mashrabburanov

/

mt5_on_translated_data

like 0

• "__torch__.torch.nn.modules.linear.___torch_mangle_76.Linear",
• "__torch__.torch.nn.modules.linear.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_106.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_253.MT5LayerFF",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_145.MT5LayerNorm",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_289.Dropout",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_10.Dropout",
• "__torch__.torch.nn.modules.linear.___torch_mangle_159.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_238.Linear",
• "__torch__.torch.nn.modules.container.___torch_mangle_281.ModuleList",
• "__torch__.torch.nn.modules.container.___torch_mangle_47.ModuleList",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_26.Dropout",
• "__torch__.transformers.activations.___torch_mangle_61.NewGELUActivation",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_9.MT5LayerNorm",
• "__torch__.torch.nn.modules.linear.___torch_mangle_178.Linear",
• "__torch__.transformers.activations.NewGELUActivation",
• "__torch__.torch.nn.modules.linear.___torch_mangle_57.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_111.MT5LayerNorm",
• "__torch__.torch.nn.modules.linear.___torch_mangle_2.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_87.Linear",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_194.Dropout",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_234.MT5LayerNorm",
• "__torch__.torch.nn.modules.linear.___torch_mangle_293.Linear",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_189.Dropout",
• "__torch__.torch.nn.modules.linear.___torch_mangle_291.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_62.MT5DenseGatedActDense",
• "__torch__.transformers.activations.___torch_mangle_168.NewGELUActivation",
• "__torch__.torch.nn.modules.linear.___torch_mangle_237.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_326.Linear",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_181.Dropout",
• "__torch__.torch.nn.modules.linear.___torch_mangle_239.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_307.MT5LayerFF",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_81.MT5DenseGatedActDense",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_282.MT5Block",
• "__torch__.torch.nn.modules.linear.___torch_mangle_150.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_255.MT5Block",
• "__torch__.torch.nn.modules.linear.___torch_mangle_40.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_278.MT5LayerNorm",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_216.Dropout",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_349.MT5Attention",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_74.Dropout",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_18.MT5LayerSelfAttention",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_63.MT5LayerNorm",
• "__torch__.torch.nn.modules.linear.___torch_mangle_346.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_109.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_350.MT5LayerNorm",
• "__torch__.torch.nn.modules.linear.___torch_mangle_192.Linear",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_146.Dropout",
• "__torch__.torch.nn.modules.linear.___torch_mangle_256.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_186.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_103.MT5LayerFF",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_35.MT5LayerNorm",
• "__torch__.torch.nn.modules.linear.___torch_mangle_69.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_37.MT5LayerSelfAttention",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_98.Dropout",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_290.MT5LayerSelfAttention",
• "__torch__.torch.nn.modules.linear.___torch_mangle_265.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_300.Linear",
• "__torch__.torch.nn.modules.sparse.___torch_mangle_4.Embedding",
• "__torch__.torch.nn.modules.linear.___torch_mangle_97.Linear",
• "__torch__.torch.nn.modules.container.___torch_mangle_308.ModuleList",
• "__torch__.torch.nn.modules.linear.___torch_mangle_232.Linear",
• "__torch__.transformers.activations.___torch_mangle_357.NewGELUActivation",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_302.Dropout",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_356.Dropout",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_100.MT5DenseGatedActDense",
• "__torch__.torch.nn.modules.linear.___torch_mangle_21.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_179.MT5Attention",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_131.Dropout",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_336.MT5Block",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_43.MT5DenseGatedActDense",
• "__torch__.transformers.activations.___torch_mangle_99.NewGELUActivation",
• "__torch__.transformers.models.mt5.modeling_mt5.MT5Attention",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_277.MT5DenseGatedActDense",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_315.MT5LayerNorm",
• "__torch__.torch.nn.modules.linear.___torch_mangle_205.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_86.MT5Block",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_25.MT5LayerNorm",
• "__torch__.transformers.activations.___torch_mangle_249.NewGELUActivation",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_124.MT5Block",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_288.MT5LayerNorm",
• "__torch__.torch.nn.modules.linear.___torch_mangle_115.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_94.MT5LayerSelfAttention",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_56.MT5LayerSelfAttention",
• "__torch__.torch.nn.modules.linear.___torch_mangle_70.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_328.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_296.MT5LayerNorm",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_141.MT5LayerFF",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_53.MT5Attention",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_242.MT5LayerNorm",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_244.MT5LayerCrossAttention",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_306.Dropout",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_187.MT5Attention",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_280.MT5LayerFF",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_174.MT5Block",
