|
Small vocabs when running build_vocab.lua on BPE tokenized data
|
|
0
|
1100
|
June 5, 2018
|
|
Hyperparameter Tuning -- Validation set
|
|
0
|
1095
|
July 9, 2021
|
|
Error using OpenNMT-py (Multiple edits, new issue)
|
|
0
|
1095
|
August 28, 2018
|
|
Pre-trained embeddings : what about special tokens?
|
|
0
|
1094
|
February 21, 2017
|
|
--start_from is removed on ONMT3?
|
|
2
|
632
|
March 31, 2023
|
|
Train-Checkpoint-train_from
|
|
1
|
773
|
January 26, 2023
|
|
Opennmt-py demo training failed from time to time
|
|
0
|
1090
|
January 4, 2019
|
|
Use GloVe with concatenated word features (OpenNMT-py)
|
|
0
|
1090
|
December 5, 2018
|
|
What is the minimal adequate corpus size for computing BLEU score?
|
|
0
|
1090
|
April 17, 2018
|
|
Converter: Hints for converting Transformer of GPTBigCodeForCausalLM
|
|
1
|
771
|
May 26, 2023
|
|
OpenNMT-py full documentation link broken
|
|
1
|
769
|
February 17, 2019
|
|
Github repo to translate from Tibetan to English with Google Colab
|
|
0
|
1089
|
June 17, 2024
|
|
Error while Training using share-vocab
|
|
1
|
768
|
January 30, 2021
|
|
Is Tokenizer::tokenize() thread-safe
|
|
0
|
1084
|
December 14, 2023
|
|
How to use the feature of " Multiple source and target RNN (lstm/gru) types and attention (dotprod/mlp) types"
|
|
0
|
1076
|
March 27, 2018
|
|
Deploying an OpenNMT-py model
|
|
0
|
1072
|
February 20, 2021
|
|
When continuing a training, the option for embeddeing seems to have no effect
|
|
1
|
756
|
March 5, 2020
|
|
Tokenization Command Error
|
|
0
|
1067
|
March 7, 2018
|
|
Influence of the parameter "number of heads" on the size of the model
|
|
1
|
754
|
July 26, 2023
|
|
Need help . SyntaxError: invalid syntax
|
|
0
|
1064
|
January 2, 2021
|
|
Tools/embedding_convert.lua Error
|
|
0
|
1059
|
February 1, 2018
|
|
Ctranslate2 Support for DeltaLM
|
|
1
|
749
|
June 22, 2023
|
|
OpenNMT-py cannot find GPU resources
|
|
0
|
1057
|
April 23, 2021
|
|
Index out of range when computing batch loss with transformer architecture
|
|
0
|
1057
|
July 11, 2018
|
|
Different BLEU scores with test2015.de.atok test2016.de
|
|
0
|
1055
|
July 1, 2018
|
|
Word_vec_size when using pre-trained embeddings
|
|
0
|
1054
|
April 22, 2018
|
|
How to update opennmt in a docker container?
|
|
1
|
741
|
February 18, 2019
|
|
Automatic Backup
|
|
0
|
1046
|
January 12, 2022
|
|
Using BART-mnli with CTranslate2
|
|
1
|
738
|
May 24, 2023
|
|
Does somebody know : How to train it to continuously upgrade?
|
|
0
|
1044
|
September 10, 2021
|
|
Range of predict score
|
|
1
|
735
|
July 7, 2021
|
|
Cannot initialize Translator class object
|
|
1
|
732
|
November 9, 2020
|
|
What's "OpenNMT-py/onmt/modules/Gate.py"?
|
|
0
|
1035
|
July 5, 2018
|
|
Quality/Confidence score
|
|
0
|
1033
|
March 11, 2020
|
|
Zero learning rate
|
|
1
|
730
|
December 17, 2019
|
|
OpenNMT-tf mixed precision
|
|
0
|
1027
|
November 23, 2023
|
|
Bad argument #2 to '?': Error during training
|
|
0
|
1028
|
May 21, 2018
|
|
Input to reshape is a tensor with 528066 values, but the requested shape has 352022
|
|
0
|
1030
|
November 20, 2023
|
|
Implement translate command using OpenNMT-py code
|
|
0
|
1024
|
March 11, 2022
|
|
ValueError: shuffle_buffer_size < 0 is not compatible with weighted datasets
|
|
1
|
722
|
June 13, 2023
|
|
BPE syntax error
|
|
0
|
1019
|
July 9, 2018
|
|
Tagalog speaker for human evaluation of 50 sentences
|
|
0
|
1017
|
October 13, 2021
|
|
Target tokens out of vocabulary
|
|
1
|
714
|
April 3, 2023
|
|
ValueError: invalid literal for int() with base 10
|
|
0
|
1000
|
August 27, 2021
|
|
Support for Multi-Task Learning?
|
|
0
|
996
|
June 14, 2023
|
|
Can we freeze any of the model parameters in OpenNMT-py?
|
|
0
|
994
|
December 27, 2019
|
|
GLaM: Efficient Scaling of Language Models with Mixture-of-Experts
|
|
0
|
991
|
December 14, 2021
|
|
OpenNMT testing instance
|
|
0
|
991
|
December 24, 2019
|
|
Large discrepancy in performance on validation set vs. test set, agglutinative languages only
|
|
0
|
990
|
April 3, 2019
|
|
How to know the case of UNK?
|
|
0
|
987
|
September 16, 2018
|