Downloads · 30 days
78
20% of all-time downloads
SeqKD-gpt2-340M
MiniLLM/SeqKD-gpt2-340M
SeqKD-gpt2-340M is a text generation model from MiniLLM. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
All-time downloads
386
Public
Repo size
2.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.4 GB · 100%
At a glance
- Task
- Text Generation
- License
- apache-2.0
- Model type
- gpt2
- Access
- Public
- Created
- Sep 26, 2024
- Updated
- Sep 26, 2024
- SHA
- 4d99fc56
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
SeqKD-gpt2-340M
SeqKD-gpt2-340M is a gpt2-medium (340M) model distilled from gpt2-xlarge (1.5B) on databricks-dolly-15k with sequence-level forward KLD.
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}
}
- Task
- Text Generation
- Type
- gpt2
- License
- apache-2.0
- Languages
- en
- Created
- Sep 26, 2024
- Updated
- Sep 26, 2024