• "__torch__.torch.nn.modules.linear.___torch_mangle_321.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_312.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.MT5DenseGatedActDense",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_16.MT5LayerNorm",
• "__torch__.torch.nn.modules.linear.___torch_mangle_301.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_50.Linear",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_36.Dropout",
• "__torch__.torch.nn.modules.linear.___torch_mangle_164.Linear",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_55.Dropout",
• "__torch__.torch.nn.modules.linear.___torch_mangle_185.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_129.MT5Attention",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_352.MT5LayerCrossAttention",
• "__torch__.torch.nn.modules.container.___torch_mangle_28.ModuleList",
• "__torch__.torch.nn.modules.linear.___torch_mangle_165.Linear",
• "__torch__.transformers.activations.___torch_mangle_195.NewGELUActivation",
• "__torch__.torch.nn.modules.linear.___torch_mangle_184.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_322.MT5Attention",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_34.MT5Attention",
• "__torch__.torch.nn.modules.linear.___torch_mangle_230.Linear",
• "collections.OrderedDict",
• "__torch__.torch.nn.modules.container.___torch_mangle_362.ModuleList",
• "__torch__.transformers.models.mt5.modeling_mt5.MT5LayerCrossAttention",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_224.MT5LayerNorm",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_221.Dropout",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_93.Dropout",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_341.MT5Attention",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_119.MT5DenseGatedActDense",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_217.MT5LayerCrossAttention",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_46.MT5LayerFF",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_262.Dropout",
• "__torch__.torch.nn.modules.linear.___torch_mangle_52.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_320.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_284.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_92.MT5LayerNorm",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_359.MT5LayerNorm",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_140.Dropout",
• "__torch__.torch.nn.modules.linear.___torch_mangle_71.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_219.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_348.Linear",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_275.Dropout",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_305.MT5LayerNorm",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_235.Dropout",
• "__torch__.torch.nn.modules.linear.___torch_mangle_345.Linear",
• "__torch__.transformers.activations.___torch_mangle_42.NewGELUActivation",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_261.MT5LayerNorm",
• "__torch__.torch.nn.modules.linear.___torch_mangle_58.Linear",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_329.Dropout",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_82.MT5LayerNorm",
• "__torch__.torch.nn.modules.linear.___torch_mangle_38.Linear",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_324.Dropout",
• "__torch__.torch.nn.modules.linear.___torch_mangle_14.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_158.Linear",
• "__torch__.torch.nn.modules.container.___torch_mangle_364.ModuleList",
• "__torch__.transformers.activations.___torch_mangle_330.NewGELUActivation",
• "__torch__.torch.nn.modules.dropout.Dropout",
• "__torch__.torch.nn.modules.linear.___torch_mangle_274.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_127.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_327.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_183.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_161.MT5Attention",
• "__torch__.torch.nn.modules.linear.___torch_mangle_259.Linear",
• "__torch__.transformers.activations.___torch_mangle_222.NewGELUActivation",
• "__torch__.torch.nn.modules.linear.___torch_mangle_175.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_241.MT5Attention",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_197.MT5LayerNorm",
• "__torch__.torch.nn.modules.linear.___torch_mangle_39.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_90.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_250.MT5DenseGatedActDense",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_260.MT5Attention",
• "__torch__.torch.nn.modules.linear.___torch_mangle_257.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_89.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_116.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_228.MT5Block",
• "__torch__.torch.nn.modules.linear.___torch_mangle_13.Linear",
• "__torch__.transformers.activations.___torch_mangle_118.NewGELUActivation",
• "__torch__.torch.nn.modules.linear.___torch_mangle_246.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_319.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_213.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_151.Linear",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_225.Dropout",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_73.MT5LayerNorm",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_325.MT5LayerCrossAttention",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_287.MT5Attention",
• "__torch__.torch.nn.modules.linear.___torch_mangle_313.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_292.Linear",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_198.Dropout",
• "__torch__.transformers.activations.___torch_mangle_137.NewGELUActivation",
• "__torch__.torch.nn.modules.linear.___torch_mangle_125.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_334.MT5LayerFF",
• "__torch__.torch.nn.modules.sparse.___torch_mangle_0.Embedding",
• "__torch__.torch.nn.modules.linear.___torch_mangle_88.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_339.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_337.Linear",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_64.Dropout",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_243.Dropout",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_105.MT5Block",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_154.MT5LayerNorm",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_180.MT5LayerNorm",
• "__torch__.torch.nn.modules.linear.___torch_mangle_210.Linear",
• "torch.FloatStorage",
