update about

src/about.py

@@ -13,8 +13,17 @@ 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("hatecheck_ita", "f1,none", "HateCheck")
-    task1 = Task("honest_ita", "acc,none", "HONEST")
+    task0 = Task("arc_challenge_ita", "acc_norm,none", "ARC-C")
+    task1 = Task("ami_2020_aggressiveness", "f1,none", "AMI 2020 Agg")
+    task2 = Task("ami_2020_misogyny", "f1,none", "AMI 2020 Miso")
+    task3 = Task("gente_rephrasing", "acc,none", "GeNTE Rephr")
+    task4 = Task("belebele_ita", "acc_norm,none", "Belebele")
+    task5 = Task("hatecheck_ita", "f1,none", "HateCheck")
+    task6 = Task("honest_ita", "acc,none", "HONEST")
+    task7 = Task("itacola", "mcc,none", "ItaCoLA")
+    task8 = Task("news_sum", "bertscore,none", "News Sum")
+    task9 = Task("squad_it", "squad_f1,get-answer", "SQuAD it")
+    task10 = Task("truthfulqa_gen_ita", "rouge1_max,none", "TruthfulQA")
 
 
 NUM_FEWSHOT = 0  # Change with your few shot
@@ -26,48 +35,38 @@ TITLE = """<h1 align="center" id="space-title">Demo leaderboard</h1>"""
 
 # What does your leaderboard evaluate?
 INTRODUCTION_TEXT = """
-Intro text
+This leaderboard evaluates language models on <b>ItaEval</b>, a new unified benchmark for Italian.
 """
 
+ITA_EVAL_REPO = "https://github.com/g8a9/ita-eval"
+
 # 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:
-
+To reproduce our results, head to {ITA_EVAL_REPO} for all the instructions.
+
+If all the setup goes smoothly, you can run 'MODEL' on ItaEval with:
+```bash
+MODEL="..."
+lm_eval -mixed_precision=bf16 --model hf \
+    --model_args pretrained=$MODEL,dtype=bfloat16 \
+    --tasks ita_eval \
+    --device cuda:0 \
+    --batch_size "auto" \
+    --log_samples \
+    --output_path $FAST/ita_eval_v1/$MODEL \
+    --use_cache $FAST/ita_eval_v1/$MODEL \
+    --cache_requests "true"
+```
 """
 
 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).
+We do not plan to accept autonomous submissions, yet. 
 """
 
 CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
 CITATION_BUTTON_TEXT = r"""
+We are working on it! :)
 """