broken-pipeline

/

MCQA-specialized-t5-base-int4

like 0

Follow

BrokenPipeline 2

• "torch.device",
• "torch._utils._rebuild_wrapper_subclass",
• "torch._utils._rebuild_parameter",
• "quanto.tensor.qtype.qtype",
• "transformers.models.t5.configuration_t5.T5Config",
• "torch._tensor._rebuild_from_type_v2",
• "quanto.tensor.qbits.qbits.QBitsTensor",
• "transformers.models.t5.modeling_t5.T5DenseGatedActDense",
• "torch.nn.modules.container.ModuleList",
• "torch.nn.modules.sparse.Embedding",
• "transformers.models.t5.modeling_t5.T5LayerNorm",
• "transformers.models.t5.modeling_t5.T5LayerSelfAttention",
• "transformers.models.t5.modeling_t5.T5Stack",
• "torch._utils._rebuild_tensor_v2",
• "transformers.activations.NewGELUActivation",
• "torch.CharStorage",
• "torch.ByteStorage",
• "torch.serialization._get_layout",
• "quanto.nn.qlinear.QLinear",
• "torch.float32",
• "transformers.models.t5.modeling_t5.T5ForConditionalGeneration",
• "transformers.models.t5.modeling_t5.T5LayerFF",
• "torch.int8",
• "transformers.quantizers.quantizer_quanto.QuantoHfQuantizer",
• "collections.OrderedDict",
• "transformers.utils.quantization_config.QuantoConfig",
• "torch.uint8",
• "transformers.models.t5.modeling_t5.T5Block",
• "transformers.utils.quantization_config.QuantizationMethod",
• "transformers.models.t5.modeling_t5.T5LayerCrossAttention",
• "__builtin__.set",
• "torch.nn.modules.linear.Linear",
• "torch.nn.modules.dropout.Dropout",
• "transformers.models.t5.modeling_t5.T5Attention",
• "torch.FloatStorage",
• "transformers.generation.configuration_utils.GenerationConfig",
• "quanto.tensor.qbits.packed.PackedTensor"

How to fix it?