• "__torch__.torch.nn.modules.container.___torch_mangle_104.ModuleList",
• "__torch__.torch.nn.modules.linear.___torch_mangle_20.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_156.MT5LayerSelfAttention",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_79.Dropout",
• "__torch__.torch.nn.modules.linear.___torch_mangle_126.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_108.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_65.MT5LayerFF",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_367.MT5Stack",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_332.MT5LayerNorm",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_207.MT5LayerNorm",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_130.MT5LayerNorm",
• "__torch__.torch.nn.modules.linear.___torch_mangle_149.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_96.Linear",
• "__torch__.torch.nn.modules.container.___torch_mangle_200.ModuleList",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_45.Dropout",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_344.MT5LayerSelfAttention",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_248.Dropout",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_117.Dropout",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_208.Dropout",
• "__torch__.torch.nn.modules.linear.___torch_mangle_107.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_363.MT5Block",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_17.Dropout",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_360.Dropout",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_172.MT5LayerFF",
• "__torch__.torch.nn.modules.linear.___torch_mangle_340.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_51.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_32.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_101.MT5LayerNorm",
• "__torch__.torch.nn.modules.linear.___torch_mangle_273.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_295.MT5Attention",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_167.Dropout",
• "__torch__.torch.nn.modules.linear.___torch_mangle_12.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_218.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_233.MT5Attention",
• "__torch__.torch.nn.modules.linear.___torch_mangle_245.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_264.Linear",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_270.Dropout",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_271.MT5LayerCrossAttention",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_223.MT5DenseGatedActDense",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_67.MT5Block",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_54.MT5LayerNorm",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_27.MT5LayerFF",
• "__torch__.transformers.models.mt5.modeling_mt5.MT5Stack",
• "__torch__.torch.nn.modules.container.___torch_mangle_227.ModuleList",
• "__torch__.torch.nn.modules.linear.___torch_mangle_11.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_211.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_84.MT5LayerFF",
• "__torch__.torch.nn.modules.container.___torch_mangle_254.ModuleList",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_60.Dropout",
• "__torch__.torch.nn.modules.linear.___torch_mangle_310.Linear",
• "__torch__.torch.nn.modules.container.___torch_mangle_66.ModuleList",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_138.MT5DenseGatedActDense",
• "__torch__.torch.nn.modules.linear.___torch_mangle_203.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_78.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.MT5ForConditionalGeneration",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_188.MT5LayerNorm",
• "__torch__.transformers.activations.___torch_mangle_80.NewGELUActivation",
• "__torch__.torch.nn.modules.linear.___torch_mangle_258.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_59.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_268.MT5Attention",
• "__torch__.torch.nn.modules.linear.___torch_mangle_354.Linear",
• "__torch__.torch.nn.modules.container.___torch_mangle_123.ModuleList",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_15.MT5Attention",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_366.Dropout",
• "__torch__.torch.nn.modules.linear.___torch_mangle_68.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_31.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_365.MT5LayerNorm",
• "__torch__.torch.nn.modules.linear.___torch_mangle_353.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_240.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_272.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_368.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_285.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_132.MT5LayerSelfAttention",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_309.MT5Block",
• "__torch__.torch.nn.modules.linear.___torch_mangle_7.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_304.MT5DenseGatedActDense",
• "__torch__.torch.nn.modules.sparse.Embedding",
• "__torch__.torch.nn.modules.linear.___torch_mangle_212.Linear",
• "torch._utils._rebuild_tensor_v2",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_236.MT5LayerSelfAttention",
• "__torch__.transformers.activations.___torch_mangle_303.NewGELUActivation",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_269.MT5LayerNorm",
• "__torch__.torch.nn.modules.linear.___torch_mangle_77.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_209.MT5LayerSelfAttention",
• "__torch__.torch.nn.modules.linear.___torch_mangle_266.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_122.MT5LayerFF",
• "__torch__.transformers.models.mt5.modeling_mt5.MT5LayerSelfAttention",
• "__torch__.torch.nn.modules.linear.___torch_mangle_286.Linear",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_333.Dropout",
• "__torch__.torch.nn.modules.linear.___torch_mangle_247.Linear",
• "__torch__.torch.nn.modules.container.ModuleList",
• "__torch__.torch.nn.modules.linear.___torch_mangle_95.Linear",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_297.Dropout",
• "__torch__.torch.nn.modules.sparse.___torch_mangle_147.Embedding",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_252.Dropout",
• "__torch__.transformers.models.mt5.modeling_mt5.MT5LayerFF",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_206.MT5Attention",
