malhajar commited on
Commit
53e53d2
1 Parent(s): fd6bbaa

Update src/display/about.py

Browse files
Files changed (1) hide show
  1. src/display/about.py +16 -15
src/display/about.py CHANGED
@@ -11,28 +11,29 @@ class Task:
11
  # Init: to update with your specific keys
12
  class Tasks(Enum):
13
  # task_key in the json file, metric_key in the json file, name to display in the leaderboard
14
- task0 = Task("MMLU", "metric_name", "MMLU")
15
- task1 = Task("Truthful_qa", "metric_name", "Truthful_qa")
16
- task2 = Task("ARC", "metric_name", "ARC")
17
- task3 = Task("HellaSwag", "metric_name", "HellaSwag")
18
  task4 = Task("GSM8K", "metric_name", "GSM8K")
19
- task5 = Task("Winogrande", "metric_name", "Winogrande")
20
 
21
 
22
  # Your leaderboard name
23
- TITLE = """<h1 align="center" id="space-title"> OpenLLM Turkish leaderboard v0.2</h1>"""
24
 
25
  # What does your leaderboard evaluate?
26
  INTRODUCTION_TEXT = """
27
- Welcome to the Turkish LLM Leaderboard, a pioneering platform dedicated to evaluating Turkish Large Language Models (LLMs). As multilingual LLMs advance, my mission is to specifically highlight models excelling in Turkish, providing benchmarks that drive progress in Turkish LLM and Generative AI for the Turkish language.
28
- The Leadboard uses [this](https://huggingface.co/collections/malhajar/openllmturkishleadboard-v02-datasets-662a8593043e73938e2f6b1e) currfelly curated benchmarks for evaluation.
29
- The benchmarks are generated and checked using both GPT-4 and Human annotation rendering the leadboard the most valuable and accurate test in the LLM arena for Turkish evaluation.
30
 
31
- 🚀 Submit Your Model 🚀
 
 
32
 
33
- Got a Turkish LLM? Submit it for evaluation (Currently Manually, due to the lack of resources! Hoping to automate this with the community's support!), leveraging the Eleuther AI Language Model Evaluation Harness for in-depth performance analysis. Learn more and contribute to Turkish AI advancements on the "About" page.
34
 
35
- Join the forefront of Turkish language technology. Submit your model, and let's advance Turkish LLM's together!
 
 
36
 
37
  """
38
 
@@ -100,11 +101,11 @@ If everything is done, check you can launch the EleutherAIHarness on your model
100
 
101
  CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
102
  CITATION_BUTTON_TEXT = r"""
103
- @misc{openllm-Turkish-leaderboard,
104
  author = {Mohamad Alhajar},
105
- title = {Open LLM Turkish Leaderboard v0.2},
106
  year = {2024},
107
  publisher = {Mohamad Alhajar},
108
- howpublished = "\url{https://huggingface.co/spaces/malhajar/OpenLLMTurkishLeaderboard}"
109
  }
110
  """
 
11
  # Init: to update with your specific keys
12
  class Tasks(Enum):
13
  # task_key in the json file, metric_key in the json file, name to display in the leaderboard
14
+ task0 = Task("BBH", "metric_name", "BBH")
15
+ task1 = Task("GPQA", "metric_name", "GPQA")
16
+ task2 = Task("IFEval", "metric_name", "IFEval")
17
+ task3 = Task("MUSR", "metric_name", "MUSR")
18
  task4 = Task("GSM8K", "metric_name", "GSM8K")
19
+ task5 = Task("MMMLU-fr", "metric_name", "MMMLU-fr")
20
 
21
 
22
  # Your leaderboard name
23
+ TITLE = """<h1 align="center" id="space-title"> OpenLLM French leaderboard 🇫🇷</h1>"""
24
 
25
  # What does your leaderboard evaluate?
26
  INTRODUCTION_TEXT = """
 
 
 
27
 
28
+ Bienvenue sur le Leaderboard des LLM en français, une plateforme pionnière dédiée à l'évaluation des grands modèles de langage (LLM) en français. Alors que les LLM multilingues progressent, ma mission est de mettre en lumière spécifiquement les modèles qui excellent en langue française,
29
+ en fournissant des benchmarks qui stimulent les avancées dans les LLM en français et l'IA générative pour la langue française. Le Leaderboard utilise ce lien (https://huggingface.co/collections/le-leadboard/openllmfrenchleadboard-jeu-de-donnees-67126437539a23c65554fd88) pour ses benchmarks soigneusement sélectionnés. Les évaluations sont générées et vérifiées à la fois par GPT-4 et par annotation humaine,
30
+ rendant ainsi ce Leaderboard l'outil le plus précieux et le plus précis pour l'évaluation des LLM en français.
31
 
32
+ 🚀 Soumettez votre Modèle 🚀
33
 
34
+ Vous avez un LLM en français ? Soumettez-le pour évaluation (Actuellement manuelle, faute de ressources ! En espérant automatiser ce processus avec le soutien de la communauté !), en utilisant le Eleuther AI Language Model Evaluation Harness pour une analyse approfondie des performances. Apprenez-en plus et contribuez aux avancées de l'IA en français sur la page "À propos".
35
+
36
+ Rejoignez l'avant-garde de la technologie linguistique en français. Soumettez votre modèle et faisons progresser ensemble les LLM en français !
37
 
38
  """
39
 
 
101
 
102
  CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
103
  CITATION_BUTTON_TEXT = r"""
104
+ @misc{openllm-French-leaderboard,
105
  author = {Mohamad Alhajar},
106
+ title = {Open LLM French Leaderboard v0.2},
107
  year = {2024},
108
  publisher = {Mohamad Alhajar},
109
+ howpublished = "\url{https://huggingface.co/spaces/le-leadboard/OpenLLMFrenchLeaderboard}"
110
  }
111
  """