Hugging Face's logo

Spaces:
AILab-CVC
/
SEED-Bench_Leaderboard
Runtime error

App Files Community
7
tttoaster commited on
Commit
e5f747b
•
1 Parent(s): 34c7db2

Update constants.py

Browse files
Files changed (1) hide show
  1. constants.py +1 -1
constants.py CHANGED
@@ -40,7 +40,7 @@ SUBMIT_INTRODUCTION = """# Submit Precautions
40
  ```shell
41
  python eval.py --model instruct_blip --anno_path SEED-Bench.json --output-dir results
42
  ```
43
- 2. If you want to revise a model, please ensure 'Model Name Revision' align with what's in the leaderboard. For example, if you want to modify InstructBLIP's evaluation result, you need to fill in 'InstructBLIP' in 'Revision Model Name'.
44
  3. Please ensure the right link for each submission. Everyone could go to the model's repository through the model name in the leaderboard.
45
  4. If you don't want to evaluate all dimensions, not evaluated dimension performance, and its corresponding average performance will be set to 0.
46
  5. After clicking 'Submit Eval', you can click 'Refresh' to obtain the latest leaderboard.
 
40
  ```shell
41
  python eval.py --model instruct_blip --anno_path SEED-Bench.json --output-dir results
42
  ```
43
+ 2. If you want to revise a model, please ensure 'Revision Model Name' align with what's in the leaderboard. For example, if you want to modify InstructBLIP's evaluation result, you need to fill in 'InstructBLIP' in 'Revision Model Name'.
44
  3. Please ensure the right link for each submission. Everyone could go to the model's repository through the model name in the leaderboard.
45
  4. If you don't want to evaluate all dimensions, not evaluated dimension performance, and its corresponding average performance will be set to 0.
46
  5. After clicking 'Submit Eval', you can click 'Refresh' to obtain the latest leaderboard.