• "__torch__.torch.nn.modules.linear.___torch_mangle_229.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_176.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_133.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_251.MT5LayerNorm",
• "__torch__.torch.nn.modules.linear.___torch_mangle_267.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_199.MT5LayerFF",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_8.Dropout",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_121.Dropout",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_190.MT5LayerCrossAttention",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_24.MT5DenseGatedActDense",
• "__torch__.torch.nn.modules.linear.___torch_mangle_204.Linear",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_136.Dropout",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_314.MT5Attention",
• "__torch__.torch.nn.modules.linear.___torch_mangle_6.Linear",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_171.Dropout",
• "__torch__.torch.nn.modules.linear.___torch_mangle_135.Linear",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_279.Dropout",
• "__torch__.torch.nn.modules.container.___torch_mangle_335.ModuleList",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_361.MT5LayerFF",
• "__torch__.torch.nn.modules.linear.___torch_mangle_283.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_48.MT5Block",
• "__torch__.torch.nn.modules.linear.___torch_mangle_148.Linear",
• "__torch__.torch.nn.modules.container.___torch_mangle_142.ModuleList",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_83.Dropout",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_331.MT5DenseGatedActDense",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_41.Dropout",
• "__torch__.torch.nn.modules.container.___torch_mangle_144.ModuleList",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_29.MT5Block",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_163.Dropout",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_22.Dropout",
• "__torch__.torch.nn.modules.linear.___torch_mangle_30.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_318.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_214.MT5Attention",
• "__torch__.torch.nn.modules.linear.___torch_mangle_338.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_33.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_298.MT5LayerCrossAttention",
• "__torch__.transformers.activations.___torch_mangle_276.NewGELUActivation",
• "__torch__.torch.nn.modules.linear.___torch_mangle_177.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_110.MT5Attention",
• "__torch__.torch.nn.modules.linear.___torch_mangle_231.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_5.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_196.MT5DenseGatedActDense",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_91.MT5Attention",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_226.MT5LayerFF",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_358.MT5DenseGatedActDense",
• "__torch__.torch.nn.modules.linear.___torch_mangle_19.Linear",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_316.Dropout",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_113.MT5LayerSelfAttention",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_215.MT5LayerNorm",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_112.Dropout",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_143.MT5Block",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_169.MT5DenseGatedActDense",
• "__torch__.torch.nn.modules.linear.___torch_mangle_157.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_3.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_202.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_1.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_49.Linear",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_102.Dropout",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_153.MT5Attention",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_343.Dropout",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_162.MT5LayerNorm",
• "__torch__.transformers.models.mt5.modeling_mt5.MT5LayerNorm",
• "__torch__.torch.nn.modules.linear.___torch_mangle_191.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_120.MT5LayerNorm",
• "__torch__.transformers.activations.___torch_mangle_23.NewGELUActivation",
• "__torch__.torch.nn.modules.sparse.___torch_mangle_152.Embedding",
• "__torch__.transformers.models.mt5.modeling_mt5.MT5Block",
• "__torch__.torch.nn.modules.container.___torch_mangle_85.ModuleList",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_201.MT5Block",
• "__torch__.torch.nn.modules.linear.___torch_mangle_311.Linear",
• "__torch__.torch.nn.modules.container.___torch_mangle_173.ModuleList",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_44.MT5LayerNorm",
• "__torch__.torch.nn.modules.linear.___torch_mangle_166.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_347.Linear",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_351.Dropout",
• "__torch__.torch.nn.modules.linear.___torch_mangle_220.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_355.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_128.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_139.MT5LayerNorm",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_317.MT5LayerSelfAttention",
• "__torch__.torch.nn.modules.linear.___torch_mangle_134.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_160.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_114.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_170.MT5LayerNorm",
• "__torch__.torch.nn.modules.dropout.___torch_mangle_155.Dropout",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_182.MT5LayerSelfAttention",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_72.MT5Attention",
• "__torch__.torch.nn.modules.linear.___torch_mangle_193.Linear",
• "__torch__.torch.nn.modules.linear.___torch_mangle_299.Linear",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_342.MT5LayerNorm",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_263.MT5LayerSelfAttention",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_323.MT5LayerNorm",
• "__torch__.transformers.models.mt5.modeling_mt5.___torch_mangle_75.MT5LayerSelfAttention",
• "__torch__.torch.nn.modules.linear.___torch_mangle_294.Linear",
• "torch.LongStorage",
• "torch.DoubleStorage",
• "torch._utils._rebuild_tensor_v2",
• "collections.OrderedDict",
• "torch.LongStorage",
• "torch.jit._pickle.restore_type_tag",
• "torch._utils._rebuild_tensor_v2",
• "collections.OrderedDict"

How to fix it?