fix: typo in description

feat: reduce experiment setup to 500 items

feat: open linkedin links in new tab

feat: add dataset item id to logs and csv result exports

feat: enhance download of csv after experiment completion

feat: wait until all items of experiment are run to download stats, split downloads in stats and raw data

chore: uncomment not used models in selection

feat: add granit models and finish model selection

feat: add qwen 3 4B to cloud model selection

feat: add option to specify model quantization in on device model selection

feat: added a button to start experiments with 1000 requests

feat: track queueing time, inference time, and total latency separately. the timestamp for start inference should be taken somewhere else

Merge branch 'main' of https://github.com/fabianHueni/UNIBE_MSGAI_HS25_Project

feat: add authorship to footnote

feat: add information text to UI

feat: added additional models

fix: correct shown device stats and add message template to on device service

feat: implement CSV download and converted logs to a table

feat: optimize console logging and fix import of transfromer.js library

feat: implement OpenRouter as cloud model provider, optimize UI, fix some issues

feat: model download progress bar and added metrics f1WordLevel, Rouge1, TotalTokens, TokensPerSecond

xenova transformers implemented

feat: add dataset, adjust scheduler to run full dataset, implement statistic download, add model load button

feat: setup base code structure for pipeline with todos

first medication list matching

feat: add initial docling pipeline and readme