Text Generation
NeMo
English
nvidia
steerlm
llama2
reward model
wgao2021 commited on
Commit
fdfc8b1
1 Parent(s): 97a3289

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -35,7 +35,7 @@ Given a conversation with multiple turns between user and assistant, it rates th
35
  8. **Complexity**: Intellectual depth required to write response (i.e. whether the response can be written by anyone with basic language competency or requires deep domain expertise).
36
  9. **Verbosity**: Amount of detail included in the response, relative to what is asked for in the prompt.
37
 
38
- The first four attrubutes are taken from the [Open Assistant](https://huggingface.co/datasets/OpenAssistant/oasst1) dataset while the others are taken from [HelpSteer](https://huggingface.co/datasets/nvidia/HelpSteer) dataset
39
 
40
 
41
  HelpSteer Paper : [HelpSteer: Multi-attribute Helpfulness Dataset for SteerLM](http://arxiv.org/abs/2311.09528)
 
35
  8. **Complexity**: Intellectual depth required to write response (i.e. whether the response can be written by anyone with basic language competency or requires deep domain expertise).
36
  9. **Verbosity**: Amount of detail included in the response, relative to what is asked for in the prompt.
37
 
38
+ The first four attributes are taken from the [Open Assistant](https://huggingface.co/datasets/OpenAssistant/oasst1) dataset while the others are taken from [HelpSteer](https://huggingface.co/datasets/nvidia/HelpSteer) dataset
39
 
40
 
41
  HelpSteer Paper : [HelpSteer: Multi-attribute Helpfulness Dataset for SteerLM](http://arxiv.org/abs/2311.09528)