Commits · evalitahf/evalita_llm

Fix: format best model scores to one decimal place

178e582

rzanoli commited on 18 days ago

Round scores to one decimal place for best textual and multimodal models

395f973

rzanoli commited on 18 days ago

Abbreviate labels for model configurations and best models

2f5d681

rzanoli commited on 18 days ago

Add "Last Update" label

b7af573

rzanoli commited on 18 days ago

Update labels for model configurations

a91626f

rzanoli commited on 18 days ago

Update labels for model configurations

f4114b4

rzanoli commited on 18 days ago

Small changes

e318805

rzanoli commited on 21 days ago

Small changes

3e30369

rzanoli commited on 21 days ago

Small changes: repositioned some figure captions

a84409c

rzanoli commited on 21 days ago

Small changes: repositioned some figure captions

1aaaec6

rzanoli commited on 21 days ago

Small changes: repositioned some figure captions

32b6295

rzanoli commited on 21 days ago

Update description of Evalita benchmark

f3bd6c6

rzanoli commited on 21 days ago

Refactor app.py: reorganize imports, update function names, and enhance medal assignment logic

42de204

rzanoli commited on 21 days ago

Add support for new MAIA task results and update Gradio app layout

4f058fb

rzanoli commited on 21 days ago

Make caption clearer

3a2b0e3

rzanoli commited on Oct 9

Move figure caption

6ea6711

rzanoli commited on Oct 9

Move figure caption

1ef0fee

rzanoli commited on Oct 9

Small changes

5445809

rzanoli commited on Oct 9

Add mean CV (coefficient of variation)

9351c65

rzanoli commited on Oct 9

Remove placeholder for best accuracy heat indication per task

3138158

rzanoli commited on Oct 7

Updated table captions for clarity

7d44717

rzanoli commited on Oct 1

Small changes

174aa6d

rzanoli commited on Oct 1

Small changes

79622c0

rzanoli commited on Oct 1

Updated leaderboard table: Added 'Best Prompt Model' values

4bcce41

rzanoli commited on Oct 1

Small changes: adjusted caption position slightly lower

396874f

rzanoli commited on Sep 30

Add heatmap and model comparison table

7b2afd4

rzanoli commited on Sep 30

Small changes

c47538f

rzanoli commited on Sep 23

Remove webhook_url

d7f622f

rzanoli commited on Sep 23

Add the submit function

a0b3b71

rzanoli commited on Sep 23

Refactor: Move inline styles from Python/HTML to CSS file

a0702aa

rzanoli commited on Sep 23

Add performance metrics labels with average, std dev, and best model info.

ad05cd8

rzanoli commited on Sep 22

Removed unused fields from the table.

89d23fd

rzanoli commited on Sep 22

Small changes

9b06c44

rzanoli commited on Sep 19

Add the function to highlight best per task

95ac6d4

rzanoli commited on Sep 19

Set tooltip background color to match corresponding boxplot color

a0f2788

rzanoli commited on Sep 18

Change tooltip background to blue in boxplot for better visibility

ab78810

rzanoli commited on Sep 18

Small changes

2794d9a

rzanoli commited on Sep 18

Small changes

5d82125

rzanoli commited on Sep 18

Refactor and optimize all interface chart code

5e09303

rzanoli commited on Sep 18

Add the results of GPT-4o for summarization

0a7c918

rzanoli commited on Sep 16

Update figure captions with minor wording changes

9ef3794

rzanoli commited on Sep 15

Add the results of GPT-4o for NER, REL and LS

07ad260

rzanoli commited on Sep 15

Remove graph visualization for prompt

fc7c800

rzanoli commited on Aug 30

Small changes

b0db80c

rzanoli commited on Aug 29

Small changes

9cfb29f

rzanoli commited on Aug 29

Samll changes

19c0895

rzanoli commited on Aug 29

Small changes

416d8d8

rzanoli commited on Aug 29

Small changes

0d0fe99

rzanoli commited on Aug 29

Small changes

0dd3537

rzanoli commited on Aug 29

Small changes

c698cfd

rzanoli commited on Aug 29

Commit History

Fix: format best model scores to one decimal place 178e582

Round scores to one decimal place for best textual and multimodal models 395f973

Abbreviate labels for model configurations and best models 2f5d681

Add "Last Update" label b7af573

Update labels for model configurations a91626f

Update labels for model configurations f4114b4

Small changes e318805

Small changes 3e30369

Small changes: repositioned some figure captions a84409c

Small changes: repositioned some figure captions 1aaaec6

Small changes: repositioned some figure captions 32b6295

Update description of Evalita benchmark f3bd6c6

Refactor app.py: reorganize imports, update function names, and enhance medal assignment logic 42de204

Add support for new MAIA task results and update Gradio app layout 4f058fb

Make caption clearer 3a2b0e3

Move figure caption 6ea6711

Move figure caption 1ef0fee

Small changes 5445809

Add mean CV (coefficient of variation) 9351c65

Remove placeholder for best accuracy heat indication per task 3138158

Updated table captions for clarity 7d44717

Small changes 174aa6d

Small changes 79622c0

Updated leaderboard table: Added 'Best Prompt Model' values 4bcce41

Small changes: adjusted caption position slightly lower 396874f

Add heatmap and model comparison table 7b2afd4

Small changes c47538f

Remove webhook_url d7f622f

Add the submit function a0b3b71

Refactor: Move inline styles from Python/HTML to CSS file a0702aa

Add performance metrics labels with average, std dev, and best model info. ad05cd8

Removed unused fields from the table. 89d23fd

Small changes 9b06c44

Add the function to highlight best per task 95ac6d4

Set tooltip background color to match corresponding boxplot color a0f2788

Change tooltip background to blue in boxplot for better visibility ab78810

Small changes 2794d9a

Small changes 5d82125

Refactor and optimize all interface chart code 5e09303

Add the results of GPT-4o for summarization 0a7c918

Update figure captions with minor wording changes 9ef3794

Add the results of GPT-4o for NER, REL and LS 07ad260

Remove graph visualization for prompt fc7c800

Small changes b0db80c

Small changes 9cfb29f

Samll changes 19c0895

Small changes 416d8d8

Small changes 0d0fe99

Small changes 0dd3537

Small changes c698cfd

Fix: format best model scores to one decimal place

178e582

Round scores to one decimal place for best textual and multimodal models

395f973

Abbreviate labels for model configurations and best models

2f5d681

Add "Last Update" label

b7af573

Update labels for model configurations

a91626f

Update labels for model configurations

f4114b4

Small changes

e318805

Small changes

3e30369

Small changes: repositioned some figure captions

a84409c

Small changes: repositioned some figure captions

1aaaec6

Small changes: repositioned some figure captions

32b6295

Update description of Evalita benchmark

f3bd6c6

Refactor app.py: reorganize imports, update function names, and enhance medal assignment logic

42de204

Add support for new MAIA task results and update Gradio app layout

4f058fb

Make caption clearer

3a2b0e3

Move figure caption

6ea6711

Move figure caption

1ef0fee

Small changes

5445809

Add mean CV (coefficient of variation)

9351c65

Remove placeholder for best accuracy heat indication per task

3138158

Updated table captions for clarity

7d44717

Small changes

174aa6d

Small changes

79622c0

Updated leaderboard table: Added 'Best Prompt Model' values

4bcce41

Small changes: adjusted caption position slightly lower

396874f

Add heatmap and model comparison table

7b2afd4

Small changes

c47538f

Remove webhook_url

d7f622f

Add the submit function

a0b3b71

Refactor: Move inline styles from Python/HTML to CSS file

a0702aa

Add performance metrics labels with average, std dev, and best model info.

ad05cd8

Removed unused fields from the table.

89d23fd

Small changes

9b06c44

Add the function to highlight best per task

95ac6d4

Set tooltip background color to match corresponding boxplot color

a0f2788

Change tooltip background to blue in boxplot for better visibility

ab78810

Small changes

2794d9a

Small changes

5d82125

Refactor and optimize all interface chart code

5e09303

Add the results of GPT-4o for summarization

0a7c918

Update figure captions with minor wording changes

9ef3794

Add the results of GPT-4o for NER, REL and LS

07ad260

Remove graph visualization for prompt

fc7c800

Small changes

b0db80c

Small changes

9cfb29f

Samll changes

19c0895

Small changes

416d8d8

Small changes

0d0fe99

Small changes

0dd3537

Small changes

c698cfd