lvwerra HF staff commited on
Commit
2cce3db
β€’
1 Parent(s): fcb283e

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +8 -3
app.py CHANGED
@@ -14,14 +14,19 @@ def load_all_usernames():
14
  return usernames
15
 
16
  st.title("Am I in The Stack?")
17
- st.markdown("This tool lets you check if a repository under a given username is part of [The Stack dataset](https://huggingface.co/datasets/bigcode/the-stack).")
18
- usernames = load_all_usernames()
 
19
 
 
20
  username = st.text_input("Your GitHub Username:")
21
 
22
  if st.button("Check!"):
23
  if username in usernames:
24
  st.markdown("**Yes**, your data is in The Stack:")
25
- st.markdown("\n".join([f"`{repo_name}`" for repo_name in usernames[username]]))
 
 
 
26
  else:
27
  st.markdown("**No**, your data is not in The Stack.")
 
14
  return usernames
15
 
16
  st.title("Am I in The Stack?")
17
+ st.markdown("As part of the BigCode project, we are releasing and maintaining [The Stack](https://huggingface.co/datasets/bigcode/the-stack), a 3.1 TB dataset of permissively licensed source code in 30 programming languages. One of our goals in this project is to give the people who wrote this source code a choice as to whether or not it should be used to develop and evaluate LLMs, as we acknowledge that not all developers may wish to have their data used for that purpose.")
18
+
19
+ st.markdown("This tool lets you check if a repository under a given username is part of The Stack dataset.")
20
 
21
+ usernames = load_all_usernames()
22
  username = st.text_input("Your GitHub Username:")
23
 
24
  if st.button("Check!"):
25
  if username in usernames:
26
  st.markdown("**Yes**, your data is in The Stack:")
27
+ for repo_name in usernames[username]:
28
+ st.markdown(f"`{repo_name}`")
29
+
30
+ st.markdown("Would you like to have your data removed from future versions of The Stack? You can opt-out following the instructions [here](https://www.bigcode-project.org/docs/about/the-stack/#how-can-i-request-that-my-data-be-removed-from-the-stack)")
31
  else:
32
  st.markdown("**No**, your data is not in The Stack.")