Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
Clean up
Browse files
README.md
CHANGED
|
@@ -20,37 +20,3 @@ tags:
|
|
| 20 |
- language:日本語
|
| 21 |
- language:Japanese
|
| 22 |
---
|
| 23 |
-
|
| 24 |
-
# Start the configuration
|
| 25 |
-
|
| 26 |
-
Most of the variables to change for a default leaderboard are in `src/env.py` (replace the path for your leaderboard) and `src/about.py` (for tasks).
|
| 27 |
-
|
| 28 |
-
Results files should have the following format and be stored as JSON files:
|
| 29 |
-
```json
|
| 30 |
-
{
|
| 31 |
-
"config": {
|
| 32 |
-
"model_dtype": "torch.float16", # or torch.bfloat16 or 8bit or 4bit
|
| 33 |
-
"model_name": "path of the model on the hub: org/model",
|
| 34 |
-
"model_sha": "revision on the hub",
|
| 35 |
-
},
|
| 36 |
-
"results": {
|
| 37 |
-
"task_name": {
|
| 38 |
-
"metric_name": score,
|
| 39 |
-
},
|
| 40 |
-
"task_name2": {
|
| 41 |
-
"metric_name": score,
|
| 42 |
-
}
|
| 43 |
-
}
|
| 44 |
-
}
|
| 45 |
-
```
|
| 46 |
-
|
| 47 |
-
Request files are created automatically by this tool.
|
| 48 |
-
|
| 49 |
-
If you encounter problem on the space, don't hesitate to restart it to remove the create eval-queue, eval-queue-bk, eval-results and eval-results-bk created folder.
|
| 50 |
-
|
| 51 |
-
# Code logic for more complex edits
|
| 52 |
-
|
| 53 |
-
You'll find
|
| 54 |
-
- the main table' columns names and properties in `src/display/utils.py`
|
| 55 |
-
- the logic to read all results and request files, then convert them in dataframe lines, in `src/leaderboard/read_evals.py`, and `src/populate.py`
|
| 56 |
-
- the logic to allow or filter submissions in `src/submission/submit.py` and `src/submission/check_validity.py`
|
|
|
|
| 20 |
- language:日本語
|
| 21 |
- language:Japanese
|
| 22 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|