Update README.md
Browse files
README.md
CHANGED
|
@@ -26,7 +26,7 @@ By accessing this model, you are agreeing to the LLama 3.1 terms and conditions
|
|
| 26 |
|
| 27 |
## RewardBench Primary Dataset LeaderBoard
|
| 28 |
|
| 29 |
-
Llama-3.1-Nemotron-70B-Reward performs best Overall on RewardBench as well as in Chat, Safety and Reasoning category.
|
| 30 |
|
| 31 |
| Model | Type of Data Used For Training | Overall | Chat | Chat-Hard | Safety | Reasoning |
|
| 32 |
|:-----------------------------|:----------------|:-----|:----------|:-------|:----------|:-----------------------|
|
|
@@ -57,8 +57,6 @@ On the other hand, when GPT-4 annotations are used as Ground-Truth, we trail sub
|
|
| 57 |
| Skywork-Reward-Gemma-2-27B | Includes GPT4 Generated Data | 91.4 | 78.3 | 89.6 | 96.0 | 97.8 | 91.5 | 86.5|
|
| 58 |
|
| 59 |
|
| 60 |
-
Last updated: 27 Sept 2024
|
| 61 |
-
|
| 62 |
## Usage:
|
| 63 |
|
| 64 |
You can use the model with [NeMo Aligner](https://github.com/NVIDIA/NeMo-Aligner) following [SteerLM training user guide](https://docs.nvidia.com/nemo-framework/user-guide/latest/modelalignment/steerlm.html).
|
|
|
|
| 26 |
|
| 27 |
## RewardBench Primary Dataset LeaderBoard
|
| 28 |
|
| 29 |
+
As of 27 Sept 2024, Llama-3.1-Nemotron-70B-Reward performs best Overall on RewardBench as well as in Chat, Safety and Reasoning category.
|
| 30 |
|
| 31 |
| Model | Type of Data Used For Training | Overall | Chat | Chat-Hard | Safety | Reasoning |
|
| 32 |
|:-----------------------------|:----------------|:-----|:----------|:-------|:----------|:-----------------------|
|
|
|
|
| 57 |
| Skywork-Reward-Gemma-2-27B | Includes GPT4 Generated Data | 91.4 | 78.3 | 89.6 | 96.0 | 97.8 | 91.5 | 86.5|
|
| 58 |
|
| 59 |
|
|
|
|
|
|
|
| 60 |
## Usage:
|
| 61 |
|
| 62 |
You can use the model with [NeMo Aligner](https://github.com/NVIDIA/NeMo-Aligner) following [SteerLM training user guide](https://docs.nvidia.com/nemo-framework/user-guide/latest/modelalignment/steerlm.html).
|