|
GLaM: Efficient Scaling of Language Models with Mixture-of-Experts
|
|
0
|
1049
|
December 14, 2021
|
|
Correct settings when source word features
|
|
0
|
1042
|
June 20, 2023
|
|
Help Needed: Converting OpenNMT Model to Hugging Face Format
|
|
0
|
1038
|
December 30, 2024
|
|
ValueError: invalid literal for int() with base 10
|
|
0
|
1036
|
August 27, 2021
|
|
Can we freeze any of the model parameters in OpenNMT-py?
|
|
0
|
1034
|
December 27, 2019
|
|
M2m100 Out-of-Vocabulary
|
|
0
|
1033
|
December 29, 2024
|
|
OpenNMT for Knime workflow
|
|
0
|
1034
|
June 8, 2023
|
|
How to know the case of UNK?
|
|
0
|
1032
|
September 16, 2018
|
|
How can I reset the position_encoding Tensor as a trainable Parameter?
|
|
0
|
1026
|
August 14, 2020
|
|
OpenNMT testing instance
|
|
0
|
1024
|
December 24, 2019
|
|
Large discrepancy in performance on validation set vs. test set, agglutinative languages only
|
|
0
|
1023
|
April 3, 2019
|
|
LibreTranslater Android app
|
|
0
|
1021
|
August 25, 2021
|
|
The Training-process does not 'finish'
|
|
0
|
1019
|
July 2, 2024
|
|
Translate.py: error: unrecognized arguments: -transforms [sentencepiece, filtertoolong]
|
|
0
|
1017
|
April 17, 2024
|
|
Forcing translation of specific words
|
|
0
|
1017
|
July 13, 2018
|
|
How are the latex formula seprated in tgt-train.txt
|
|
0
|
1014
|
February 5, 2020
|
|
Overfitting query after training
|
|
0
|
1010
|
February 25, 2025
|
|
Scaling Loss for Character Level Seq2seq model
|
|
0
|
1011
|
June 28, 2020
|
|
Is there an implementation of GOLD in openNMT?
|
|
0
|
1006
|
January 16, 2024
|
|
Training back-translation model separately
|
|
0
|
1006
|
October 1, 2020
|
|
Running ct2-marian-converter converted marian model on cpu
|
|
0
|
1002
|
November 27, 2024
|
|
Difference between train-src.TXT and train.tags.fr
|
|
1
|
703
|
January 5, 2021
|
|
Epochs vs steps
|
|
0
|
990
|
July 5, 2018
|
|
Model inference keeps repeating the same translation
|
|
0
|
988
|
June 6, 2024
|
|
Stop printing Model Output
|
|
0
|
986
|
April 11, 2020
|
|
Transfer learning
|
|
1
|
692
|
January 7, 2023
|
|
MFCC feature extraction Speech to Text
|
|
0
|
974
|
November 19, 2019
|
|
NLLB Translation, skip or mask some tokens
|
|
0
|
971
|
October 12, 2024
|
|
Tune transformer for low-resource languages
|
|
0
|
970
|
October 19, 2021
|
|
Similarity of the fine-tuning data with domain for successful adaptation
|
|
0
|
969
|
February 9, 2021
|
|
Is there any way I can give custom fairseq config while using fairseq_converter in ctranslate2
|
|
0
|
967
|
February 14, 2024
|
|
When does the model transform string to int during training?
|
|
0
|
968
|
October 6, 2017
|
|
Best practices for multiple corpora
|
|
0
|
966
|
July 9, 2021
|
|
Why value of list(train_iter)[0].src[0] in train.py always changing?
|
|
0
|
962
|
October 6, 2017
|
|
H100 perfomance
|
|
0
|
962
|
September 20, 2023
|
|
AttributeError: ‘M2M100Encoder’ object has no attribute ‘embed_stale’
|
|
0
|
957
|
August 31, 2024
|
|
Paragraph-based training with LSTM Network
|
|
0
|
955
|
November 14, 2020
|
|
Wav2vec2 support in CTranslate2
|
|
0
|
953
|
June 16, 2023
|
|
How to use BiLSTM model
|
|
0
|
952
|
November 26, 2020
|
|
Shards v/s Batch size - Image2Text
|
|
0
|
949
|
September 7, 2021
|
|
Memory Error while training with Cyrrillic UTF-8 decoded tokens
|
|
1
|
670
|
February 27, 2023
|
|
Canʻt get past Sentencepiece subword tokenization with pretrained embeddings
|
|
0
|
946
|
April 14, 2024
|
|
Quantized model shards
|
|
0
|
942
|
June 15, 2024
|
|
AttributeError: 'DeprecateAction' object has no attribute 'mdhelp'
|
|
0
|
941
|
August 13, 2018
|
|
Attn_debug usage
|
|
0
|
939
|
July 29, 2019
|
|
Convert a model trained with opennmt-py 0.4.1 to opennmt-py 2.2.2
|
|
0
|
937
|
August 6, 2024
|
|
Where data resides in OpneNMT
|
|
0
|
933
|
May 14, 2018
|
|
Using T-rex dataset with OpenNMT
|
|
0
|
922
|
December 13, 2021
|
|
How to tranfser names from source to target?
|
|
0
|
923
|
January 23, 2020
|
|
Types of generalizations learned by NMT?
|
|
0
|
922
|
February 10, 2020
|