COMMITS
/ eval/predict.py October 21, 2023
Y
Fix the max_num_batched_tokens error in vllm.
yizhongw committed
September 22, 2023
Y
Use fast tokenizer by default.
yizhongw committed
September 17, 2023
Y
Fix a bug in iterating in `eval/predict.py`
yizhongw committed
September 5, 2023
Y
Use dynamic function import in prediction
yizhongw committed
September 3, 2023
September 2, 2023
Y
Support LLaMa2 chat format.
yizhongw committed
August 14, 2023
Y
Add eval/predict.py for more generic use cases.
yizhongw committed