Update README.md

README.md

@@ -227,10 +227,9 @@ library_name: transformers
 
 # Model Card for DeBERTa-v3-base-tasksource-nli
 
-DeBERTa-v3-base fine-tuned with multi-task learning on 520 tasks of the [tasksource collection](https://github.com/sileod/tasksource/)
+DeBERTa-v3-base fine-tuned with multi-task learning on 560 tasks of the [tasksource collection](https://github.com/sileod/tasksource/)
 This checkpoint has strong zero-shot validation performance on many tasks (e.g. 70% on WNLI), and can be used for zero-shot NLI pipeline (similar to bart-mnli but better).
-You can further fine-tune this model to use it for any classification or multiple-choice task.
-The untuned model CLS embedding also has strong linear probing performance (90% on MNLI), due to the multitask training.
+You can also further fine-tune this model to use it for any classification or multiple-choice task.
 
 This is the shared model with the MNLI classifier on top. Its encoder was trained on many datasets including bigbench, Anthropic rlhf, anli... alongside many NLI and classification tasks with one shared encoder.
 Each task had a specific CLS embedding, which is dropped 10% of the time to facilitate model use without it. All multiple-choice model used the same classification layers. For classification tasks, models shared weights if their labels matched.
@@ -251,13 +250,9 @@ pipe(['That movie was great !', 'Awful movie.'])
 # [{'label': 'positive', 'score': 0.9956129789352417}, {'label': 'negative', 'score': 0.9967049956321716}]
 ```
 
-### Software
-https://github.com/sileod/tasksource/ \
-https://github.com/sileod/tasknet/ \
-Training took 7 days on RTX6000 24GB gpu.
 
-## Model Recycling
-This model ranked 1st among all models with the microsoft/deberta-v3-base architecture.
+## Evaluation
+This model ranked 1st among all models with the microsoft/deberta-v3-base architecture according to IBM model recycling evaluation.
 Results:
 [Evaluation on 36 datasets](https://ibm.github.io/model-recycling/model_gain_chart?avg=1.41&mnli_lp=nan&20_newsgroup=0.63&ag_news=0.46&amazon_reviews_multi=-0.40&anli=0.94&boolq=2.55&cb=10.71&cola=0.49&copa=10.60&dbpedia=0.10&esnli=-0.25&financial_phrasebank=1.31&imdb=-0.17&isear=0.63&mnli=0.42&mrpc=-0.23&multirc=1.73&poem_sentiment=0.77&qnli=0.12&qqp=-0.05&rotten_tomatoes=0.67&rte=2.13&sst2=0.01&sst_5bins=-0.02&stsb=1.39&trec_coarse=0.24&trec_fine=0.18&tweet_ev_emoji=0.62&tweet_ev_emotion=0.43&tweet_ev_hate=1.84&tweet_ev_irony=1.43&tweet_ev_offensive=0.17&tweet_ev_sentiment=0.08&wic=-1.78&wnli=3.03&wsc=9.95&yahoo_answers=0.17&model_name=sileod%2Fdeberta-v3-base_tasksource-420&base_name=microsoft%2Fdeberta-v3-base) using sileod/deberta-v3-base_tasksource-420 as a base model yields average score of 80.45 in comparison to 79.04 by microsoft/deberta-v3-base.
 
@@ -270,6 +265,11 @@ Results:
 
 For more information, see: [Model Recycling](https://ibm.github.io/model-recycling/)
 
+### Software
+https://github.com/sileod/tasksource/ \
+https://github.com/sileod/tasknet/ \
+Training took 7 days on RTX6000 24GB gpu.
+
 
 # Citation