vistec-AI/thai2transformers
Pretraining transformer based Thai language models
Jupyter NotebookApache-2.0
Pinned issues
Issues
- 3
Error บน wongnai_reviews
#65 opened by peune - 2
- 0
Major, breaking refactoring to v1
#76 opened by cstorm125 - 0
Missing model_max_length in roberta config
#73 opened by ThewBear - 1
some markdown files are lost
#74 opened by GoArsenal - 11
Experiment on full set of `iapp_wiki_qa_squad`
#21 opened by cstorm125 - 2
Broken URLs
#68 opened by luangtatipsy - 1
Incorrect filename in ./scripts/downstream
#69 opened by takipipo - 0
- 0
- 0
Translate and align SQuAD 1.1 and SQuAD 2.0
#57 opened by cstorm125 - 1
- 0
Benchmark against AI4Thai
#33 opened by cstorm125 - 2
Optimize for QA performance
#40 opened by cstorm125 - 0
- 0
Source data for LegalWangchanBERTa
#48 opened by cstorm125 - 0
Documentation on HuggingFace
#18 opened by cstorm125 - 0
AutoTokenizer/Model on HuggingFace
#19 opened by cstorm125 - 1
New WangchanBERTa
#43 opened by cstorm125 - 0
Fix an issue where input tokens to the WangchanBERTa NER pipeline may be in the incorrect form
#32 opened by lalital - 2
tokenizers package conflicting
#28 opened by p4l3k1n6 - 1
- 1
Update all tokenizers to fast
#27 opened by cstorm125 - 2