add more info

README.md

@@ -10,29 +10,10 @@ pinned: true
 license: apache-2.0
 ---
 
-Most of the variables to change for a default leaderboard are in src/env (replace the path for your leaderboard) and src/about.
+Depending on whether you want to use lighteval or lm_eval for your evaluations, you might need to complete the 
+requirements.txt file to contain relevant dependencies.
 
-Results files should have the following format:
-```
-{
-    "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,
-        }
-    }
-}
-```
+You'll also need to select, in app.py, whether you want to use the ligtheval or lm_eval by selecting the correct 
+import and commenting the other.
 
-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.
-
-If you want to run your own backend, you only need to change the logic in src/backend/run_eval_suite_..., which at the moment launches the Eleuther AI Harness or Lighteval, and edit the app.py to point to the correct file.
+All env variables that you should need to edit to launch the evaluations should be in `envs`.

app.py

@@ -9,6 +9,7 @@ from functools import partial
 
 import gradio as gr
 from main_backend_lighteval import run_auto_eval
+# from main_backend_harness import run_auto_eval
 from src.display.log_visualizer import log_file_to_html_string
 from src.display.css_html_js import dark_mode_gradio_js
 from src.envs import REFRESH_RATE, REPO_ID, QUEUE_REPO, RESULTS_REPO
@@ -25,6 +26,7 @@ This is a visual for the auto evaluator.
 
 links_md = f"""
 # Important links
+
 | Description     | Link |
 |-----------------|------|
 | Leaderboard     | [{REPO_ID}](https://huggingface.co/spaces/{REPO_ID}) |

requirements.txt

@@ -1,20 +1,10 @@
 APScheduler==3.10.1
 black==23.11.0
 click==8.1.3
-datasets==2.14.5
-gradio==4.4.0 # will have to move to 4.19.2
-gradio_client
 huggingface-hub>=0.18.0
-matplotlib==3.7.1
-numpy==1.24.2
-pandas==2.0.0
 python-dateutil==2.8.2
 requests==2.28.2
 tqdm==4.65.0
-transformers
-tokenizers>=0.15.0
-git+https://github.com/EleutherAI/lm-evaluation-harness.git@b281b0921b636bc36ad05c0b0b0763bd6dd43463#egg=lm-eval
-git+https://github.com/huggingface/lighteval.git#egg=lighteval
 accelerate==0.24.1
 sentencepiece