Update README.md
Browse files
README.md
CHANGED
|
@@ -25,6 +25,8 @@ datasets:
|
|
| 25 |
|
| 26 |
The Nemotron-4-340B-Reward is a multi-dimensional Reward Model that can be used as part of a synthetic data generation pipeline to create training data that helps researchers and developers build their own LLMs; Nemotron-4-340B-Reward consists of the Nemotron-4-340B-Base model and a linear layer that converts the final layer representation of the end-of-response token into five scalar values, each corresponding to a [HelpSteer2](https://arxiv.org/abs/2406.08673) attribute.
|
| 27 |
|
|
|
|
|
|
|
| 28 |
It supports a context length of up to 4,096 tokens.
|
| 29 |
|
| 30 |
Given a conversation with multiple turns between user and assistant, it rates the following attributes (typically between 0 and 4) for every assistant turn.
|
|
|
|
| 25 |
|
| 26 |
The Nemotron-4-340B-Reward is a multi-dimensional Reward Model that can be used as part of a synthetic data generation pipeline to create training data that helps researchers and developers build their own LLMs; Nemotron-4-340B-Reward consists of the Nemotron-4-340B-Base model and a linear layer that converts the final layer representation of the end-of-response token into five scalar values, each corresponding to a [HelpSteer2](https://arxiv.org/abs/2406.08673) attribute.
|
| 27 |
|
| 28 |
+
Try it for free at [build.nvidia.com](https://build.nvidia.com/nvidia/nemotron-4-340b-reward) - comes with an OpenAI-compatible API interface!
|
| 29 |
+
|
| 30 |
It supports a context length of up to 4,096 tokens.
|
| 31 |
|
| 32 |
Given a conversation with multiple turns between user and assistant, it rates the following attributes (typically between 0 and 4) for every assistant turn.
|