meinvirgos

/

aina-translator-es-ast-quantized

like 0

• "torch.ao.nn.quantized.modules.linear.LinearPackedParams",
• "torch.per_tensor_affine",
• "transformers.models.m2m_100.modeling_m2m_100.M2M100ForConditionalGeneration",
• "transformers.models.m2m_100.modeling_m2m_100.M2M100SdpaAttention",
• "torch.nn.modules.normalization.LayerNorm",
• "transformers.generation.configuration_utils.GenerationConfig",
• "torch.float32",
• "transformers.models.m2m_100.modeling_m2m_100.M2M100SinusoidalPositionalEmbedding",
• "torch.qint8",
• "transformers.models.m2m_100.modeling_m2m_100.M2M100EncoderLayer",
• "torch._utils._rebuild_qtensor",
• "torch.FloatStorage",
• "transformers.generation.configuration_utils.CompileConfig",
• "transformers.models.m2m_100.modeling_m2m_100.M2M100ScaledWordEmbedding",
• "torch.ScriptObject",
• "transformers.models.m2m_100.modeling_m2m_100.M2M100DecoderLayer",
• "transformers.models.m2m_100.modeling_m2m_100.M2M100Encoder",
• "__builtin__.set",
• "collections.OrderedDict",
• "torch._utils._rebuild_parameter",
• "transformers.models.m2m_100.configuration_m2m_100.M2M100Config",
• "torch.nn.modules.activation.ReLU",
• "transformers.models.m2m_100.modeling_m2m_100.M2M100Decoder",
• "transformers.models.m2m_100.modeling_m2m_100.M2M100Model",
• "torch.QInt8Storage",
• "torch._utils._rebuild_tensor_v2",
• "torch.nn.modules.container.ModuleList",
• "torch.ao.nn.quantized.dynamic.modules.linear.Linear"

How to fix it?