cartesinus

/

xlm_r-massive-joint_nlu

like 0

• "torch.device",
• "transformers.models.xlm_roberta.modeling_xlm_roberta.XLMRobertaEmbeddings",
• "torch.LongStorage",
• "joint_nlu.model.JointNLUModel",
• "torch._utils._rebuild_tensor_v2",
• "torch.nn.modules.linear.Linear",
• "transformers.models.xlm_roberta.modeling_xlm_roberta.XLMRobertaPooler",
• "transformers.models.xlm_roberta.modeling_xlm_roberta.XLMRobertaOutput",
• "transformers.models.xlm_roberta.modeling_xlm_roberta.XLMRobertaLayer",
• "torch.nn.modules.normalization.LayerNorm",
• "transformers.models.xlm_roberta.modeling_xlm_roberta.XLMRobertaAttention",
• "torch.FloatStorage",
• "joint_nlu.config.NLUConfig",
• "transformers.models.xlm_roberta.modeling_xlm_roberta.XLMRobertaIntermediate",
• "torch._C._nn.gelu",
• "torch.nn.modules.sparse.Embedding",
• "transformers.models.xlm_roberta.modeling_xlm_roberta.XLMRobertaSelfOutput",
• "transformers.models.xlm_roberta.configuration_xlm_roberta.XLMRobertaConfig",
• "__builtin__.set",
• "transformers.models.xlm_roberta.modeling_xlm_roberta.XLMRobertaModel",
• "torch.nn.modules.container.ModuleList",
• "torch.nn.modules.dropout.Dropout",
• "transformers.activations.GELUActivation",
• "transformers.models.xlm_roberta.modeling_xlm_roberta.XLMRobertaSelfAttention",
• "torch._utils._rebuild_parameter",
• "collections.OrderedDict",
• "transformers.models.xlm_roberta.modeling_xlm_roberta.XLMRobertaEncoder",
• "torch.nn.modules.activation.Tanh"

How to fix it?