How quality of validation dataset affects final results of a model with a fixed number of steps?
|
|
2
|
279
|
September 19, 2023
|
Any tutorial on how to finetune using OpenNMT
|
|
1
|
554
|
September 16, 2023
|
Learning rate start to decay before start_decay_steps
|
|
3
|
260
|
September 8, 2023
|
BLEU decreases so much after averaging checkpoints
|
|
5
|
581
|
March 27, 2022
|
Fine-Tuning Llama-2 quantized with CT2
|
|
5
|
1590
|
September 2, 2023
|
English Persian translator
|
|
5
|
403
|
September 1, 2023
|
Any negative effects of using the parameter "Replace unknowns = True" in inference?
|
|
3
|
243
|
August 31, 2023
|
OpenNMT-TF checkpoint conversion
|
|
1
|
228
|
August 26, 2023
|
Create Knime Workflow with OpenNMT on AWS GPU instance
|
|
0
|
208
|
August 18, 2023
|
Ctranslate2 gives KeyError: 'vocab' when translating HF Llama2 model
|
|
2
|
325
|
August 10, 2023
|
How to define the train steps when finetune nllb-200
|
|
0
|
279
|
August 3, 2023
|
Issues running the OpenNMT-py REST server
|
|
61
|
5617
|
August 3, 2023
|
Failing conversion of Small100 (SMALL100Tokenizer does not exist or is not currently imported)
|
|
6
|
449
|
August 1, 2023
|
Extra token produced
|
|
6
|
318
|
July 26, 2023
|
Inference Llama-2 with CTranslate2
|
|
1
|
1308
|
July 26, 2023
|
Influence of the parameter "number of heads" on the size of the model
|
|
1
|
225
|
July 26, 2023
|
Increasing effective batch size
|
|
4
|
508
|
July 21, 2023
|
Is Data Checkpointing possible?
|
|
1
|
261
|
July 7, 2023
|
[Outdated] -report_align not working
|
|
3
|
251
|
July 6, 2023
|
What are the best techniques to add noise
|
|
1
|
316
|
June 23, 2023
|
Ctranslate2 Support for DeltaLM
|
|
1
|
290
|
June 22, 2023
|
Correct settings when source word features
|
|
0
|
300
|
June 20, 2023
|
cTranslated Falcon-7B on OpenNMT-py server
|
|
1
|
373
|
June 17, 2023
|
Wav2vec2 support in CTranslate2
|
|
0
|
317
|
June 16, 2023
|
I want to run in gpu but actually it runs in cpu
|
|
1
|
307
|
June 16, 2023
|
Worse performance with different CTranslate2 quantization types
|
|
2
|
462
|
June 14, 2023
|
ValueError: not enough values to unpack (expected 2, got 1)
|
|
4
|
3169
|
June 14, 2023
|
Incorporating Linguistic Features in Training Data?
|
|
4
|
246
|
June 13, 2023
|
ValueError: shuffle_buffer_size < 0 is not compatible with weighted datasets
|
|
1
|
218
|
June 13, 2023
|
List index out of range while training a model using Opennmt-py
|
|
1
|
322
|
June 9, 2023
|