docs: add a guide on how to add new results

Signed-off-by: Tarek <tareknaser360@gmail.com>

CONTRIBUTING.md

@@ -0,0 +1,56 @@
+# Contributing
+
+To run the leaderboard locally:
+
+```bash
+python app.py
+```
+
+## Adding Experiments to the Leaderboard
+
+Follow these steps to add new experiments to the leaderboard:
+
+### 1. Adding a New Dataset Variant
+
+If your experiment uses a new dataset variant (not already in the leaderboard):
+
+1. Add an entry to [data/dataset_info.json](data/dataset_info.json) with the variant name and description:
+
+```json
+"my-variant": {
+  "name": "My Variant",
+  "description": "Description of the variant"
+}
+```
+
+2. Add the variant to [src/display/dataset_config.py](src/display/dataset_config.py) in the `DATASET_VARIANTS` dictionary:
+
+### 2. Adding a New Model
+
+If your experiment uses a new model (not already in the leaderboard):
+
+- Update [src/metrics/data_utils.py](src/metrics/data_utils.py):
+  - Add the model to `MODEL_NAMES` dictionary (mapping the model ID to display name)
+  - Add the display name to `MODEL_ORDER` list (controls display order)
+
+### 3. Adding the Experiment Data
+
+1. Copy your LLM processed results folder to `data/experiments/` in a new folder
+
+   - The folder should follow the format from `mizan-cli` evaluation (After running `process_experiments` script)
+   - Expected files: `results.json`, `processed_results.csv`, and `metadata.json`
+
+2. Add an entry to [data/experiments.json](data/experiments.json):
+   - Key: the model name (matching the key in `MODEL_NAMES`)
+   - Value: object mapping dataset variant to experiment folder name (relative to `data/experiments/`)
+
+Example:
+
+```json
+{
+  "my-model-id": {
+    "vanilla": "my_experiment_folder_name",
+    "neutral": "another_experiment_folder_name"
+  }
+}
+```

README.md

@@ -12,38 +12,6 @@ tags:
   - leaderboard
 ---
 
-# Start the configuration
+## Contributing
 
-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).
-
-Results files should have the following format and be stored as json files:
-
-```json
-{
-    "config": {
-        "model_dtype": "torch.float16", # or torch.bfloat16 or 8bit or 4bit
-        "model_name": "path of the model on the hub: org/model",
-        "model_sha": "revision on the hub",
-    },
-    "results": {
-        "task_name": {
-            "metric_name": score,
-        },
-        "task_name2": {
-            "metric_name": score,
-        }
-    }
-}
-```
-
-Request files are created automatically by this tool.
-
-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.
-
-# Code logic for more complex edits
-
-You'll find
-
-- the main table' columns names and properties in `src/display/utils.py`
-- 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`
-- the logic to allow or filter submissions in `src/submission/submit.py` and `src/submission/check_validity.py`
+To add new experiments to the leaderboard, see [CONTRIBUTING.md](CONTRIBUTING.md).