search

SqueezeAILab / LLM2LLM

[ACL 2024] LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement
https://arxiv.org/abs/2403.15042
MIT License
149 stars 10 forks source link

where is run_all.sh #4

Closed TTCoding closed 5 months ago

TTCoding commented 6 months ago

Thank you for open-sourcing this work . I'd like to try it on my own dataset. But I cannot find the complete running pipeline 'run_all.sh'. Is it missing?

dragon18456 commented 5 months ago

when you run generator_gsm.py, it will generate an experiment folder based on the base_path in the config here: https://github.com/SqueezeAILab/LLM2LLM/blob/main/GSM8K/config.yaml#L4. In this case, for example, there will be a folder called llama2_0.1_chatgpt_10steps_1example which will have run_all.sh inside it.