YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Continual pretraining Qwen 14b on tiny-lessons (translated into Vietnamese and Chinese), and a part of mini-FLAN (translated in to Vietnamese) to help the model doing cross knowledge transfer to Vietnamese.
- Total tokens: 1.28b
- Context length: 4096
- Batch size: 1024
- Training method: Full paramater finetune
- Final training loss: 0.4818
- Data source:
- Downloads last month
- 2