ShishirPatil/gorilla

[Apibench] Resume interrupted LLM generations from last generation

Aberta

#484 aberto em 24 de jun. de 2024

 (1 comentário) (0 reação) (0 responsável)Python (1.399 forks)batch import
apibench-datagood first issue

Métricas do repositório

Stars
 (13.001 estrelas)
Métricas de merge de PR
 (Nenhuma PRs mesclada em 30d)

Description

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

Guia do colaborador