OpenNMT/OpenNMT-py
Open Source Neural Machine Translation and (Large) Language Models in PyTorch
PythonMIT
Issues
- 1
- 1
UnicodeDecodeError: 'utf-8' codec can't decode byte 0x80 in position 55: invalid start byte
#2579 opened by fkurushin - 0
[Bug - Translation server] - Missing `tgt`param in `translator.translate` method (allows some multilingual/seq2seq models to work properly)
#2586 opened by medfreeman - 0
Supported languages
#2584 opened by Mayyarkmp - 0
Issues with Custom SentencePiece Models and Pretrained Embeddings in Training
#2582 opened by HURIMOZ - 0
- 0
- 0
Index out of range
#2580 opened by MSKantulu - 3
- 3
Custom callbacks for metrics, saving checkpoints
#2575 opened by Garfounkel - 2
(Again, but different) AssertionError: assert model_dim % head_count == 0
#2571 opened by James-Decatur - 5
Support for torch 2.2
#2560 opened by jakeBass - 2
- 1
NaN values when training big transformer model
#2559 opened by PC91 - 1
Any plan to support "mps" backend?
#2474 opened by everdark - 8
NCCL timeout with 2B+ parameter model
#2515 opened by Dagamies - 1
Supported SentencePiece parameters
#2546 opened by PC91 - 1
- 3
Speech to Text Toy Data Could Not Be Downloaded
#2554 opened by Keram-Yasin - 1
Translation API Not Working
#2555 opened by Keram-Yasin - 0
List index out of range in onmt.utils.distributed.all_reduce_and_rescale_tensors:51
#2549 opened by alexis-allemann - 1
Error evaluating LM-prior checkpoint:
#2541 opened by anthdr - 1
Error message of `SequenceTooLongError`
#2522 opened by PC91 - 1
Bug when training encoder-decoder models
#2528 opened by JOHW85 - 2
Data generation when resuming from a checkpoint
#2517 opened by PC91 - 1
Input size mismatch
#2519 opened by pranjaliseth - 1
set random seed for a multi-GPU model
#2516 opened by Galaxy-Husky - 1
transforms: filtertoolong failed in translating
#2501 opened by ares89 - 7
- 3
- 0
Columns and DataType Not Explicitly Set on line 163 of run_mmlu_opennmt.py
#2510 opened by CodeSmileBot - 4
bash: scripts/onmt/train.sh: No such file or directory
#2502 opened by Armilius - 5
[help] onmt.inputters.text_dataset
#2482 opened by timon49 - 18
Maybe exist some bug in attn_debug function in vesion 3,
#2490 opened by zw-SIMM - 2
Is it a requirement for the parallel training corpus to be 100% strictly correspondent paraghaph by paragraph?
#2488 opened by fishfree - 1
The result of opennmt-py translate different from CTranslate2.Translator (beamsearch10)
#2483 opened by zw-SIMM - 3
Bug in Encoder-Decoder Translation models
#2468 opened by henyee - 3
Translator fails with coverage penalty enabled
#2471 opened by robertBrnnn - 0
Please delete
#2478 opened by BaGRoS - 1
Translation fails with torch<2.0
#2475 opened by robertBrnnn - 2
number of features mismatch
#2459 opened by totaltube - 3
translate only one sentence input by user.
#2461 opened by 13633491388 - 2
Can not finetune nllb-200-3.3B
#2458 opened by ILG2021 - 2
cuda out of memeory
#2456 opened by Mamooshe - 1
Some questions about fine-tune nllb-200
#2457 opened by ILG2021 - 8
Confusion about grad and loss computation in distributed multi-gpu training
#2451 opened by Galaxy-Husky - 2
ValueError on calling onmt_translate
#2455 opened by Lguyogiro - 10
Question about Falcon40b result on MMLU
#2454 opened by MozerWang - 0
A question about “world_size” and "gpu_rank"
#2453 opened by fdggdfgg - 9
some problem about "-world-size" and "gpu_ranks"
#2450 opened by fdggdfgg