|
Ctranslate2 + model conversion
|
|
8
|
4224
|
February 5, 2020
|
|
CTranslate2 conversion of Hugging Face fine-tuned model
|
|
6
|
4781
|
May 9, 2022
|
|
Using pretrained Elmo embeddings
|
|
4
|
3174
|
October 30, 2018
|
|
Getting attention weights
|
|
8
|
4190
|
July 27, 2019
|
|
Training get stuck and GPU is 100% used at 257100 or 507100 steps
|
|
4
|
5616
|
September 3, 2019
|
|
Docker flask server timeout when calling ctranslate python module
|
|
5
|
5083
|
December 10, 2020
|
|
How to use pre-trained BPEmb subword embeddings with latest versions of OpenNMT and OpenNMT-py?
|
|
5
|
5068
|
June 16, 2024
|
|
Bpe for chinese characters?
|
|
5
|
5033
|
May 30, 2017
|
|
Chinese to english translation many unknown words
|
|
8
|
4076
|
June 11, 2020
|
|
TLIte Converter
|
|
4
|
1723
|
June 8, 2021
|
|
Hosting a OpenNMT-tf model on OpenNMT-py server
|
|
2
|
1245
|
January 30, 2023
|
|
Help with character-level model settings
|
|
8
|
4027
|
April 18, 2017
|
|
Ctranslate2 installation error
|
|
4
|
5399
|
May 20, 2021
|
|
Preprocess Vocab - how it works?
|
|
8
|
4006
|
December 5, 2019
|
|
_pickle.PicklingError: Can't pickle <function Field.<lambda>: attribute lookup Field.<lambda> on torchtext.data.field failed
|
|
6
|
4513
|
March 15, 2019
|
|
CTranslate2 model conversion error
|
|
7
|
4200
|
February 18, 2020
|
|
Sentence embeddings and n-best lists
|
|
5
|
4827
|
November 22, 2017
|
|
CUDA out of memory when training the model
|
|
3
|
5856
|
November 24, 2020
|
|
Error converting model to ctranslate2
|
|
5
|
2683
|
April 7, 2023
|
|
Can OpenNMT-py support multi datasets for multilingual translation?
|
|
8
|
3894
|
December 31, 2021
|
|
GPU out of memory: After checkpoint is saved and during first step of eval
|
|
4
|
5205
|
March 22, 2019
|
|
How can I use embeddings?
|
|
6
|
4398
|
June 8, 2019
|
|
Length Penalty Question
|
|
5
|
4745
|
June 2, 2020
|
|
How to extend an already-trained engine?
|
|
4
|
1641
|
September 26, 2017
|
|
Add noise to corpus and improve training signal
|
|
4
|
1626
|
August 8, 2019
|
|
Support Crayon Logging
|
|
6
|
2440
|
March 6, 2017
|
|
Convert T5 for ctranslate2
|
|
4
|
5131
|
January 2, 2023
|
|
Training chatbot with multiple inputs (to add context)
|
|
4
|
5129
|
June 22, 2017
|
|
Tds not found when running preprocess.lua
|
|
3
|
5704
|
April 19, 2018
|
|
Incremental vocab
|
|
6
|
2414
|
June 21, 2017
|
|
Errors while training with Transformer: CUDA OOM and removed batches
|
|
7
|
3963
|
February 8, 2021
|
|
Tensorflow error with training command
|
|
4
|
4998
|
December 18, 2019
|
|
How computing loss in shards helps reduce memory cost?
|
|
0
|
1986
|
January 13, 2018
|
|
Best Practice for Splitting Datasets
|
|
5
|
4558
|
November 13, 2019
|
|
Is there German->English pretrained model parallel to English-> German (WMT) in Openmy-py?
|
|
2
|
6444
|
May 17, 2018
|
|
OpenNMT-tf toy-ende model scoring and inference clarification
|
|
4
|
4969
|
March 23, 2019
|
|
How to Activate the Tensorboard
|
|
5
|
4532
|
March 25, 2019
|
|
Looking for Advice on Developing a Specialised Translation Model for Technical Documents
|
|
1
|
1391
|
July 21, 2024
|
|
How to open TensorBoard running on a EC2 instance
|
|
4
|
4924
|
March 29, 2019
|
|
TransformerBig model - GTX 1080 Ti (11G) - ResourceExhaustedError
|
|
8
|
3665
|
December 5, 2018
|
|
Over fitting and over training
|
|
1
|
1382
|
March 11, 2021
|
|
Transformer: Freezing Encoder while training Decoder
|
|
3
|
5483
|
December 27, 2019
|
|
RuntimeError: Length of all samples has to be greater than 0, but found an element in 'lengths' that is <= 0
|
|
6
|
4142
|
May 6, 2021
|
|
Evaluate translation hypotheses
|
|
6
|
4076
|
December 17, 2021
|
|
Should I use OpenNMT-py or OpenNMT-tf
|
|
2
|
1967
|
January 2, 2023
|
|
English to Russian translation with OpenNMT-py
|
|
8
|
3591
|
March 4, 2019
|
|
How to deploy in Android
|
|
0
|
1915
|
October 14, 2024
|
|
Inference best practices
|
|
1
|
1352
|
July 13, 2020
|
|
Wandb integration
|
|
0
|
1909
|
February 15, 2021
|
|
How to speed up beam search?
|
|
5
|
4349
|
March 8, 2017
|