Hugging Face's logo

vikp
/
instruct_rater

Text Classification
Transformers
PyTorch
gpt_neox
Model card Files
xet
 Community
1
vikp commited on
Commit
6346687
·
1 Parent(s): 28c1fff

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -6,7 +6,7 @@ This model judges if a given output is sufficient to recreate a given instructio
6
 
7
  It's useful for filtering data to train a reverse instruct model. It could also have applications around determining if an output/instruction pair is linked, or around quality filtering data (data where the instruction can be recreated from the output might be higher quality).
8
 
9
- The model is a binary classifier trained on top of Python 160m with 50k examples for 1 epoch. The final validation loss is .35. You can see an example of a dataset filtered with this model [here](https://huggingface.co/datasets/vikp/reverse_instruct).
10
 
11
  To use it, pass in this prompt format:
12
 
 
6
 
7
  It's useful for filtering data to train a reverse instruct model. It could also have applications around determining if an output/instruction pair is linked, or around quality filtering data (data where the instruction can be recreated from the output might be higher quality).
8
 
9
+ The model is a binary classifier trained on top of Python 410m with 100k examples for 1 epoch. The final validation loss is .35. You can see an example of a dataset filtered with this model [here](https://huggingface.co/datasets/vikp/reverse_instruct).
10
 
11
  To use it, pass in this prompt format:
12