Upload traced_bert.pt
a5185f8
-
1.22 kB
initial commit
-
718 Bytes
Upload config.json
-
535 MB
Upload model.onnx
-
440 MB
Upload pytorch_model.bin with git-lfs
-
112 Bytes
Upload special_tokens_map.json
-
377 Bytes
Upload tokenizer_config.json
traced_bert.pt
Detected Pickle imports (224)
- "__torch__.torch.nn.modules.dropout.___torch_mangle_26.Dropout",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_128.Dropout",
- "__torch__.torch.nn.modules.linear.___torch_mangle_34.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_177.Linear",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_23.BertIntermediate",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_10.LayerNorm",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_196.Dropout",
- "__torch__.torch.nn.modules.linear.___torch_mangle_41.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_92.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_160.Linear",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_49.Dropout",
- "__torch__.torch.nn.modules.linear.___torch_mangle_2.Linear",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_157.BertAttention",
- "torch.LongStorage",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_91.BertIntermediate",
- "__torch__.torch.nn.modules.linear.___torch_mangle_81.Linear",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_154.LayerNorm",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_108.BertIntermediate",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_121.Dropout",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_125.BertIntermediate",
- "__torch__.torch.nn.modules.linear.___torch_mangle_24.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_47.Linear",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_191.BertAttention",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_20.BertSelfOutput",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_15.Dropout",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_50.BertSelfAttention",
- "torch.FloatStorage",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_33.BertSelfAttention",
- "__torch__.torch.nn.modules.linear.___torch_mangle_141.Linear",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_178.LayerNorm",
- "__torch__.torch.nn.modules.linear.___torch_mangle_85.Linear",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_186.BertSelfAttention",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_118.BertSelfAttention",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_161.LayerNorm",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_190.BertSelfOutput",
- "__torch__.torch.nn.modules.linear.___torch_mangle_98.Linear",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_156.BertSelfOutput",
- "__torch__.torch.nn.modules.linear.___torch_mangle_3.Linear",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_142.BertIntermediate",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_144.LayerNorm",
- "__torch__.torch.nn.modules.linear.___torch_mangle_167.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_116.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_124.Linear",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_130.BertLayer",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_197.BertOutput",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_117.Dropout",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_57.BertIntermediate",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_174.BertAttention",
- "__torch__.torch.nn.modules.container.ModuleList",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_45.BertLayer",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_35.LayerNorm",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_164.BertLayer",
- "__torch__.torch.nn.modules.linear.___torch_mangle_183.Linear",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_193.BertIntermediate",
- "__torch__.torch.nn.modules.linear.___torch_mangle_5.Linear",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_61.BertOutput",
- "__torch__.torch.nn.modules.linear.___torch_mangle_39.Linear",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_72.BertAttention",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_93.LayerNorm",
- "__torch__.torch.nn.modules.linear.___torch_mangle_29.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_75.Linear",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_138.Dropout",
- "__torch__.torch.nn.modules.sparse.___torch_mangle_1.Embedding",
- "__torch__.transformers.models.bert.modeling_bert.BertAttention",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_4.Dropout",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_38.BertAttention",
- "__torch__.torch.nn.modules.linear.___torch_mangle_153.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_187.Linear",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_111.Dropout",
- "__torch__.transformers.models.bert.modeling_bert.BertLayer",
- "__torch__.torch.nn.modules.linear.___torch_mangle_109.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_165.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_31.Linear",
- "__torch__.transformers.models.bert.modeling_bert.BertPooler",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_18.LayerNorm",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_89.BertAttention",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_139.BertSelfOutput",
- "__torch__.torch.nn.modules.linear.Linear",
- "__torch__.transformers.models.bert.modeling_bert.BertIntermediate",
- "__torch__.torch.nn.modules.linear.___torch_mangle_148.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_182.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_73.Linear",
- "__torch__.torch.nn.modules.normalization.LayerNorm",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_112.BertOutput",
- "__torch__.torch.nn.modules.linear.___torch_mangle_149.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_12.Linear",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_52.LayerNorm",
- "__torch__.torch.nn.modules.linear.___torch_mangle_58.Linear",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_171.LayerNorm",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_110.LayerNorm",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_67.BertSelfAttention",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_151.Dropout",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_32.Dropout",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_145.Dropout",
- "__torch__.torch.nn.modules.linear.___torch_mangle_158.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_82.Linear",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_40.BertIntermediate",
- "__torch__.transformers.models.bert.modeling_bert.BertOutput",
- "__torch__.torch.nn.modules.linear.___torch_mangle_143.Linear",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_28.BertLayer",
- "__torch__.transformers.models.bert.modeling_bert.BertEmbeddings",
- "__torch__.torch.nn.modules.linear.___torch_mangle_131.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_9.Linear",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_83.Dropout",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_101.BertSelfAttention",
- "__torch__.torch.nn.modules.linear.___torch_mangle_65.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_170.Linear",
- "__torch__.torch.nn.modules.activation.Tanh",
- "__torch__.torch.nn.modules.linear.___torch_mangle_63.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_46.Linear",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_173.BertSelfOutput",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_188.LayerNorm",
