Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
as-cle-bert 
posted an update Jul 21
Post
556
Hi HF Community!🤗

As you may know, small language models like the SmolLM series have been on the rise recently: although it may not be completely fair to compare them with larger models, my thought was that we could build a space where these SLMs could compete against each other in a chat arena, and here is what came out: as-cle-bert/smolLM-arena 🚀
Even though there might be some little issues and hiccups due to GPU resources allocation, this space offers you the possibility to compare and play around with several Small Language Models, coming also with a leaderboard page (make sure to refresh it for the latest updates!)👑
Have fun!🍕

404 error !

·

Thanks for pointing that out, now it should work!

I really thought I could test my models! KKKKKKKKKKKKKKKKKKKKKKKKKKKKK

What the heck, I thought it was for models we use more, like between 7 to 10B parameters, or better yet, between 7 and 20B parameters, which can run on an RTX 5050 Nvidia card and above, with 6 to 12GB VRam ( the most common for all people ). But you presented with models tiny size, like less than 1.5B models. Are those for smartphones ? I never used them. So bad ! Why don't you create a second small LLM leaderboard for models between 7 and 20B ? 👍🙏

·

The SmolLM series is specifically designed to run on devices like smartphones, yes :) And, concerning the arena for models 7 to 20B, I didn't want to spoiler it, but It's coming soon! ;)