Add link to paper
Browse filesThis PR makes sure the model can be discovered from https://huggingface.co/papers/2410.14940.
README.md
CHANGED
|
@@ -14,6 +14,7 @@ pipeline_tag: text-generation
|
|
| 14 |
|
| 15 |
Llama3-PBM-Nova-70B is a chat model developed by PKU-Baichuan-MLSysLab, based on the Llama3-70B. In order to better utilize open-source data, we've performed deduplication, quality filtering, and data synthesis on it. Then, through Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF), we've significantly enhanced the base model's performance.
|
| 16 |
|
|
|
|
| 17 |
- **Developed by:** [PKU-Baichuan-MLSysLab](https://github.com/PKU-Baichuan-MLSystemLab)
|
| 18 |
- **Base Model:** [Llama-3-70B](https://huggingface.co/meta-llama/Meta-Llama-3-70B)
|
| 19 |
- **Model Type:** Chat Model
|
|
|
|
| 14 |
|
| 15 |
Llama3-PBM-Nova-70B is a chat model developed by PKU-Baichuan-MLSysLab, based on the Llama3-70B. In order to better utilize open-source data, we've performed deduplication, quality filtering, and data synthesis on it. Then, through Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF), we've significantly enhanced the base model's performance.
|
| 16 |
|
| 17 |
+
- **Paper:** [Baichuan Alignment Technical Report](https://huggingface.co/papers/2410.14940)
|
| 18 |
- **Developed by:** [PKU-Baichuan-MLSysLab](https://github.com/PKU-Baichuan-MLSystemLab)
|
| 19 |
- **Base Model:** [Llama-3-70B](https://huggingface.co/meta-llama/Meta-Llama-3-70B)
|
| 20 |
- **Model Type:** Chat Model
|