test

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.jsonl filter=lfs diff=lfs merge=lfs -text

app.py

@@ -2,12 +2,14 @@ import streamlit as st
 import datasets
 from functools import partial
 
+
 data = datasets.load_dataset("json", data_files="small_test_data.jsonl")["train"].select(range(100))
 
 bad_cutoff = st.slider('Bad words cutoff', 0, 1)
 stp_cutoff = st.slider('Stop words cutoff', 0, 1)
 ppl_cutoff = st.slider('ppl cutoff', 0, 1)
 
+
 def filter_ppl(examples, invert=False):
     return [ppl < ppl_cutoff for ppl in examples["ppl"]]
 
@@ -17,4 +19,5 @@ def filter_bad(examples, invert=False):
 def filter_stp(examples, invert=False):
     return [stp > stp_cutoff for stp in examples["stop_words"]]
 
+
 st.table(data)