Text Generation
PyTorch
Safetensors
English
gpt2
init-gpt2-120M / README.md
t1101675's picture
Update README.md
7a5aa64 verified
|
raw
history blame
788 Bytes
metadata
license: apache-2.0
datasets:
  - databricks/databricks-dolly-15k
language:
  - en
metrics:
  - rouge
base_model:
  - openai-community/gpt2
pipeline_tag: text-generation

init-gpt2-120M

paper | code

init-gpt2-120M is a gpt2 (120M) model supervised fine-tuned on databricks-dolly-15k.

It is used as the initialization for training MiniLLM.

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}
}