Specializing Large Language Models for Telecom Networks by ITU AI/ML in 5G Challenge
€6 000 EUR
Completed (over 2 years ago)
Generative AI
479 joined
130 active
Start
07 May 24
Close
26 Jul 24
Reveal
26 Jul 24
'/%3e%3c/defs%3e%3cpath fill='%23fff' d='M-120-80h240V80h-240z'/%3e%3cpath d='M-120-80h240v48h-240z'/%3e%3cpath fill='%23060' d='M-120 32h240v48h-240z'/%3e%3cg id='b'%3e%3cuse xlink:href='%23a' stroke='%23000'/%3e%3cuse xlink:href='%23a' fill='%23fff'/%3e%3c/g%3e%3cuse xlink:href='%23b' transform='scale(-1 1)'/%3e%3cpath fill='%23b00' d='M-120-24v48h101c3 8 13 24 19 24s16-16 19-24h101v-48H19C16-32 6-48 0-48s-16 16-19 24z'/%3e%3cpath id='c' d='M19 24c3-8 5-16 5-24s-2-16-5-24c-3 8-5 16-5 24s2 16 5 24'/%3e%3cuse xlink:href='%23c' transform='scale(-1 1)'/%3e%3cg fill='%23fff'%3e%3cellipse rx='4' ry='6'/%3e%3cpath id='d' d='M1 5.85s4 8 4 21-4 21-4 21z'/%3e%3cuse xlink:href='%23d' transform='scale(-1)'/%3e%3cuse xlink:href='%23d' transform='scale(-1 1)'/%3e%3cuse xlink:href='%23d' transform='scale(1 -1)'/%3e%3c/g%3e%3c/svg%3e)
How are People Getting Near Perfect Accuracy?
Platform · 26 Jul 2024, 07:29 · 7
How are People getting near Perfect Accuracy? My thought is they are not using either phi-2 or falcon. So if they are using other powerful models, Will they be disqualified because the rules were we either use phi-2 or falcon?
The final score is based on the private leaderboard (Not the public one) code quality and submitted paper.
But still it we be unfair for people to use more powerful models than what was specified right?
I do not know what people is doing but we will check. Please focus on your contribution :)
Hi Antonio, do all the participants have to submit the paper write-ups? Or the result from the private leaderboard will be published and only the top 3/5/10 teams need to submit the report in written form?
Anyone thinking that he/she has done a good work can continue the competition. Follow the instruction discussed here https://zindi.africa/competitions/specializing-large-language-models-for-telecom-networks/discussions/21743
How can someone get private leaderboard score 0 if he is having public leaderboard score 0.45? Can someone please explain?
the participant has likely not replied to the question from the private leaderboard