trapoom555/Language-Model-STS-CFT
Improving Text Embedding of Language Models Using Contrastive Fine-tuning
Python
Issues
- 1
Improve discoverability of your work on HF
#16 opened by NielsRogge - 1
Efficient Loss Calculation with `all_gather` to Achieve Even More Batch Size
#14 opened by trapoom555 - 0
STS Evaluation
#7 opened by trapoom555 - 3
Enlarge Batch Size Per GPU
#6 opened by trapoom555 - 1
Preprocess DataLoader with Tokenization
#10 opened by trapoom555 - 0
Add a Logging Flag Option in train.sh
#8 opened by trapoom555