3208a0690290c9f33d3e430f23fdc1629e912e4aebc646"},{"name":"language_model.model.layers.0.linear_attn.in_proj_a.scales","shape":[1,40],"sha256":"3cc64281a64367b9cd3208a0690290c9f33d3e430f23fdc1629e912e4aebc646"},{"name":"language_model.model.layers.0.linear_attn.in_proj_a.weight","shape":[1,640],"sha256":"5960d935462afb14142cd594f11be0ee621a7d6ca32a681a0702e5e3841a27b9"},{"name":"language_model.model.layers.0.linear_attn.in_proj_b.biases","shape":[1,40],"sha256":"0f2a0cf1884b62d37e48589848b2e621fbd9105f9ed398b08cd1a05563e12a6f"},{"name":"language_model.model.layers.0.linear_attn.in_proj_b.scales","shape":[1,40],"sha256":"0f2a0cf1884b62d37e48589848b2e621fbd9105f9ed398b08cd1a05563e12a6f"},{"name":"language_model.model.layers.0.linear_attn.in_proj_b.weight","shape":[1,320],"sha256":"ca845474d18d0fc0ae5d66e884ed3f933b1ee2c0c9af7c3c4b34a1416739639e"},{"name":"language_model.model.layers.0.linear_attn.in_proj_qkv.biases","shape":[5,40],"sha256":"fd85f811b5562e5bae2bc05832f1027a57a234a1df7d9e8f4d99416b931983c9"},{"name":"language_model.model.layers.0.linear_attn.in_proj_qkv.scales","shape":[5,40],"sha256":"fd85f811b5562e5bae2bc05832f1027a57a234a1df7d9e8f4d99416b931983c9"},{"name":"language_model.model.layers.0.linear_attn.in_proj_qkv.weight","shape":[5,320],"sha256":"e7955ba6c02e956caea42526136b0f41c29cc3066eefe8a2c6a71bed9dc9da11"},{"name":"language_model.model.layers.0.linear_attn.in_proj_z.biases","shape":[3,40],"sha256":"243eb49ade9062ffcac3214e640b24995402febcfd7a9aafdae8682d7cbb2cc8"},{"name":"language_model.model.layers.0.linear_attn.in_proj_z.scales","shape":[3,40],"sha256":"243eb49ade9062ffcac3214e640b24995402febcfd7a9aafdae8682d7cbb2cc8"},{"name":"language_model.model.layers.0.linear_attn.in_proj_z.weight","shape":[3,320],"sha256":"3b1cab4c5a92b13a4ca492b882ce350b36866dd6b246172046483aad9d82e357"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_biases","shape":[8,40],"sha256":"ccc740c7994dd6367548fb81759a1916e3ed492b6c137b1337cdabe3ca453332"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_scales","shape":[8,40],"sha256":"ccc740c7994dd6367548fb81759a1916e3ed492b6c137b1337cdabe3ca453332"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_weight","shape":[8,320],"sha256":"393fc4f46b05750db834b2a79ccbeef674d7b073a73edd51e67510e177beccb2"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_biases","shape":[2,8,40],"sha256":"592f72b7046080a0c440832a296bf061ee56d889b0e75f3308774c1d7cfa1f99"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_scales","shape":[2,8,40],"sha256":"592f72b7046080a0c440832a296bf061ee56d889b0e75f3308774c1d7cfa1f99"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_weight","shape":[2,8,320],"sha256":"c59e7fcfc36b3d60bc29d59592c841efaf9434de2379190942f68625636abf17"},{"name":"language_model.model.layers.1.self_attn.qkv_fused.biases","shape":[12,40],"sha256":"cf540511bc52e64fe93a6cbcfc075af24e29f0ae5124482fb982d406bfbcfb7d"},{"name":"language_model.model.layers.1.self_attn.qkv_fused.scales","shape":[12,40],"sha256":"cf540511bc52e64fe93a6cbcfc075af24e29f0ae5124482fb982d406bfbcfb7d"},{"name":"language_model.model.layers.1.self_attn.qkv_fused.weight","shape":