Switch Space SDK gradio -> static

README.md

@@ -2,13 +2,11 @@
 title: Arabic LLM Leaderboard
 emoji: 🏆
 colorFrom: green
-colorTo: indigo
-sdk: gradio
-app_file: app.py
+colorTo: yellow
+sdk: static
 pinned: true
 license: apache-2.0
 short_description: Benchmarking LLMs on Modern Standard Arabic
-sdk_version: 5.43.1
 tags:
 - leaderboard
 - arabic
@@ -16,45 +14,12 @@ tags:
 - evaluation
 ---
 
-# Start the configuration
+# Arabic LLM Leaderboard
 
-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).
+A static single-page leaderboard for Arabic (Modern Standard Arabic) LLMs. It reads results
+live (client-side) from the **[Mushari440/results](https://huggingface.co/datasets/Mushari440/results)**
+dataset and the evaluation queue from **[Mushari440/requests](https://huggingface.co/datasets/Mushari440/requests)**.
 
-Results files should have the following format and be stored as json files. Scores are `0–1` fractions
-(rendered as percentages), the metric key is `acc`, and a model must report **all 13** dimensions or it is
-skipped:
-```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": {
-        "reasoning_logic": {"acc": 0.559},
-        "generation_instruction": {"acc": 0.617},
-        "sentiment_emotion_meaning": {"acc": 0.884},
-        "safety_trust_bias": {"acc": 0.820},
-        "arabic_language_understanding": {"acc": 0.638},
-        "knowledge_stem": {"acc": 0.784},
-        "multi_turn_dialogue": {"acc": 0.703},
-        "biology": {"acc": 0.0},
-        "islam": {"acc": 0.0},
-        "medicine": {"acc": 0.0},
-        "completion": {"acc": 0.80},
-        "contextual": {"acc": 0.74},
-        "semantic": {"acc": 0.77}
-    }
-}
-```
-
-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`
+Each model is scored on 13 capability & domain dimensions; the headline **Average** is the
+**item-weighted** mean (every one of the 29,417 benchmark items counts equally). No server,
+no framework — just `index.html`, so it never breaks from dependency drift.