Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / Jingjing-NLP/VOLT issues and pull requests
#31 - Only vocab = vocab[:optimal_size]?
Issue -
State: open - Opened by hitcslj 3 months ago
- 2 comments
#30 - SentencePiece .vocab file lacks frequency information
Issue -
State: open - Opened by hitcslj 3 months ago
- 1 comment
#29 - Is it applicable to Large Language Models as well?
Issue -
State: open - Opened by ericxsun about 1 year ago
#28 - RuntimeWarning: overflow encountered in true_divide
Issue -
State: open - Opened by andmek about 2 years ago
#27 - Reproducibility Study pt II
Issue -
State: open - Opened by KyraGolden almost 3 years ago
#26 - Reproducibility Study
Issue -
State: open - Opened by KyraGolden almost 3 years ago
- 2 comments
#25 - "../ot_run.py", line 107, in write_vocab
Issue -
State: open - Opened by Timaos123 about 3 years ago
- 2 comments
#24 - fixed scripts for sentencepiece
Pull Request -
State: open - Opened by xinyiz1019 over 3 years ago
#23 - Error when generating Sentencepiece vocab
Issue -
State: open - Opened by Aiden-Frost over 3 years ago
#22 - 标点符号的问题
Issue -
State: closed - Opened by andongBlue over 3 years ago
- 1 comment
#21 - Scripts for MUV-search
Issue -
State: closed - Opened by Saltychtao over 3 years ago
- 2 comments
#20 - What exactly is V_S[t]?
Issue -
State: open - Opened by kirefu over 3 years ago
- 9 comments
#19 - questions about sentencepiece method learned vocab
Issue -
State: open - Opened by dearchill over 3 years ago
- 3 comments
#18 - How can I use SentencePiece to generate vocb
Issue -
State: closed - Opened by andongBlue over 3 years ago
- 3 comments
#17 - run_ot and run_ot_write
Issue -
State: closed - Opened by kirefu over 3 years ago
- 4 comments
#16 - The D matrix
Issue -
State: open - Opened by kirefu over 3 years ago
- 9 comments
#15 - Confused about subword-nmt style output
Issue -
State: closed - Opened by bbo0924 over 3 years ago
- 1 comment
#14 - 弱问下,VOLT对比 直接按词频过滤后的vocab的baseline,是论文哪个图?感谢!
Issue -
State: open - Opened by guotong1988 over 3 years ago
- 2 comments
#13 - 关于VOLT生成的词表
Issue -
State: open - Opened by TomasAndersonFang over 3 years ago
- 1 comment
#12 - add support for gpt byte-bpe?
Issue -
State: closed - Opened by nlpcat over 3 years ago
- 1 comment
#11 - > 请问你在测试zh-en的过程中,也是按照这样去cat zh en 训练文件吗?
Issue -
State: closed - Opened by hnlp1993 over 3 years ago
#10 - 请问一下,如何理解熵随着vocabulary size的增加而减少
Issue -
State: open - Opened by leoozy over 3 years ago
- 5 comments
#9 - I found that VOLT can indeed effectively reduce the size of BPE vocabulary, but it may damage the performance of the model in practice
Issue -
State: open - Opened by MarsPain over 3 years ago
- 14 comments
#8 - Missing `ted/onemanydata` data?
Issue -
State: closed - Opened by tiendung over 3 years ago
- 1 comment
#7 - Are there any recommended hyperparameters for a larger dataset?
Issue -
State: closed - Opened by SefaZeng over 3 years ago
- 3 comments
#6 - Paper Issue for relaxed constraints
Issue -
State: closed - Opened by hscspring over 3 years ago
#5 - --vocab_file
Issue -
State: closed - Opened by hnlp1993 over 3 years ago
- 1 comment
#4 - Write output of target to bpeoutput/target.file
Pull Request -
State: closed - Opened by veer66 over 3 years ago
#3 - Got error while running training script
Issue -
State: open - Opened by tiendung over 3 years ago
- 9 comments
#1 - 您好,我想请问一下ot_run.py里几个参数的含义
Issue -
State: closed - Opened by q178 over 3 years ago
- 2 comments