Update README.md

README.md

@@ -1,3 +1,47 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+datasets:
+- databricks/databricks-dolly-15k
+language:
+- en
+metrics:
+- rouge
+base_model:
+- facebook/opt-1.3b
+pipeline_tag: text-generation
+---
+# MiniLLM-OPT-1.3B
+
+[paper](https://arxiv.org/abs/2306.08543) | [code](https://github.com/microsoft/LMOps/tree/main/minillm)
+
+**MiniLLM-OPT-1.3B** is a OPT-1.3B model distilled from [OPT-13B](https://huggingface.co/MiniLLM/teacher-OPT-13B) on [databricks-dolly-15k](https://huggingface.co/datasets/aisquared/databricks-dolly-15k)
+
+<p align='left'>
+    <img src="https://cdn-uploads.huggingface.co/production/uploads/624ac662102fcdff87be51b9/7hBWGZzYMJihCRQ70XoiQ.png" width="1000">
+</p>
+
+**Note**: MiniLLM requires an [SFT model](https://huggingface.co/MiniLLM/init-opt-1.3B) 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](https://huggingface.co/datasets/aisquared/databricks-dolly-15k) (test set), [self-instruct](https://github.com/tatsu-lab/stanford_alpaca/blob/main/alpaca_data.json), and [vicuna](https://github.com/lm-sys/vicuna-blog-eval)
+
+<p align='left'>
+    <img src="https://cdn-uploads.huggingface.co/production/uploads/624ac662102fcdff87be51b9/rDXnaDbKH5mBYAmqGC-_a.png" width="1000">
+</p>
+
+## Baseline Models
++ [SFT w/o KD](https://huggingface.co/MiniLLM/SFT-opt-1.3B)
++ [KD](https://huggingface.co/MiniLLM/KD-opt-1.3B)
++ [SeqKD](https://huggingface.co/MiniLLM/SeqKD-opt-1.3B)
+
+
+## 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}
+}
+```