NeMo
English
nvidia
llama3.1
reward model
zhilinw commited on
Commit
290dce2
·
verified ·
1 Parent(s): 057236d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -186,7 +186,7 @@ v1.0
186
  * [HelpSteer2](https://huggingface.co/datasets/nvidia/HelpSteer2)
187
 
188
  **Properties (Quantity, Dataset Descriptions, Sensor(s)):** <br>
189
- * 37,120 prompt-responses built to make more models more aligned with human preference - specifically more helpful, factually-correct, coherent, and customizable based on complexity and verbosity.
190
 
191
 
192
  # Inference:
 
186
  * [HelpSteer2](https://huggingface.co/datasets/nvidia/HelpSteer2)
187
 
188
  **Properties (Quantity, Dataset Descriptions, Sensor(s)):** <br>
189
+ * Built to make more models more aligned with human preference - specifically more helpful, factually-correct, coherent, and customizable based on complexity and verbosity.
190
 
191
 
192
  # Inference: