license, datasets, language, metrics, base_model, pipeline_tag
license datasets language metrics base_model pipeline_tag
apache-2.0
databricks/databricks-dolly-15k
en
rouge
facebook/opt-6.7B
text-generation

SFT-OPT-6.7B

paper | code

SFT-OPT-6.7B is an OPT-6.7B model supervised fine-tuned on databricks-dolly-15k.

It is used as a baseline for MiniLLM.

Other Baselines

Citation

@inproceedings{minillm,
  title={MiniLLM: Knowledge Distillation of Large Language Models},
  author={Gu, Yuxian and Dong, Li and Wei, Furu and Huang, Minlie},
  booktitle={Proceedings of ICLR},
  year={2024}
}
Description
Model synced from source: MiniLLM/SFT-OPT-6.7B
Readme 1.3 MiB
Languages
Text 100%