- "__torch__.torch.nn.modules.linear.___torch_mangle_192.Linear",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_127.LayerNorm",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_86.LayerNorm",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_120.LayerNorm",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_96.BertLayer",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_134.Dropout",
- "__torch__.torch.nn.modules.sparse.Embedding",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_16.BertSelfAttention",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_36.Dropout",
- "__torch__.torch.nn.modules.linear.___torch_mangle_13.Linear",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_106.BertAttention",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_198.BertLayer",
- "__torch__.torch.nn.modules.linear.___torch_mangle_194.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_48.Linear",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_103.LayerNorm",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_62.BertLayer",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_169.BertSelfAttention",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_44.BertOutput",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_25.LayerNorm",
- "__torch__.torch.nn.modules.linear.___torch_mangle_30.Linear",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_66.Dropout",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_172.Dropout",
- "__torch__.torch.nn.modules.linear.___torch_mangle_132.Linear",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_59.LayerNorm",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_69.LayerNorm",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_42.LayerNorm",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_84.BertSelfAttention",
- "__torch__.torch.nn.modules.linear.___torch_mangle_126.Linear",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_53.Dropout",
- "__torch__.torch.nn.modules.linear.___torch_mangle_175.Linear",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_146.BertOutput",
- "__torch__.transformers.models.bert.modeling_bert.BertSelfAttention",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_180.BertOutput",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_6.LayerNorm",
- "__torch__.torch.nn.modules.linear.___torch_mangle_107.Linear",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_152.BertSelfAttention",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_43.Dropout",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_113.BertLayer",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_21.BertAttention",
- "__torch__.torch.nn.modules.linear.___torch_mangle_8.Linear",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_7.Dropout",
- "__torch__.torch.nn.modules.linear.___torch_mangle_136.Linear",
- "__torch__.transformers.models.bert.modeling_bert.BertSelfOutput",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_79.BertLayer",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_74.BertIntermediate",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_11.Dropout",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_155.Dropout",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_54.BertSelfOutput",
- "__torch__.torch.nn.modules.linear.___torch_mangle_14.Linear",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_181.BertLayer",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_179.Dropout",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_95.BertOutput",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_100.Dropout",
- "__torch__.torch.nn.modules.linear.___torch_mangle_22.Linear",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_185.Dropout",
- "__torch__.torch.nn.modules.linear.___torch_mangle_115.Linear",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_123.BertAttention",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_195.LayerNorm",
- "__torch__.transformers.models.bert.modeling_bert.BertEncoder",
- "__torch__.torch.nn.modules.linear.___torch_mangle_199.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_150.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_102.Linear",
- "torch._utils._rebuild_tensor_v2",
- "collections.OrderedDict",
- "__torch__.torch.nn.modules.linear.___torch_mangle_68.Linear",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_137.LayerNorm",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_162.Dropout",
- "__torch__.torch.nn.modules.normalization.___torch_mangle_76.LayerNorm",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_135.BertSelfAttention",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_71.BertSelfOutput",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_176.BertIntermediate",
- "__torch__.torch.nn.modules.linear.___torch_mangle_90.Linear",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_19.Dropout",
- "__torch__.torch.nn.modules.sparse.___torch_mangle_0.Embedding",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_147.BertLayer",
- "__torch__.torch.nn.modules.linear.___torch_mangle_64.Linear",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_129.BertOutput",
- "__torch__.torch.nn.modules.linear.___torch_mangle_17.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_56.Linear",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_27.BertOutput",
- "__torch__.torch.nn.modules.linear.___torch_mangle_133.Linear",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_122.BertSelfOutput",
- "__torch__.torch.nn.modules.linear.___torch_mangle_119.Linear",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_88.BertSelfOutput",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_87.Dropout",
- "__torch__.transformers.models.bert.modeling_bert.BertModel",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_37.BertSelfOutput",
- "__torch__.torch.nn.modules.linear.___torch_mangle_114.Linear",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_163.BertOutput",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_159.BertIntermediate",
- "__torch__.torch.nn.modules.dropout.Dropout",
- "__torch__.torch.nn.modules.linear.___torch_mangle_99.Linear",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_78.BertOutput",
- "__torch__.torch.nn.modules.linear.___torch_mangle_97.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_166.Linear",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_70.Dropout",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_105.BertSelfOutput",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_60.Dropout",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_77.Dropout",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_55.BertAttention",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_104.Dropout",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_189.Dropout",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_94.Dropout",
- "__torch__.torch.nn.modules.linear.___torch_mangle_51.Linear",
- "__torch__.transformers.models.bert.modeling_bert.___torch_mangle_140.BertAttention",
- "__torch__.torch.nn.modules.dropout.___torch_mangle_168.Dropout",
- "__torch__.torch.nn.modules.linear.___torch_mangle_184.Linear",
- "__torch__.torch.nn.modules.linear.___torch_mangle_80.Linear",
- "torch.LongStorage",
- "collections.OrderedDict",
- "torch._utils._rebuild_tensor_v2",
- "torch.DoubleStorage"
How to fix it?
438 MB
Upload traced_bert.pt
training_args.bin
Detected Pickle imports (6)
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_utils.HubStrategy",
- "torch.device",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.training_args.OptimizerNames",
- "transformers.training_args.TrainingArguments"
How to fix it?
2.99 kB
Upload training_args.bin with git-lfs
-
228 kB
Upload vocab.txt
