Update README.md

README.md

@@ -4,9 +4,10 @@ language:
 - en
 ---
 
-GPT-J (with value head weights) trained on HH with PPO following [@reciprocated's](https://github.com/reciprocated) `trlx` example https://github.com/CarperAI/trlx/blob/2f90ba0ecd640ae18cd62adb5e934a4b779f534b/examples/hh/ppo_hh.py
+GPT-J (with value head weights) trained on HH with PPO following [@reciprocated's](https://github.com/reciprocated) `trlx` example [here](https://github.com/CarperAI/trlx/blob/2f90ba0ecd640ae18cd62adb5e934a4b779f534b/examples/hh/ppo_hh.py)
 
-Logs: https://wandb.ai/jon-tow/trlx/reports/hh-gpt-j--VmlldzozODE1NjAw
+- Dataset: [Dahoas/full-hh-rlhf](https://huggingface.co/datasets/Dahoas/full-hh-rlhf)
+- Logs: https://wandb.ai/jon-tow/trlx/reports/hh-gpt-j--VmlldzozODE1NjAw
 
 Usage: