data/performance.csv

model,task,type,sst2 (acc),imdb (acc),tomatoes (acc),sciq (acc),squad (f1),"squad_v2 (f1, has answer)",samsum (rouge),xsum (rouge),cnn (rouge)
bigscience/bloomz-560m,sentiment,decoder,0.9243,0.9409,0.848,,,,,,
bigscience/bloomz-560m,summarization,decoder,,,,,,,0.2253,0.1463,0.1017
bigscience/bloomz-560m,qa,decoder,,,,0.9180,0.4269,0.209,,,
bigscience/bloomz-1b7,sentiment,decoder,0.9438,0.9724,0.9296,,,,,,
bigscience/bloomz-1b7,summarization,decoder,,,,,,,0.257,0.1553,0.1803
bigscience/bloomz-1b7,qa,decoder,,,,0.9590,0.5033,0.248,,,
bigscience/bloomz-3b,sentiment,decoder,0.9472,0.9778,0.9493,,,,,,
bigscience/bloomz-3b,summarization,decoder,,,,,,,0.2792,0.1722,0.211
bigscience/bloomz-3b,qa,decoder,,,,0.9670,0.5341,0.2639,,,
bigscience/bloomz-7b1,sentiment,decoder,0.9438,0.9786,0.9465,,,,,,
bigscience/bloomz-7b1,summarization,decoder,,,,,,,0.3183,0.2145,0.0941
bigscience/bloomz-7b1,qa,decoder,,,,0.966,0.5388,0.2667,,,
google/flan-t5-xxl,sentiment,seq2seq,0.9553,0.9691,0.9193,,,,,,
google/flan-t5-xxl,qa,seq2seq,,,,0.7210,0.9754,0.4886,,,
google/flan-t5-xxl,summarization,seq2seq,,,,,,,0.30332,0.37269,0.2281
google/flan-t5-xl,sentiment,seq2seq,0.9564,0.9663,0.9259,,,,,,
google/flan-t5-xl,qa,seq2seq,,,,0.6550,0.968,0.4867,,,
google/flan-t5-xl,summarization,seq2seq,,,,,,,0.4919,0.3844,0.2371
google/flan-t5-large,sentiment,seq2seq,0.9438,0.9634,0.9174,,,,,,
google/flan-t5-large,qa,seq2seq,,,,0.5340,0.9683,0.5019,,,
google/flan-t5-large,summarization,seq2seq,,,,,,,0.4539,0.3047,0.2408
google/flan-t5-base,sentiment,seq2seq,0.9289,0.9466,0.8846,,,,,,
google/flan-t5-base,qa,seq2seq,,,,0.6100,0.9487,0.477,,,
google/flan-t5-base,summarization,seq2seq,,,,,,,0.4569,0.322,0.2336
distilbert-base-uncased-distilled-squad,qa,encoder-finetuned,,,,0.4434,0.8655,0.8621,,,
distilbert-base-cased-distilled-squad,qa,encoder-finetuned,,,,0.4615,0.8699,0.8694,,,
deepset/roberta-base-squad2,qa,encoder-finetuned,,,,0.4785,0.9315,0.8295,,,
bert-large-uncased-whole-word-masking-finetuned-squad,qa,encoder-finetuned,,,,0.4774,0.9300,0.8388,,,
timpal0l/mdeberta-v3-base-squad2,qa,encoder-finetuned,,,,0.4604,0.9059,0.9037,,,
deepset/tinyroberta-squad2,qa,encoder-finetuned,,,,0.4536,0.9793,0.9056,,,
deepset/electra-base-squad2,qa,encoder-finetuned,,,,0.4830,0.8882,0.8171,,,
deepset/bert-large-uncased-whole-word-masking-squad2,qa,encoder-finetuned,,,,0.4638,0.9250,0.9240,,,
sshleifer/distilbart-xsum-12-6,summarization,seq2seq-finetuned,,,,,,,0.203249,0.452877,0.230331
sshleifer/distilbart-cnn-12-6,summarization,seq2seq-finetuned,,,,,,,0.291424,0.210314,0.44241
pszemraj/led-large-book-summary,summarization,seq2seq-finetuned,,,,,,,0.334514,0.162446,0.328774
google/pegasus-xsum,summarization,seq2seq-finetuned,,,,,,,0.219676,0.218096,0.222062
google/pegasus-large,summarization,seq2seq-finetuned,,,,,,,0.270341,0.174476,0.342469
google/pegasus-multi_news,summarization,seq2seq-finetuned,,,,,,,0.11537,0.16396,0.290169
facebook/bart-large-cnn,summarization,seq2seq-finetuned,,,,,,,0.315257,0.207919,0.440558
ainize/bart-base-cnn,summarization,seq2seq-finetuned,,,,,,,0.270195,0.15911,0.259687
distilbert-base-uncased-finetuned-sst-2-english,sentiment,encoder-finetuned,0.9885521686,0.88412,0.8968105066,,,,,,
nlptown/bert-base-multilingual-uncased-sentiment,sentiment,encoder-finetuned,0.752293578,0.84824,0.7307692308,,,,,,
twitter-roberta-base-sentiment-latest,sentiment,encoder-finetuned,0.8199541284,0.7952,0.7664165103,,,,,,
cardiffnlp/twitter-xlm-roberta-base-sentiment,sentiment,encoder-finetuned,0.7912844037,0.70856,0.7420262664,,,,,,
lvwerra/distilbert-imdb,sentiment,encoder-finetuned,0.878440367,0.928,0.8151969981,,,,,,
siebert/sentiment-roberta-large-english,sentiment,encoder-finetuned,0.9243119266,0.91616,0.9202626642,,,,,,
finiteautomata/bertweet-base-sentiment-analysis,sentiment,encoder-finetuned,0.8188073394,0.72068,0.7739212008,,,,,,
sbcBI/sentiment_analysis_model,sentiment,encoder-finetuned,0.8061926606,0.74636,0.7636022514,,,,,,