Update README.md
Browse files
README.md
CHANGED
|
@@ -9,7 +9,7 @@ April 17, 2024
|
|
| 9 |
|
| 10 |
Felix-8B-v2 is an experimental language model developed by Ontocord.ai, specializing in addressing lawfulness concerns under the Biden-Harris Executive Order on AI and the principles of the EU AI Act. This model has achieved one of the highest scores on the TruthfulQA benchmark compared to models of its size, showcasing its exceptional performance in providing accurate and reliable responses.
|
| 11 |
Felix-8B-v2 is **experimental and a research work product** and a DPO reinforcement learning version of [ontocord/sft-4e-exp2](https://huggingface.co/ontocord/sft-4e-exp2) which in turn is a fine-tuned version of [TencentARC/Mistral_Pro_8B_v0.1](https://huggingface.co/TencentARC/Mistral_Pro_8B_v0.1).
|
| 12 |
-
|
| 13 |
|
| 14 |
This model is exactly the same as [Felix-8B](https://huggingface.co/ontocord/Felix-8B) except we modified the ``</s>`` and ``<s>`` tags of the original Felix-8b DPO model to fix the issue of being too verbose.
|
| 15 |
|
|
|
|
| 9 |
|
| 10 |
Felix-8B-v2 is an experimental language model developed by Ontocord.ai, specializing in addressing lawfulness concerns under the Biden-Harris Executive Order on AI and the principles of the EU AI Act. This model has achieved one of the highest scores on the TruthfulQA benchmark compared to models of its size, showcasing its exceptional performance in providing accurate and reliable responses.
|
| 11 |
Felix-8B-v2 is **experimental and a research work product** and a DPO reinforcement learning version of [ontocord/sft-4e-exp2](https://huggingface.co/ontocord/sft-4e-exp2) which in turn is a fine-tuned version of [TencentARC/Mistral_Pro_8B_v0.1](https://huggingface.co/TencentARC/Mistral_Pro_8B_v0.1).
|
| 12 |
+
Felix-8B was DPO trained on our synthetically generated dataset [Auto Redteam Triplets (ART): a synthetic dataset to perform reinforcement learning redteaming for the EU AI Act and Biden-Harris AI Executive Order concerns](ontocord/auto_redteam_triplets).
|
| 13 |
|
| 14 |
This model is exactly the same as [Felix-8B](https://huggingface.co/ontocord/Felix-8B) except we modified the ``</s>`` and ``<s>`` tags of the original Felix-8b DPO model to fix the issue of being too verbose.
|
| 15 |
|