EleutherAI is a research institute that focuses on interpretability, alignment, and ethics and large language models.
External link for EleutherAI
How well does your model fair in Italian? Come try it out on this new leaderboard!
We just release an updated version of the Italian leaderboard with new models and evaluations integrated in lm-evaluation-harness from EleutherAI, created and maintained by Samuele Colombo who continued the work of Federico Andrea Galatolo, and supported for the computational effort by the AI cloud team of Seeweb.
EleutherAI reposted this
We just release an updated version of the Italian leaderboard with new models and evaluations integrated in lm-evaluation-harness from EleutherAI, created and maintained by Samuele Colombo who continued the work of Federico Andrea Galatolo, and supported for the computational effort by the AI cloud team of Seeweb.
Getting the most out of your hardware when training transformers requires thinking about your model as a sequence of GPU kernel calls. This mindset, common in HPC, is rare in ML and leads to inefficiencies in LLM training. Learn more in our paper https://lnkd.in/gpqq4_Kt And for a condensed version, see https://lnkd.in/giCg8aTM
Want to know which LLMs have open licenses or open data? Check out this excellent list by Stella Biderman
𝐀 𝐝𝐚𝐭𝐚𝐛𝐚𝐬𝐞 𝐨𝐟 𝐋𝐋𝐌 𝐛𝐚𝐬𝐞 𝐦𝐨𝐝𝐞𝐥𝐬 𝐰𝐢𝐭𝐡 𝐝𝐞𝐭𝐚𝐢𝐥𝐞𝐝 𝐢𝐧𝐟𝐨 𝐚𝐛𝐨𝐮𝐭 𝐭𝐡𝐞 𝐥𝐢𝐜𝐞𝐧𝐬𝐢𝐧𝐠 Link: https://lnkd.in/gT6sxnvA Credit & Maintainer: Stella Biderman #AI #LLM #GENAI #aimodels #license #opensource #OSS #opensourceai