serializeToBundle throwing java.lang.NegativeArraySizeException

The failure occurs while ModelSerializer.scala writes ml.bundle.Model.toByteArray, reached through PipelineOp.scala and SimpleSparkSerializer.scala; start by reproducing it with the large ALS pipeline under Spark 2.4.4. Done means serializeToBundle completes for the large model without NegativeArraySizeException and retains the model data.

I'm trying to generate an ALS model and serialize it into an mleap bundle. When my model gets too large, serializeToBundle throws java.lang.NegativeArraySizeException. Is there a way to fix this without sacrificing data?

Traceback (most recent call last):
File "/mnt/tmp/spark-820f6826-cd62-4bbc-ad45-694147dc5f0d/mleap_model.py", line 105, in
pipelineModel.serializeToBundle("jar:file:/tmp/mleap-recommendations.zip", pipelineModel.transform(df_als))
File "/usr/local/lib/python3.6/site-packages/mleap/pyspark/spark_support.py", line 25, in serializeToBundle
serializer.serializeToBundle(self, path, dataset=dataset)
File "/usr/local/lib/python3.6/site-packages/mleap/pyspark/spark_support.py", line 42, in serializeToBundle
self._java_obj.serializeToBundle(transformer._to_java(), path, dataset._jdf)
File "/usr/lib/spark/python/lib/py4j-0.10.7-src.zip/py4j/java_gateway.py", line 1257, in call
File "/usr/lib/spark/python/lib/pyspark.zip/pyspark/sql/utils.py", line 63, in deco
File "/usr/lib/spark/python/lib/py4j-0.10.7-src.zip/py4j/protocol.py", line 328, in get_return_value
py4j.protocol.Py4JJavaError: An error occurred while calling o469.serializeToBundle.
: java.lang.NegativeArraySizeException
at ml.combust.mleap.shaded.scalapb.GeneratedMessage$class.toByteArray(GeneratedMessageCompanion.scala:132)
at ml.bundle.Model.toByteArray(Model.scala:9)
at ml.combust.bundle.serializer.ProtoFormatModelSerializer.write(ModelSerializer.scala:60)
at ml.combust.bundle.serializer.ModelSerializer$$anonfun$write$2$$anonfun$apply$1.apply$mcV$sp(ModelSerializer.scala:89)
at ml.combust.bundle.serializer.ModelSerializer$$anonfun$write$2$$anonfun$apply$1.apply(ModelSerializer.scala:89)
at ml.combust.bundle.serializer.ModelSerializer$$anonfun$write$2$$anonfun$apply$1.apply(ModelSerializer.scala:89)
at scala.util.Try$.apply(Try.scala:192)
at ml.combust.bundle.serializer.ModelSerializer$$anonfun$write$2.apply(ModelSerializer.scala:89)
at ml.combust.bundle.serializer.ModelSerializer$$anonfun$write$2.apply(ModelSerializer.scala:89)
at scala.util.Success.flatMap(Try.scala:231)
at ml.combust.bundle.serializer.ModelSerializer.write(ModelSerializer.scala:88)
at ml.combust.bundle.serializer.NodeSerializer$$anonfun$write$1.apply(NodeSerializer.scala:85)
at ml.combust.bundle.serializer.NodeSerializer$$anonfun$write$1.apply(NodeSerializer.scala:81)
at scala.util.Try$.apply(Try.scala:192)
at ml.combust.bundle.serializer.NodeSerializer.write(NodeSerializer.scala:81)
at ml.combust.bundle.serializer.GraphSerializer$$anonfun$writeNode$1.apply(GraphSerializer.scala:34)
at ml.combust.bundle.serializer.GraphSerializer$$anonfun$writeNode$1.apply(GraphSerializer.scala:30)
at scala.util.Try$.apply(Try.scala:192)
at ml.combust.bundle.serializer.GraphSerializer.writeNode(GraphSerializer.scala:30)
at ml.combust.bundle.serializer.GraphSerializer$$anonfun$write$2.apply(GraphSerializer.scala:21)
at ml.combust.bundle.serializer.GraphSerializer$$anonfun$write$2.apply(GraphSerializer.scala:21)
at scala.collection.IndexedSeqOptimized$class.foldl(IndexedSeqOptimized.scala:57)
at scala.collection.IndexedSeqOptimized$class.foldLeft(IndexedSeqOptimized.scala:66)
at scala.collection.mutable.WrappedArray.foldLeft(WrappedArray.scala:35)
at ml.combust.bundle.serializer.GraphSerializer.write(GraphSerializer.scala:20)
at org.apache.spark.ml.bundle.ops.PipelineOp$$anon$1.store(PipelineOp.scala:21)
at org.apache.spark.ml.bundle.ops.PipelineOp$$anon$1.store(PipelineOp.scala:14)
at ml.combust.bundle.serializer.ModelSerializer$$anonfun$write$1.apply(ModelSerializer.scala:87)
at ml.combust.bundle.serializer.ModelSerializer$$anonfun$write$1.apply(ModelSerializer.scala:83)
at scala.util.Try$.apply(Try.scala:192)
at ml.combust.bundle.serializer.ModelSerializer.write(ModelSerializer.scala:83)
at ml.combust.bundle.serializer.NodeSerializer$$anonfun$write$1.apply(NodeSerializer.scala:85)
at ml.combust.bundle.serializer.NodeSerializer$$anonfun$write$1.apply(NodeSerializer.scala:81)
at scala.util.Try$.apply(Try.scala:192)
at ml.combust.bundle.serializer.NodeSerializer.write(NodeSerializer.scala:81)
at ml.combust.bundle.serializer.BundleSerializer$$anonfun$write$1.apply(BundleSerializer.scala:34)
at ml.combust.bundle.serializer.BundleSerializer$$anonfun$write$1.apply(BundleSerializer.scala:29)
at scala.util.Try$.apply(Try.scala:192)
at ml.combust.bundle.serializer.BundleSerializer.write(BundleSerializer.scala:29)
at ml.combust.bundle.BundleWriter.save(BundleWriter.scala:31)
at ml.combust.mleap.spark.SimpleSparkSerializer$$anonfun$serializeToBundleWithFormat$2.apply(SimpleSparkSerializer.scala:26)
at ml.combust.mleap.spark.SimpleSparkSerializer$$anonfun$serializeToBundleWithFormat$2.apply(SimpleSparkSerializer.scala:25)
at ml.combust.mleap.shaded.resource.AbstractManagedResource$$anonfun$5.apply(AbstractManagedResource.scala:88)
at scala.util.control.Exception$Catch$$anonfun$either$1.apply(Exception.scala:125)
at scala.util.control.Exception$Catch$$anonfun$either$1.apply(Exception.scala:125)
at scala.util.control.Exception$Catch.apply(Exception.scala:103)
at scala.util.control.Exception$Catch.either(Exception.scala:125)
at ml.combust.mleap.shaded.resource.AbstractManagedResource.acquireFor(AbstractManagedResource.scala:88)
at ml.combust.mleap.shaded.resource.ManagedResourceOperations$class.apply(ManagedResourceOperations.scala:26)
at ml.combust.mleap.shaded.resource.AbstractManagedResource.apply(AbstractManagedResource.scala:50)
at ml.combust.mleap.shaded.resource.DeferredExtractableManagedResource$$anonfun$tried$1.apply(AbstractManagedResource.scala:33)
at scala.util.Try$.apply(Try.scala:192)
at ml.combust.mleap.shaded.resource.DeferredExtractableManagedResource.tried(AbstractManagedResource.scala:33)
at ml.combust.mleap.spark.SimpleSparkSerializer.serializeToBundleWithFormat(SimpleSparkSerializer.scala:27)
at ml.combust.mleap.spark.SimpleSparkSerializer.serializeToBundle(SimpleSparkSerializer.scala:17)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:282)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:238)
at java.lang.Thread.run(Thread.java:748)

Running Spark 2.4.4 if that helps.