Hugging Face's logo

ScalableMath
/
llemma-7b-prm-metamath-level-1to3-hf

Text Generation
Transformers
PyTorch
llama
text-generation-inference
Model card Files
xet
Community
2
zhiqings commited on
Commit
19ce69f
·
verified ·
1 Parent(s): 6d3cd9b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -1,4 +1,4 @@
1
- PRMs are trained to predict the correctness of solutions on the positions of "\n\n".
2
 
3
  Usage:
4
 
 
1
+ PRMs are trained to predict the correctness of solutions on the positions of "\n\n" and "<eos>".
2
 
3
  Usage:
4