microsoft MASS issues - Githubissues

microsoft / MASS

MASS: Masked Sequence to Sequence Pre-training for Language Generation

https://arxiv.org/pdf/1905.02450.pdf

Other

1.11k stars 206 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

who can share the model with me

#183 icegomic opened 11 months ago
0
This repo is missing important files

#182 microsoft-github-policy-service[bot] closed 1 year ago
2
Adding Microsoft SECURITY.MD

#181 microsoft-github-policy-service[bot] closed 1 year ago
0
Where is the file "fairseq-preprocess"

#180 xcssgzs opened 2 years ago
0
Does mass implement the translate method？

#179 mqy9787 opened 2 years ago
1
how can you get the data for MASS supNMT?

#178 xiuzhilu opened 2 years ago
0
supNMT pre-train problem with multi gpus

#177 Andrewlesson opened 2 years ago
1
How does MASS supervised machine translation perform preprocessing?

#176 IdaBetsy opened 2 years ago
0
Mass_unsup has no problem on a single GPU, and errors are reported on multiple GPUs

#175 MayDomine closed 2 years ago
0
invalid task choice

#174 yaocheng95 closed 3 years ago
0
Translation results on Zh-En pre-trained model

#173 riddlehk opened 3 years ago
0
How to create dictionary dict.lg.txt in MASS supNMT

#172 Ashmari opened 3 years ago
0
Question about data processing in Unsupervised NMT

#171 ElliottYan opened 3 years ago
0
Questions for SupNMT

#170 MSWon opened 3 years ago
0
Predictions on XSUM?

#169 danyaljj opened 3 years ago
0
Question towards the Pre-trained weight for the Neural Machine Translation under supNMT

#168 MichaelCaohn opened 3 years ago
0
How to create dictionary dict.lg.txt

#167 abdullahkhilji opened 3 years ago
0
Incorrect dictionary format

#166 abdullahkhilji opened 3 years ago
3
Do two direction data for parallel data is necessary?

#165 SefaZeng opened 3 years ago
0
Confusion regarding data

#164 kr-sundaram opened 3 years ago
1
Quick question about "masked_block_start"

#163 Derekkk closed 3 years ago
1
Problem while running Supervised NMT

#162 RachitBansal opened 3 years ago
2
Question of pretraining text-generation task, it seems that pretraining is not work for a small model?

#161 guotong1988 closed 3 years ago
3
Confusion about the amount of monolingual data used in the experiments

#160 cbaziotis opened 3 years ago
1
Fixes `value_error low >= high`

#159 leloykun opened 3 years ago
0
per-training BlUE always 0.0000

#158 Nanamumuhan opened 3 years ago
1
data/processed/en-fr/train.en.pth valid.en.pth. test.en.pth..........

#157 bozhenhhu closed 3 years ago
0
What is the difference between pretrain-tensor2tensor and MASS?

#156 guotong1988 closed 3 years ago
5
Will BERT+transformer-decoder better than tensor2tensor for text-generation?

#155 guotong1988 closed 3 years ago
1
How to reload checkpoint for UNMT?

#154 him-mah10 closed 4 years ago
8
Unable to load Zh-En Pre-trained Model for fine-tuning

#153 riddlehk opened 4 years ago
1
Update README w/ command for distributed training

#152 thammegowda closed 4 years ago
0
.

#151 masonreznov closed 3 years ago
0
Experiment setting for Multilingual pretraining and Supervised NMT

#150 renziver closed 4 years ago
1
Questions on Table 3 of the MASS paper?

#149 Epsilon-Lee opened 4 years ago
2
Fine Tuning with MBART pretrained model

#148 masonreznov closed 4 years ago
0
how to preprocess data and use the finetuned model ?

#147 15091444119 closed 4 years ago
1
error in running training script for pre-training multiple monolingual data

#146 renziver closed 4 years ago
0
Script breaks on whitespace directory!!!

#145 masonreznov closed 1 year ago
0
is it typo in README (Fine-tuning (CNN / Daily Mail))?

#144 SoyChae closed 3 years ago
1
How to use MASS for Style Transfer?

#143 him-mah10 closed 4 years ago
2
unable to set a proper batch_size in MASS-supNMT pretraining

#142 vikrant97 closed 4 years ago
2
Fail to Reproduce the Result of UnsupMT-EnDe

#141 LibertFan closed 4 years ago
3
Outputs of summarization task

#140 shahbazsyed closed 4 years ago
1
MASS-supNMT: Args say word_mask_keep_rand but code is word_mask_rand_keep

#139 JasonVann opened 4 years ago
0
In text summarization

#138 KawhiZhao closed 3 years ago
2
How to implement fine-tuned model by myself?

#137 kaneyxx opened 4 years ago
1
Hyperparameter for low-resource experiment

#136 yukiyakiZ opened 4 years ago
0
How to prepare data pipeline and utilize the provided BPE codes?

#135 liuchongming74 closed 4 years ago
3
How many Gpu needed for Text Summarization of CNNDM fine-tuning ?

#134 fseasy closed 4 years ago
2