update leaderboard config

src/about.py

@@ -12,59 +12,27 @@ class Task:
 # ---------------------------------------------------
 class Tasks(Enum):
     # task_key in the json file, metric_key in the json file, name to display in the leaderboard 
-    task0 = Task("anli_r1", "acc", "ANLI")
-    task1 = Task("logiqa", "acc_norm", "LogiQA")
-
-NUM_FEWSHOT = 0 # Change with your few shot
-# ---------------------------------------------------
-
+    ParsiNLUـEntailment = Task("ParsiNLU Entailment", "Exact Match", "ParsiNLU Entailment")
+    ParsiNLU_Machine_Translation_Fa_En = Task("ParsiNLU Machine Translation Fa-En", "English Sentence Bleu", "ParsiNLU Machine Translation Fa-En")
+    ParsiNLU_Machine_Translation_En_Fa = Task("ParsiNLU Machine Translation En-Fa", "Persian Sentence Bleu", "ParsiNLU Machine Translation En-Fa")
+    ParsiNLU_Reading_Comprehension = Task("ParsiNLU Reading Comprehension", "Common Tokens", "ParsiNLU Reading Comprehension")
+    Persian_Math = Task("Persian Math", "Math Equivalence", "Persian Math")
 
 
 # Your leaderboard name
-TITLE = """<h1 align="center" id="space-title">Demo leaderboard</h1>"""
+TITLE = """<h1 align="center" id="space-title">ParsBench Leaderboard</h1>"""
 
 # What does your leaderboard evaluate?
 INTRODUCTION_TEXT = """
-Intro text
+This leaderboard is created using <a href="https://github.com/shahriarshm/parsbench">ParsBench</a> framework benchmarking toolkit.
 """
 
 # Which evaluations are you running? how can people reproduce what you have?
 LLM_BENCHMARKS_TEXT = f"""
-## How it works
-
-## Reproducibility
-To reproduce our results, here is the commands you can run:
-
 """
 
 EVALUATION_QUEUE_TEXT = """
-## Some good practices before submitting a model
-
-### 1) Make sure you can load your model and tokenizer using AutoClasses:
-```python
-from transformers import AutoConfig, AutoModel, AutoTokenizer
-config = AutoConfig.from_pretrained("your model name", revision=revision)
-model = AutoModel.from_pretrained("your model name", revision=revision)
-tokenizer = AutoTokenizer.from_pretrained("your model name", revision=revision)
-```
-If this step fails, follow the error messages to debug your model before submitting it. It's likely your model has been improperly uploaded.
-
-Note: make sure your model is public!
-Note: if your model needs `use_remote_code=True`, we do not support this option yet but we are working on adding it, stay posted!
-
-### 2) Convert your model weights to [safetensors](https://huggingface.co/docs/safetensors/index)
-It's a new format for storing weights which is safer and faster to load and use. It will also allow us to add the number of parameters of your model to the `Extended Viewer`!
-
-### 3) Make sure your model has an open license!
-This is a leaderboard for Open LLMs, and we'd love for as many people as possible to know they can use your model 🤗
-
-### 4) Fill up your model card
-When we add extra information about models to the leaderboard, it will be automatically taken from the model card
-
-## In case of model failure
-If your model is displayed in the `FAILED` category, its execution stopped.
-Make sure you have followed the above steps first.
-If everything is done, check you can launch the EleutherAIHarness on your model locally, using the above command without modifications (you can add `--limit` to limit the number of examples per task).
+For now, you can contact me at [email protected] for submitting a new request.
 """
 
 CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"

src/leaderboard/read_evals.py

@@ -136,7 +136,7 @@ def get_request_file_for_model(requests_path, model_name, precision):
     """Selects the correct request file for a given model. Only keeps runs tagged as FINISHED"""
     request_files = os.path.join(
         requests_path,
-        f"{model_name}_eval_request_*.json",
+        f"leaderboard/{model_name}_eval_request_*.json",
     )
     request_files = glob.glob(request_files)
 
@@ -156,6 +156,8 @@ def get_request_file_for_model(requests_path, model_name, precision):
 
 def get_raw_eval_results(results_path: str, requests_path: str) -> list[EvalResult]:
     """From the path of the results folder root, extract all needed info for results"""
+    results_path = os.path.join(results_path, "leaderboard")
+
     model_result_filepaths = []
 
     for root, _, files in os.walk(results_path):
@@ -187,10 +189,10 @@ def get_raw_eval_results(results_path: str, requests_path: str) -> list[EvalResu
 
     results = []
     for v in eval_results.values():
-        try:
-            v.to_dict() # we test if the dict version is complete
-            results.append(v)
-        except KeyError:  # not all eval values present
-            continue
+        # try:
+        v.to_dict() # we test if the dict version is complete
+        results.append(v)
+        # except KeyError:  # not all eval values present
+            # continue
 
     return results