Update README.md
Browse files
README.md
CHANGED
|
@@ -7,8 +7,6 @@ language:
|
|
| 7 |
---
|
| 8 |
This is a model released for our paper: [REBEL: Reinforcement Learning via Regressing Relative Rewards](https://arxiv.org/abs/2404.16767).
|
| 9 |
|
| 10 |
-
Please refer to our [repository](https://github.com/ZhaolinGao/REBEL) for more details.
|
| 11 |
-
|
| 12 |
# REBEL-Llama-3
|
| 13 |
|
| 14 |
This model is developed with [REBEL](https://arxiv.org/abs/2404.16767) based on [Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) with [FsfairX-LLaMA3-RM-v0.1](https://huggingface.co/sfairXC/FsfairX-LLaMA3-RM-v0.1) as the reward model and [UltraFeedback](https://huggingface.co/datasets/openbmb/UltraFeedback) dataset.
|
|
|
|
| 7 |
---
|
| 8 |
This is a model released for our paper: [REBEL: Reinforcement Learning via Regressing Relative Rewards](https://arxiv.org/abs/2404.16767).
|
| 9 |
|
|
|
|
|
|
|
| 10 |
# REBEL-Llama-3
|
| 11 |
|
| 12 |
This model is developed with [REBEL](https://arxiv.org/abs/2404.16767) based on [Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) with [FsfairX-LLaMA3-RM-v0.1](https://huggingface.co/sfairXC/FsfairX-LLaMA3-RM-v0.1) as the reward model and [UltraFeedback](https://huggingface.co/datasets/openbmb/UltraFeedback) dataset.
|