Update README.md
Browse files
README.md
CHANGED
|
@@ -19,7 +19,7 @@ license: apache-2.0
|
|
| 19 |
Tulu is a series of language models that are trained to act as helpful assistants.
|
| 20 |
Tulu V2.5 is a series of models trained using DPO and PPO starting from the [Tulu 2 suite](https://huggingface.co/collections/allenai/tulu-v2-suite-6551b56e743e6349aab45101).
|
| 21 |
This is a 70B reward model used for PPO training trained on the UltraFeedback dataset.
|
| 22 |
-
It was used to train [this](https://huggingface.co/allenai/tulu-v2.5-ppo-13b-uf-mean-70b-uf-rm) model.
|
| 23 |
|
| 24 |
For more details, read the paper:
|
| 25 |
[Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback](https://link.todo).
|
|
|
|
| 19 |
Tulu is a series of language models that are trained to act as helpful assistants.
|
| 20 |
Tulu V2.5 is a series of models trained using DPO and PPO starting from the [Tulu 2 suite](https://huggingface.co/collections/allenai/tulu-v2-suite-6551b56e743e6349aab45101).
|
| 21 |
This is a 70B reward model used for PPO training trained on the UltraFeedback dataset.
|
| 22 |
+
It was used to train [this](https://huggingface.co/allenai/tulu-v2.5-ppo-13b-uf-mean-70b-uf-rm) model, and [this](https://huggingface.co/allenai/tulu-v2.5-ppo-13b-uf-mean-70b-uf-rm-mixed-prompts) model.
|
| 23 |
|
| 24 |
For more details, read the paper:
|
| 25 |
[Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback](https://link.todo).
|