[12,320],"sha256":"4200990ccbbcd1a186b7e02ddb7978e75e212d03fd4e219de6ea7e627f12334d"}]} {"mask":7,"profile":"gdn_missing","fusions":{"language_model.model.layers.0.mlp.switch_mlp":{"bits":4,"group":64,"splits":[]},"language_model.model.layers.0.mlp.shared_expert":{"bits":4,"group":64,"splits":[]},"language_model.model.layers.1.self_attn.qkv_fused":{"bits":4,"group":64,"splits":[5,7,9]}},"tensors":[{"name":"language_model.model.layers.0.linear_attn.in_proj_a.scales","shape":[1,40],"sha256":"3cc64281a64367b9cd3208a0690290c9f33d3e430f23fdc1629e912e4aebc646"},{"name":"language_model.model.layers.0.linear_attn.in_proj_a.weight","shape":[1,320],"sha256":"3954880a15bd19c135403b7908b5dfe89f45914b48d9d7390d5c0b5721d828de"},{"name":"language_model.model.layers.0.linear_attn.in_proj_b.biases","shape":[1,40],"sha256":"0f2a0cf1884b62d37e48589848b2e621fbd9105f9ed398b08cd1a05563e12a6f"},{"name":"language_model.model.layers.0.linear_attn.in_proj_b.scales","shape":[1,40],"sha256":"0f2a0cf1884b62d37e48589848b2e621fbd9105f9ed398b08cd1a05563e12a6f"},{"name":"language_model.model.layers.0.linear_attn.in_proj_b.weight","shape":[1,320],"sha256":"ca845474d18d0fc0ae5d66e884ed3f933b1ee2c0c9af7c3c4b34a1416739639e"},{"name":"language_model.model.layers.0.linear_attn.in_proj_qkv.biases","shape":[5,40],"sha256":"fd85f811b5562e5bae2bc05832f1027a57a234a1df7d9e8f4d99416b931983c9"},{"name":"language_model.model.layers.0.linear_attn.in_proj_qkv.scales","shape":[5,40],"sha256":"fd85f811b5562e5bae2bc05832f1027a57a234a1df7d9e8f4d99416b931983c9"},{"name":"language_model.model.layers.0.linear_attn.in_proj_qkv.weight","shape":[5,320],"sha256":"e7955ba6c02e956caea42526136b0f41c29cc3066eefe8a2c6a71bed9dc9da11"},{"name":"language_model.model.layers.0.linear_attn.in_proj_z.biases","shape":[3,40],"sha256":"243eb49ade9062ffcac3214e640b24995402febcfd7a9aafdae8682d7cbb2cc8"},{"name":"language_model.model.layers.0.linear_attn.in_proj_z.scales","shape":[3,40],"sha256":"243eb49ade9062ffcac3214e640b24995402febcfd7a9aafdae8682d7cbb2cc8"},{"name":"language_model.model.layers.0.linear_attn.in_proj_z.weight","shape":[3,320],"sha256":"3b1cab4c5a92b13a4ca492b882ce350b36866dd6b246172046483aad9d82e357"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_biases","shape":[8,40],"sha256":"ccc740c7994dd6367548fb81759a1916e3ed492b6c137b1337cdabe3ca453332"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_scales","shape":[8,40],"sha256":"ccc740c7994dd6367548fb81759a1916e3ed492b6c137b1337cdabe3ca453332"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_weight","shape":[8,320],"sha256":"393fc4f46b05750db834b2a79ccbeef674d7b073a73edd51e67510e177beccb2"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_biases","shape":[2,8,40],"sha256":"592f72b7046080a0c440832a296bf061ee56d889b0e75f3308774c1d7cfa1f99"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_scales","shape":[2,8,40],"sha256":"592f72b7046080a0c440832a296bf061ee56d889b0e75f3308774c1d7cfa1f99"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_weight","shape":[2,8,320],"sha256":"c59e7fcfc36b3d60bc29d59592c841efaf9434de2379190942f68625636abf17"},{"name":"language_model.model.layers.1.self