Update README.md
Browse files
README.md
CHANGED
|
@@ -5,6 +5,7 @@ language:
|
|
| 5 |
---
|
| 6 |
|
| 7 |
GPT-J (with value head weights) trained on HH with PPO following @reciprocate's `trlx` example https://github.com/CarperAI/trlx/blob/2f90ba0ecd640ae18cd62adb5e934a4b779f534b/examples/hh/ppo_hh.py
|
|
|
|
| 8 |
Logs: https://wandb.ai/jon-tow/trlx/reports/hh-gpt-j--VmlldzozODE1NjAw
|
| 9 |
|
| 10 |
Usage:
|
|
|
|
| 5 |
---
|
| 6 |
|
| 7 |
GPT-J (with value head weights) trained on HH with PPO following @reciprocate's `trlx` example https://github.com/CarperAI/trlx/blob/2f90ba0ecd640ae18cd62adb5e934a4b779f534b/examples/hh/ppo_hh.py
|
| 8 |
+
|
| 9 |
Logs: https://wandb.ai/jon-tow/trlx/reports/hh-gpt-j--VmlldzozODE1NjAw
|
| 10 |
|
| 11 |
Usage:
|