"tao n_gram export" generates a .binary file, not a .riva file

Hi there,
I am trying to export an n_gram LM I trained with Tao to a Riva file.

Here is the command I used to train it:

tao n_gram train \
            -e $SPECS_DIR/train.yaml \
            -r $RESULTS_DIR/train_lm_1 \
            training_ds.data_file=$DATA_DIR/preprocessed.txt \
            model.order=3 \
            model.pruning=[0,0,1]

The command I used to export it:

tao n_gram export \
            -e $SPECS_DIR/export.yaml \
            -r $RESULTS_DIR/export_lm_1 \
            export_format=RIVA \
            export_to=exported-model.riva \
            restore_from=$RESULTS_DIR/train_lm_1/checkpoints/train_n_gram.arpa \
            binary_type=trie \
            binary_q_bits=8 \
            binary_b_bits=7 \
            binary_a_bits=256

The export.yaml spec file:

# Copyright (c) 2020, NVIDIA CORPORATION. All rights reserved.

# Name of the .arpa EFF archive to be loaded/model to be exported.
restore_from: ???

# Set export format: ONNX | RIVA
export_format: RIVA

# Output EFF archive containing binary.
export_to: exported-model.riva

# Data structure to use (default is probing)
binary_type: ??? 

# probabillity bits (quantization)
binary_q_bits: 0

# backoff bits (quantization)
binary_b_bits: 0

# pointer compression
binary_a_bits: 0 

The logs for the export command:

2021-11-23 19:15:08,783 [INFO] root: Registry: ['nvcr.io']
2021-11-23 19:15:08,885 [WARNING] tlt.components.docker_handler.docker_handler: 
Docker will run the commands as root. If you would like to retain your
local host permissions, please add the "user":"UID:GID" in the
DockerOptions portion of the "/home/ubuntu/.tao_mounts.json" file. You can obtain your
users UID and GID by using the "id -u" and "id -g" commands on the
terminal.
[nltk_data] Downloading package punkt to /root/nltk_data...
[nltk_data]   Unzipping tokenizers/punkt.zip.
/tlt-lm/lm/n_gram/scripts/export.py:103: UserWarning: 
'export.yaml' is validated against ConfigStore schema with the same name.
This behavior is deprecated in Hydra 1.1 and will be removed in Hydra 1.2.
See https://hydra.cc/docs/next/upgrades/1.0_to_1.1/automatic_schema_matching for migration instructions.
Experiment configuration:
restore_from: /results/n_gram/train_lm_1/checkpoints/train_n_gram.arpa
export_to: exported-model.riva
export_format: RIVA
exp_manager:
  task_name: export
  explicit_log_dir: /results/n_gram/export_lm_1
encryption_key: '********'
binary_type: trie
binary_q_bits: 8
binary_b_bits: 7
binary_a_bits: 256

Reading /results/n_gram/train_lm_1/checkpoints/train_n_gram.arpa
----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100
****************************************************************************************************
Identifying n-grams omitted by SRI
----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100
****************************************************************************************************
Quantizing
----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100
****************************************************************************************************
Writing trie
----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100
****************************************************************************************************
SUCCESS
Experiment logs saved to '/results/n_gram/export_lm_1'
Binary model saved to /results/n_gram/export_lm_1/exported-model.binary
2021-11-23 19:15:13,100 [INFO] tlt.components.docker_handler.docker_handler: Stopping container.

When I run the export command, I get a “exported-model.binary” file, not an “exported-model.riva” file, and I am having trouble getting that file to be accepted by the “riva-build” command I want to use in order to pair it with a Citrinet ASR model.

Can anyone help?

Hardware: AWS g4dn.xlarge instance, with a T4 GPU
Operating System: Ubuntu 20.04 LTS via NVIDIA GPU Cloud image
Riva Version - 1.7
TLT Version (if relevant) - 3.21.08