_attn.qkv_fused.biases","shape":[12,40],"sha256":"cf540511bc52e64fe93a6cbcfc075af24e29f0ae5124482fb982d406bfbcfb7d"},{"name":"language_model.model.layers.1.self_attn.qkv_fused.scales","shape":[12,40],"sha256":"cf540511bc52e64fe93a6cbcfc075af24e29f0ae5124482fb982d406bfbcfb7d"},{"name":"language_model.model.layers.1.self_attn.qkv_fused.weight","shape":[12,320],"sha256":"4200990ccbbcd1a186b7e02ddb7978e75e212d03fd4e219de6ea7e627f12334d"}]} {"mask":7,"profile":"indexer_missing","fusions":{"language_model.model.layers.0.mlp.switch_mlp":{"bits":4,"group":64,"splits":[]},"language_model.model.layers.0.mlp.shared_expert":{"bits":4,"group":64,"splits":[]},"language_model.model.layers.0.linear_attn.in_proj_fused":{"bits":4,"group":64,"splits":[5,8,9]},"language_model.model.layers.1.self_attn.qkv_fused":{"bits":4,"group":64,"splits":[5,7]}},"tensors":[{"name":"language_model.model.layers.0.linear_attn.in_proj_fused.biases","shape":[10,40],"sha256":"5a2483da6433a2e53182a5f3acdfb6f6ea3646947527a87211354bbcee15dfd5"},{"name":"language_model.model.layers.0.linear_attn.in_proj_fused.scales","shape":[10,40],"sha256":"5a2483da6433a2e53182a5f3acdfb6f6ea3646947527a87211354bbcee15dfd5"},{"name":"language_model.model.layers.0.linear_attn.in_proj_fused.weight","shape":[10,320],"sha256":"84703ee405db83d0cd5f823950a6f244a727432729299a4138e12a3c7f244335"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_biases","shape":[8,40],"sha256":"ccc740c7994dd6367548fb81759a1916e3ed492b6c137b1337cdabe3ca453332"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_scales","shape":[8,40],"sha256":"ccc740c7994dd6367548fb81759a1916e3ed492b6c137b1337cdabe3ca453332"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_weight","shape":[8,320],"sha256":"393fc4f46b05750db834b2a79ccbeef674d7b073a73edd51e67510e177beccb2"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_biases","shape":[2,8,40],"sha256":"592f72b7046080a0c440832a296bf061ee56d889b0e75f3308774c1d7cfa1f99"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_scales","shape":[2,8,40],"sha256":"592f72b7046080a0c440832a296bf061ee56d889b0e75f3308774c1d7cfa1f99"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_weight","shape":[2,8,320],"sha256":"c59e7fcfc36b3d60bc29d59592c841efaf9434de2379190942f68625636abf17"},{"name":"language_model.model.layers.1.self_attn.qkv_fused.biases","shape":[9,40],"sha256":"7842994a9311147878aa9815eeab8feb8ce0958cd893b576ff3c3c9895ec02db"},{"name":"language_model.model.layers.1.self_attn.qkv_fused.scales","shape":[9,40],"sha256":"7842994a9311147878aa9815eeab8feb8ce0958cd893b576ff3c3c9895ec02db"},{"name":"language_model.model.layers.1.self_attn.qkv_fused.weight","shape":[9,320],"sha256":"cd9c264e5527c297097b2e7cfb16fbeb5069092138cb60ac47cc7b85478a7e4d"}]} {"mask":7,"profile":"no_indexer","fusions":{"language_model.model.layers.0.mlp.switch_mlp":{"bits":4,"group":64,"splits":[]},"language_model.model.layers.0.mlp.shared_expert":{"bits":4,"group":64,"splits":[]},"language_model.model.layers.0.linear_attn.in_proj_fused":{"bits":4,"group":64,"splits":[5,8,9]}},"tensors":[{"name":"language_model.model.layers.0.linear_attn.in_proj_fused.biases","