ShishirPatil/gorilla
[Apibench] Resume interrupted LLM generations from last generation
Aperta
#484 aperta il 24 giu 2024
apibench-datagood first issue
Metriche repository
- Star
- (12.997 stelle)
- Metriche merge PR
- (Nessuna PR mergiata in 30 g)
Descrizione
Describe the issue When we try to launch LLM generations on APIBench, if the generation is interrupted midway, currently the partial file is deleted and restart generation from start. What we should instead do is check where the generation stopped and resume from the last generated index. This is specially critical for large models where generation can take >1 hours.
ID datapoint 2. Provider: This affects all 3: TorchHub/HuggingFace/PyTorch Hub
File that needs to be edited: https://github.com/ShishirPatil/gorilla/blob/main/eval/get_llm_responses.py