|
Wait-k decoding?
|
|
1
|
559
|
May 7, 2024
|
|
Dual-source Transformer produces only <unk> tags in inference
|
|
0
|
513
|
May 6, 2024
|
|
RuntimeError: One input stream has less examples than the others
|
|
0
|
493
|
April 30, 2024
|
|
What does the value shown in "Weighted corpora loaded so far: *corpus_1: <value> mean?
|
|
0
|
558
|
April 28, 2024
|
|
Phi-3-3.8B + Llama2-7B ensemble .... just for fun
|
|
1
|
533
|
April 24, 2024
|
|
Translate.py: error: unrecognized arguments: -transforms [sentencepiece, filtertoolong]
|
|
0
|
605
|
April 17, 2024
|
|
Fine tuning nllb-200-distilled-600M model
|
|
16
|
4068
|
April 15, 2024
|
|
Model dimension must be divisible by the number of heads
|
|
2
|
819
|
February 29, 2024
|
|
Canʻt get past Sentencepiece subword tokenization with pretrained embeddings
|
|
0
|
516
|
April 14, 2024
|
|
AttributeError: 'Namespace' object has no attribute 'block_ngram_repeat'
|
|
0
|
2358
|
April 9, 2024
|
|
Epochs Determination
|
|
21
|
5332
|
April 2, 2024
|
|
Building CTranslate2 From Source
|
|
3
|
3428
|
April 1, 2024
|
|
Using ORCA embeddings in OpenNMT-py
|
|
0
|
392
|
March 31, 2024
|
|
How can I visualize attention for ONMT-py
|
|
0
|
507
|
March 29, 2024
|
|
Why the encoder‘s input:src always zero?
|
|
0
|
369
|
March 28, 2024
|
|
Available model checkpoints for Arabic English?
|
|
9
|
2029
|
March 27, 2024
|
|
Error in converting Fairseq Wikitext-103 transformer_lm model
|
|
1
|
681
|
March 26, 2024
|
|
Export all token scores in CTranslate2
|
|
9
|
1549
|
March 11, 2024
|
|
Using a learned BPE Model for Transformer
|
|
0
|
603
|
March 9, 2024
|
|
Support for Intel GPU
|
|
0
|
504
|
March 8, 2024
|
|
UNK replacement
|
|
4
|
2778
|
March 6, 2024
|
|
An error was encountered while running the pre training model
|
|
10
|
1882
|
March 6, 2024
|
|
Errors when installing OpenNMT 3 on Kaggle
|
|
1
|
780
|
March 5, 2024
|
|
The encoder and decoder use different networks and an error occurs
|
|
0
|
400
|
March 2, 2024
|
|
OpenNMT-py does not output </s> EOS token nor did it stop the inference
|
|
5
|
567
|
March 2, 2024
|
|
OpenNMT for SpellCheck
|
|
1
|
1132
|
February 28, 2024
|
|
LLMs as NMT: comparison between ALMA-7/13B-R and TowerInstruct
|
|
5
|
2350
|
February 27, 2024
|
|
Traceback AssertionError while training in Vast.ai
|
|
6
|
1396
|
April 6, 2023
|
|
Device side assert triggered on AWQ Mistral converted model
|
|
5
|
1865
|
February 16, 2024
|
|
Is it normal to see "Weighted corpora loaded so far" in a loop during the finetuning phase on a very small dataset?
|
|
6
|
1584
|
February 15, 2024
|