lewtun HF staff commited on
Commit
20aaf01
1 Parent(s): 33b64ec

Add description

Browse files
Files changed (1) hide show
  1. app.py +10 -0
app.py CHANGED
@@ -80,6 +80,16 @@ def format_submissions(submissions):
80
  ###########
81
  st.set_page_config(layout="wide")
82
  st.title("RAFT Leaderboard")
 
 
 
 
 
 
 
 
 
 
83
  submissions = download_submissions()
84
  df = format_submissions(submissions)
85
  # hack to remove index column from https://github.com/streamlit/streamlit/issues/641
80
  ###########
81
  st.set_page_config(layout="wide")
82
  st.title("RAFT Leaderboard")
83
+ st.markdown("""
84
+ RAFT: Real-world Annotated Few-shot Tasks
85
+
86
+ Large pre-trained language models have shown promise for few-shot learning, completing text-based tasks given only a few task-specific examples. Will models soon solve classification tasks that have so far been reserved for human research assistants? RAFT is a few-shot classification benchmark that tests language models
87
+ across multiple domains (lit review, tweets, customer interaction, etc.)
88
+ on economically valuable classification tasks (someone inherently cares about the task)
89
+ in a setting that mirrors deployment (50 examples per task, info retrieval allowed, hidden test set)
90
+
91
+ To submit to RAFT, follow the instruction posted on [this page](https://github.com/oughtinc/raft_submission).
92
+ """)
93
  submissions = download_submissions()
94
  df = format_submissions(submissions)
95
  # hack to remove index column from https://github.com/streamlit/streamlit/issues/641