Commit
•
4062100
1
Parent(s):
5693173
Update README.md
Browse files
README.md
CHANGED
|
@@ -82,11 +82,9 @@ The Beta model has been developed to excel in several different medical tasks. F
|
|
| 82 |
|
| 83 |
|
| 84 |
|
| 85 |
-
We also compared the performance of the model in the general domain, using the OpenLLM Leaderboard benchmark:
|
| 86 |
|
| 87 |
-
|
| 88 |
-
|
| 89 |
-
|
| 90 |
|
| 91 |
## Uses
|
| 92 |
|
|
@@ -276,7 +274,7 @@ The model is aligned using the Direct Preference Optimization (DPO) technique th
|
|
| 276 |
2. Red-Teaming Alignment: This step further fine-tunes the model to resist a variety of potential attacks, enhancing its robustness and security. Dataset will be shared soon. In this stage, we set the learning rate to 1e-7.
|
| 277 |
|
| 278 |
<!---
|
| 279 |
-
^^^ LINKS TO DPO DATA ^^^
|
| 280 |
-->
|
| 281 |
|
| 282 |
|
|
|
|
| 82 |
|
| 83 |
|
| 84 |
|
| 85 |
+
We also compared the performance of the model in the general domain, using the OpenLLM Leaderboard benchmark. Aloe-Beta gets competitive results with the current SOTA general models in the most used general benchmarks and outperforms the medical models:
|
| 86 |
|
| 87 |
+
|
|
|
|
|
|
|
| 88 |
|
| 89 |
## Uses
|
| 90 |
|
|
|
|
| 274 |
2. Red-Teaming Alignment: This step further fine-tunes the model to resist a variety of potential attacks, enhancing its robustness and security. Dataset will be shared soon. In this stage, we set the learning rate to 1e-7.
|
| 275 |
|
| 276 |
<!---
|
| 277 |
+
^^^ LINKS TO DPO DATA (DPO added, missing the RT^^^
|
| 278 |
-->
|
| 279 |
|
| 280 |
|