Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,29 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- databricks/databricks-dolly-15k
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
metrics:
|
| 8 |
+
- rouge
|
| 9 |
+
base_model:
|
| 10 |
+
- openai-community/gpt2-large
|
| 11 |
+
pipeline_tag: text-generation
|
| 12 |
+
---
|
| 13 |
+
# init-gpt2-760M
|
| 14 |
+
|
| 15 |
+
[paper](https://arxiv.org/abs/2306.08543) | [code](https://github.com/microsoft/LMOps/tree/main/minillm)
|
| 16 |
+
|
| 17 |
+
**init-gpt2-760M** is a gpt2 (760M) model supervised fine-tuned on [databricks-dolly-15k](https://huggingface.co/datasets/aisquared/databricks-dolly-15k).
|
| 18 |
+
|
| 19 |
+
It is used as the initialization for training [MiniLLM](https://huggingface.co/MiniLLM/MiniLLM-gpt2-760M).
|
| 20 |
+
|
| 21 |
+
## Citation
|
| 22 |
+
```
|
| 23 |
+
@inproceedings{minillm,
|
| 24 |
+
title={MiniLLM: Knowledge Distillation of Large Language Models},
|
| 25 |
+
author={Gu, Yuxian and Dong, Li and Wei, Furu and Huang, Minlie},
|
| 26 |
+
booktitle={Proceedings of ICLR},
|
| 27 |
+
year={2024}
|
| 28 |
+
}
|
| 29 |
+
```
|