Commit
•
ec2726b
1
Parent(s):
ba7015e
End of training
Browse files
README.md
CHANGED
|
@@ -28,7 +28,7 @@ print(output["generated_text"][1]["content"])
|
|
| 28 |
|
| 29 |
## Training procedure
|
| 30 |
|
| 31 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/huggingface/huggingface/runs/
|
| 32 |
|
| 33 |
This model was trained with XPO, a method introduced in [Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF](https://huggingface.co/papers/2405.21046).
|
| 34 |
|
|
@@ -57,7 +57,6 @@ Cite XPO as:
|
|
| 57 |
Cite TRL as:
|
| 58 |
|
| 59 |
```bibtex
|
| 60 |
-
|
| 61 |
@misc{vonwerra2022trl,
|
| 62 |
title = {{TRL: Transformer Reinforcement Learning}},
|
| 63 |
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
|
|
@@ -66,5 +65,4 @@ Cite TRL as:
|
|
| 66 |
publisher = {GitHub},
|
| 67 |
howpublished = {\url{https://github.com/huggingface/trl}}
|
| 68 |
}
|
| 69 |
-
|
| 70 |
```
|
|
|
|
| 28 |
|
| 29 |
## Training procedure
|
| 30 |
|
| 31 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/huggingface/huggingface/runs/erixlr9e)
|
| 32 |
|
| 33 |
This model was trained with XPO, a method introduced in [Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF](https://huggingface.co/papers/2405.21046).
|
| 34 |
|
|
|
|
| 57 |
Cite TRL as:
|
| 58 |
|
| 59 |
```bibtex
|
|
|
|
| 60 |
@misc{vonwerra2022trl,
|
| 61 |
title = {{TRL: Transformer Reinforcement Learning}},
|
| 62 |
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
|
|
|
|
| 65 |
publisher = {GitHub},
|
| 66 |
howpublished = {\url{https://github.com/huggingface/trl}}
|
| 67 |
}
|
|
|
|
| 68 |
```
|