shape":[10,40],"sha256":"5a2483da6433a2e53182a5f3acdfb6f6ea3646947527a87211354bbcee15dfd5"},{"name":"language_model.model.layers.0.linear_attn.in_proj_fused.scales","shape":[10,40],"sha256":"5a2483da6433a2e53182a5f3acdfb6f6ea3646947527a87211354bbcee15dfd5"},{"name":"language_model.model.layers.0.linear_attn.in_proj_fused.weight","shape":[10,320],"sha256":"84703ee405db83d0cd5f823950a6f244a727432729299a4138e12a3c7f244335"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_biases","shape":[8,40],"sha256":"ccc740c7994dd6367548fb81759a1916e3ed492b6c137b1337cdabe3ca453332"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_scales","shape":[8,40],"sha256":"ccc740c7994dd6367548fb81759a1916e3ed492b6c137b1337cdabe3ca453332"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_weight","shape":[8,320],"sha256":"393fc4f46b05750db834b2a79ccbeef674d7b073a73edd51e67510e177beccb2"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_biases","shape":[2,8,40],"sha256":"592f72b7046080a0c440832a296bf061ee56d889b0e75f3308774c1d7cfa1f99"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_scales","shape":[2,8,40],"sha256":"592f72b7046080a0c440832a296bf061ee56d889b0e75f3308774c1d7cfa1f99"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_weight","shape":[2,8,320],"sha256":"c59e7fcfc36b3d60bc29d59592c841efaf9434de2379190942f68625636abf17"},{"name":"language_model.model.layers.1.self_attn.indexer.index_qk_proj.biases","shape":[3,40],"sha256":"95f422d87acf791e984abd847ed88b7e7b0ea2d68c1551493460ca6ed70b1a04"},{"name":"language_model.model.layers.1.self_attn.indexer.index_qk_proj.scales","shape":[3,40],"sha256":"95f422d87acf791e984abd847ed88b7e7b0ea2d68c1551493460ca6ed70b1a04"},{"name":"language_model.model.layers.1.self_attn.indexer.index_qk_proj.weight","shape":[3,320],"sha256":"3de0965101509f3b7448fe48331a3d5cc03383edac337d98597a5c122046b50d"},{"name":"language_model.model.layers.1.self_attn.k_proj.biases","shape":[2,40],"sha256":"232a4c45122a0e17b33bcafa70e313d3cbcbac0436066caf6660d5bfdbc115f8"},{"name":"language_model.model.layers.1.self_attn.k_proj.scales","shape":[2,40],"sha256":"232a4c45122a0e17b33bcafa70e313d3cbcbac0436066caf6660d5bfdbc115f8"},{"name":"language_model.model.layers.1.self_attn.k_proj.weight","shape":[2,320],"sha256":"f7d11c32334014020edcd53479ba08c7235c7779fe7be62af8a25a3bdd56f315"},{"name":"language_model.model.layers.1.self_attn.q_proj.biases","shape":[5,40],"sha256":"3dbadbdc762991a12c532218f3b14845cee793cd01894d9a21b19e91991f8130"},{"name":"language_model.model.layers.1.self_attn.q_proj.scales","shape":[5,40],"sha256":"3dbadbdc762991a12c532218f3b14845cee793cd01894d9a21b19e91991f8130"},{"name":"language_model.model.layers.1.self_attn.q_proj.weight","shape":[5,320],"sha256":"56b2d930469ab03a73e4f24448aa4b9ad2a4b634df5f7498966f43a94ba55e73"},{"name":"language_model.model.layers.1.self_attn.v_proj.biases","shape":[2,40],"sha256":"97d50c02e62d40b6049e08441573ea5c2850acd8175a9e78050360c50fee96e7"},{"name":"language_model.model.layers.1.self_attn.v_proj.scales","shape":[2,40],"sha256":"97d50c02e62d40b6049e08441573ea5c2850acd8175a9e78050360c50fee96e7"},{"name":"language_model.model.layers.1.self_attn.v_proj.weight","shape":[2,320],"sha256":"a8ba87d8b51862aa10ebf5c0f67f22b3f9a11991992e90911be9e707d706635a"}]} {"mask":7,"profile":"gate_missing_bias","fusions":{"language_model.model.layers.0.mlp.shared_expert":{"bits":4,"group":64,"splits":[]},"language_model.model.layers.0.linear_attn.in_proj_fused":{"bits":4,"group":64,"splits":[5,8,9]},"language_model.model.layers.1.self_attn.qkv_fused":{"bits":4,"group":64,"splits":[5,7,9]}},"tensors":[{"name":"language_model.model.layers.0.linear_attn.in_proj_fused.biases","shape":[10,40],"sha256":"5a2483da6433a2e53182a5f3acdfb6f6ea3646947527a87211354bbcee15dfd5"},{"name":"language_model.model.layers.0.linear_attn.in_proj_fused.scales","shape":[10,40],"sha256":"5a2483da6433a2e53182a5f3acdfb6f6ea3646947527a87211354bbcee15dfd5"},{"name":"language_model.model.layers.0.linear_attn.in_proj_fused.weight","shape":[10,320],"sha256":"84703ee405db83d0cd5f823950a6f244a727432729299a4138e12a3c7f244335"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_biases","shape":[8,40],"sha256":"ccc740c7994dd6367548fb81759a1916e3ed492b6c137b1337cdabe3ca453332"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_scales","shape":[8,40],"sha256":"ccc740c7994dd6367548fb81759a1916e3ed492b6c137b1337cdabe3ca453332"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_weight","shape":[8,320],"sha256":"393fc4f46b05750db834b2a79ccbeef674d7b073a73edd51e67510e177beccb2"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gate_proj.biases","shape":[2,4,40],"sha256":"80dca76d4ead1253410b9c4352909882e73a90241ef0a0c7b28506f727b13c95"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gate_proj.scales","shape":[2,4,40],"sha256":"80dca76d4ead1253410b9c4352909882e73a90241ef0a0c7b28506f727b13c95"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gate_proj.weight","shape":[2,4,320],"sha256":"7506968c7bf5d98034f3d0d5122e8619b4c17c8938400528ddf94a7cabb7848b"},{"name":"language_model.model.layers.0.mlp.switch_mlp.up_proj.scales","shape":[2,4,40],"sha256":"79d157796e519f46fa701dbe0ae0136cef75da591467b58c6a31b46cdb04d8bb"},{"name":"language_model.model.layers.0.mlp.switch_mlp.up_proj.weight","shape":[2,4,320],"sha256":"074f9a181bd0604c53d2c54d74c272117fe237cd4b29503a944f95932c444fcb"},{"name":"language_model.model.layers.1.self_attn.qkv_fused.biases","shape":[12,40],"sha256":"cf540511bc52e64fe93a6cbcfc075af24e29f0ae5124482fb982d406bfbcfb7d"},{"name":"language_model.model.layers.1.self_attn.qkv_fused.scales","shape":[12,40],"sha256":"cf540511bc52e64fe93a6cbcfc075af24e29f0ae5124482fb982d406bfbcfb7d"},{"name":"language_model.model.layers.1.self_attn.qkv_fused.weight","shape":[12,320],"sha256":"4200990ccbbcd1a186b7e02ddb7978e75e212d03fd4e219de6ea7e627f12334d"}]} {"mask":7,"profile":"shared_only","fusions":{"language_model.model.layers.0.linear_attn.in_proj_fused":{"bits":4,"group":64,"splits":[5,8,9]},"language_model.model.layers.1.self_attn.qkv_fused":{"bits":4,"group":64,"splits":[5,7,9]}},"tensors":[{"name":"language_model.model.layers.0.linear_attn.in_proj_fused.biases","shape":[10,40],"sha256":"5a2483da6433a2e53182a5f3acdfb6f6ea3646947527a87211354bbcee15dfd5"},{"name":"language