MiniLLM-OPT-2.7B – AI Model by MiniLLM | AlphaNeural AI

You can deploy this model and start earning money today!

MiniLLM/
MiniLLM-OPT-2.7B

like

0

text-generation

databricks/databricks-dolly-15k

facebook/opt-2.7b

Views

No views yet

MiniLLM-OPT-2.7B

MiniLLM-OPT-2.7B is an OPT-2.7B model distilled from OPT-13B on databricks-dolly-15k

Note: MiniLLM requires an SFT model for initilization to perform the PPO optimization.

Evaluation

We ask GPT-4 to give scores for the generated responses of MiniLLM. The prompts are taken from databricks-dolly-15k (test set), self-instruct, and vicuna

Baseline Models

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}
}