Welcome to
mirror list
, hosted at
ThFree Co
, Russian Federation.
github.com/OpenNMT/CTranslate2.git - Unnamed repository; edit this file 'description' to name the repository.
index
:
github.com/OpenNMT/CTranslate2.git
gh-pages
master
r1.10
r1.17
r1.6
r1.7
r1.9
r2.3
Unnamed repository; edit this file 'description' to name the repository.
www-data
summary
refs
log
tree
commit
diff
log msg
author
committer
range
Age
Commit message (
Expand
)
Author
2022-07-29
Bump version to 2.21.1
v2.21.1
Guillaume Klein
2022-07-29
Fix conversion of NLLB models without tokenizer_class in config (#889)
Guillaume Klein
2022-07-29
Update version of action pypa/gh-action-pypi-publish
Guillaume Klein
2022-07-27
Bump version to 2.21.0
v2.21.0
Guillaume Klein
2022-07-27
Add support for NLLB multilingual models (#878)
Guillaume Klein
2022-07-27
Fix FP16 dtype error with return_alternatives + return_attention (#884)
Guillaume Klein
2022-07-27
Add conversion for Pegasus summarization models (#883)
Guillaume Klein
2022-07-21
Do not stop decoding when EOS is coming from the user input (#880)
Guillaume Klein
2022-07-21
Update pybind11 to 2.10.0 (#881)
Guillaume Klein
2022-07-21
Update cibuildwheel to 2.8.1 (#882)
Guillaume Klein
2022-07-19
Remove checks for old Intel MKL versions (#875)
Guillaume Klein
2022-07-18
Add conversion test for OpenNMT-py's transformer_lm (#874)
Guillaume Klein
2022-07-18
Fix converter relative position propagation in opennmt-py lm converter (#873)
Valentin Berkes
2022-07-15
Add missing docstring for parameter read_batch_size (#872)
Guillaume Klein
2022-07-15
Remove non needed register_variable_alias override
Guillaume Klein
2022-07-15
Minor fix in environment variables documentation
Guillaume Klein
2022-07-15
Fix extra character in documentation file
Guillaume Klein
2022-07-15
Fix linear layers fusion without bias (#871)
Guillaume Klein
2022-07-14
Fix missing processing of linear weights in language models (#869)
Guillaume Klein
2022-07-13
Keep test parameters close to the test case
Guillaume Klein
2022-07-12
Compute d_model from the linear layer output, not from the layer norm
Guillaume Klein
2022-07-12
Do not check model arguments for unsupported Fairseq models (#868)
Guillaume Klein
2022-07-08
Vectorize GELU operator on CPU (#823)
Guillaume Klein
2022-07-06
Bump version to 2.20.0
v2.20.0
Guillaume Klein
2022-07-06
Fix application of max_decoding_length in return_alternatives mode (#866)
Guillaume Klein
2022-07-06
Update PyPI classifiers with supported CUDA versions
Guillaume Klein
2022-07-06
Remove <pad> token when converting MarianMT models (#865)
Guillaume Klein
2022-07-06
Highlight important note in Transformers guide
Guillaume Klein
2022-07-05
Fix asynchronous result state when a runtime exception is raised (#864)
Guillaume Klein
2022-07-04
Do not modify config passed to OpenNMTTFConverterV2.from_config (#863)
Guillaume Klein
2022-07-04
List class members at the top of the class documentation (#861)
Guillaume Klein
2022-07-04
Update FasterTransformer to 5.0 in benchmark script (#860)
Guillaume Klein
2022-06-30
Prevent setting new attributes in layer specifications (#859)
Guillaume Klein
2022-06-30
Vectorize accumulator horizontal reduction (#855)
Guillaume Klein
2022-06-30
Add option no_repeat_ngram_size to prevent repetitions of ngrams (#854)
Guillaume Klein
2022-06-30
Remove unnecessary libomp installation command on macOS (#857)
Guillaume Klein
2022-06-30
Fix conversion of OpenNMT-tf models using static position embeddings (#858)
Guillaume Klein
2022-06-30
Pin PyTorch version for the macOS Python tests (#856)
Guillaume Klein
2022-06-28
Update Ubuntu and macOS versions used on GitHub runners (#852)
Guillaume Klein
2022-06-23
Bump version to 2.19.1
v2.19.1
Guillaume Klein
2022-06-23
Minor change in device_index docstring
Guillaume Klein
2022-06-23
Add missing final layer norm in OPT model (#850)
Guillaume Klein
2022-06-23
Check if relative position is used directly from the attention layer (#849)
Guillaume Klein
2022-06-21
Keep verbose mode enabled for Transformers' tokenizer (#848)
Guillaume Klein
2022-06-21
Factorize layer creation (#846)
Guillaume Klein
2022-06-20
Do not pass EmbeddingsSpec modules to the base classes
Guillaume Klein
2022-06-20
Define float16_t type in public headers (#841)
Guillaume Klein
2022-06-20
Do not mark relative position as optional when they are required (#844)
Guillaume Klein
2022-06-20
Remove attribute multiply_by_sqrt_depth that is no longer set (#843)
Guillaume Klein
2022-06-20
Fix conversion of OpenNMT-tf V1 checkpoints with the new converter (#845)
Guillaume Klein
[next]