_model.model.layers.0.linear_attn.in_proj_fused.scales","shape":[10,40],"sha256":"5a2483da6433a2e53182a5f3acdfb6f6ea3646947527a87211354bbcee15dfd5"},{"name":"language_model.model.layers.0.linear_attn.in_proj_fused.weight","shape":[10,320],"sha256":"84703ee405db83d0cd5f823950a6f244a727432729299a4138e12a3c7f244335"},{"name":"language_model.model.layers.0.mlp.shared_expert.gate_proj.biases","shape":[4,40],"sha256":"765708c88ebadb8446fe8fac04f627a928498202c1e108a61fe816772e7460f7"},{"name":"language_model.model.layers.0.mlp.shared_expert.gate_proj.scales","shape":[4,40],"sha256":"765708c88ebadb8446fe8fac04f627a928498202c1e108a61fe816772e7460f7"},{"name":"language_model.model.layers.0.mlp.shared_expert.gate_proj.weight","shape":[4,320],"sha256":"102d250f8e3223ff4a07b32ae21da305982eeeafe25d569fb64d408ee205a699"},{"name":"language_model.model.layers.0.mlp.shared_expert.up_proj.biases","shape":[4,40],"sha256":"2f56a66287bb3cba50ca9b47df972ebaa483d83e6a9a74391ed044e54b0002c2"},{"name":"language_model.model.layers.0.mlp.shared_expert.up_proj.scales","shape":[4,40],"sha256":"2f56a66287bb3cba50ca9b47df972ebaa483d83e6a9a74391ed044e54b0002c2"},{"name":"language_model.model.layers.0.mlp.shared_expert.up_proj.weight","shape":[4,320],"sha256":"fafcd9dcd7459bcd6db2929be8a67f3b7ae0140f1446f240c7b83d2713575867"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gate_proj.biases","shape":[2,4,40],"sha256":"80dca76d4ead1253410b9c4352909882e73a90241ef0a0c7b28506f727b13c95"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gate_proj.scales","shape":[2,4,40],"sha256":"80dca76d4ead1253410b9c4352909882e73a90241ef0a0c7b28506f727b13c95"},{"name":"language_model.model.layers.0.mlp.switch_mlp.up_proj.biases","shape":[2,4,40],"sha256":"79d157796e519f46fa701dbe0ae0136cef75da591467b58c6a31b46cdb04d8bb"},{"name":"language_model.model.layers.0.mlp.switch_mlp.up_proj.scales","shape":[2,4,40],"sha256":"79d157796e519f46fa701dbe0ae0136cef75da591467b58c6a31b46cdb04d8bb"},{"name":"language_model.model.layers.0.mlp.switch_mlp.up_proj.weight","shape":[2,4,320],"sha256":"074f9a181bd0604c53d2c54d74c272117fe237cd4b29503a944f95932c444fcb"},{"name":"language_model.model.layers.1.self_attn.qkv_fused.biases","shape":[12,40],"sha256":"cf540511bc52e64fe93a6cbcfc075af24e29f0ae5124482fb982d406bfbcfb7d"},{"name":"language_model.model.layers.1.self_attn.qkv_fused.scales","shape":[12,40],"sha256":"cf540511bc52e64fe93a6cbcfc075af24e29f0ae5124482fb982d406bfbcfb7d"},{"name":"language_model.model.layers.1.self_attn.qkv_fused.weight","shape":[12,320],"sha256":"4200990ccbbcd1a186b7e02ddb7978e75e212d03fd4e219de6ea7e627f12334d"}]} {"mask":7,"profile":"gdn_2bit","fusions":{"language_model.model.layers.0.mlp.switch_mlp":{"bits":4,"group":64,"splits":[]},"language_model.model.layers.0.mlp.shared_expert":{"bits":4,"group":64,"splits":[]},"language_model.model.layers.1.self_attn.qkv_fused":{"bits":4,"group":64,"splits":[5,7,9]}},"tensors":[{"name":"language_model.model.layers.0.linear_attn.in_proj_a.biases","shape":[1,40],"sha256":"3cc64281a64367b9cd3208a0690290c9f33d3e430f23fdc1629e912e4aebc646"},{"name":"language_model.model.layers.0.linear_attn.in