Update README.md
Browse files
README.md
CHANGED
|
@@ -42,7 +42,7 @@ SteerLM Paper: [SteerLM: Attribute Conditioned SFT as an (User-Steerable) Altern
|
|
| 42 |
|
| 43 |
Llama3-70B-SteerLM-RM is trained with NVIDIA [NeMo-Aligner](https://github.com/NVIDIA/NeMo-Aligner), a scalable toolkit for performant and efficient model alignment. NeMo-Aligner is built using the [NeMo Framework](https://github.com/NVIDIA/NeMo) which allows for scaling training up to 1000s of GPUs using tensor, data and pipeline parallelism for all components of alignment. All of our checkpoints are cross compatible with the NeMo ecosystem, allowing for inference deployment and further customization.
|
| 44 |
|
| 45 |
-
## RewardBench LeaderBoard
|
| 46 |
|
| 47 |
|
| 48 |
| Model | Type of Model| Overall | Chat | Chat-Hard | Safety | Reasoning |
|
|
|
|
| 42 |
|
| 43 |
Llama3-70B-SteerLM-RM is trained with NVIDIA [NeMo-Aligner](https://github.com/NVIDIA/NeMo-Aligner), a scalable toolkit for performant and efficient model alignment. NeMo-Aligner is built using the [NeMo Framework](https://github.com/NVIDIA/NeMo) which allows for scaling training up to 1000s of GPUs using tensor, data and pipeline parallelism for all components of alignment. All of our checkpoints are cross compatible with the NeMo ecosystem, allowing for inference deployment and further customization.
|
| 44 |
|
| 45 |
+
## RewardBench Primary Dataset LeaderBoard
|
| 46 |
|
| 47 |
|
| 48 |
| Model | Type of Model| Overall | Chat | Chat-Hard | Safety | Reasoning |
|