_proj_a.scales","shape":[1,40],"sha256":"3cc64281a64367b9cd3208a0690290c9f33d3e430f23fdc1629e912e4aebc646"},{"name":"language_model.model.layers.0.linear_attn.in_proj_a.weight","shape":[1,160],"sha256":"913f665297f94f2247ac5826cc34718f9529387df89f66a8bc806615a9d6e5a8"},{"name":"language_model.model.layers.0.linear_attn.in_proj_b.biases","shape":[1,40],"sha256":"0f2a0cf1884b62d37e48589848b2e621fbd9105f9ed398b08cd1a05563e12a6f"},{"name":"language_model.model.layers.0.linear_attn.in_proj_b.scales","shape":[1,40],"sha256":"0f2a0cf1884b62d37e48589848b2e621fbd9105f9ed398b08cd1a05563e12a6f"},{"name":"language_model.model.layers.0.linear_attn.in_proj_b.weight","shape":[1,160],"sha256":"a3679076f09417d2724b6e38d8b6d6221dad6ada610463fecf937fff43c812d2"},{"name":"language_model.model.layers.0.linear_attn.in_proj_qkv.biases","shape":[5,40],"sha256":"fd85f811b5562e5bae2bc05832f1027a57a234a1df7d9e8f4d99416b931983c9"},{"name":"language_model.model.layers.0.linear_attn.in_proj_qkv.scales","shape":[5,40],"sha256":"fd85f811b5562e5bae2bc05832f1027a57a234a1df7d9e8f4d99416b931983c9"},{"name":"language_model.model.layers.0.linear_attn.in_proj_qkv.weight","shape":[5,160],"sha256":"96496ab8bb1ff1da1ba829b81ae3a83776fb3d0103858f1e85d308c5d3e2cc6c"},{"name":"language_model.model.layers.0.linear_attn.in_proj_z.biases","shape":[3,40],"sha256":"243eb49ade9062ffcac3214e640b24995402febcfd7a9aafdae8682d7cbb2cc8"},{"name":"language_model.model.layers.0.linear_attn.in_proj_z.scales","shape":[3,40],"sha256":"243eb49ade9062ffcac3214e640b24995402febcfd7a9aafdae8682d7cbb2cc8"},{"name":"language_model.model.layers.0.linear_attn.in_proj_z.weight","shape":[3,160],"sha256":"53cf7d49e00085ac4b215707a74eeceac69984bd12b75f7bf5f88c52315cc54b"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_biases","shape":[8,40],"sha256":"ccc740c7994dd6367548fb81759a1916e3ed492b6c137b1337cdabe3ca453332"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_scales","shape":[8,40],"sha256":"ccc740c7994dd6367548fb81759a1916e3ed492b6c137b1337cdabe3ca453332"},{"name":"language_model.model.layers.0.mlp.shared_expert.gu_weight","shape":[8,320],"sha256":"393fc4f46b05750db834b2a79ccbeef674d7b073a73edd51e67510e177beccb2"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_biases","shape":[2,8,40],"sha256":"592f72b7046080a0c440832a296bf061ee56d889b0e75f3308774c1d7cfa1f99"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_scales","shape":[2,8,40],"sha256":"592f72b7046080a0c440832a296bf061ee56d889b0e75f3308774c1d7cfa1f99"},{"name":"language_model.model.layers.0.mlp.switch_mlp.gu_weight","shape":[2,8,320],"sha256":"c59e7fcfc36b3d60bc29d59592c841efaf9434de2379190942f68625636abf17"},{"name":"language_model.model.layers.1.self_attn.qkv_fused.biases","shape":[12,40],"sha256":"cf540511bc52e64fe93a6cbcfc075af24e29f0ae5124482fb982d406bfbcfb7d"},{"name":"language_model.model.layers.1.self_attn.qkv_fused.scales","shape":[12,40],"sha256":"cf540511bc52e64fe93a6cbcfc075af24e29f0ae5124482fb982d406bfbcfb7d"},{"name":"language_model.model.layers.1.self_attn.qkv_fused.weight","shape":[12,320],"sha256":"4200990ccbbcd1a186b7e02ddb7978e75e212d03fd4e219de6ea7e627f12334d"}]}