
Nous Research
@nousresearch
The AI Accelerator Company
discord.gg/nousresearch
ID: 1318419526132862976
http://nousresearch.com 20-10-2020 05:11:31
534 Tweet
57,57K Takipçi
55 Takip Edilen












101 new and challenging reasoning RL environments are now supported in Atropos! The entirety of the Reasoning Gym from by Oliver Stanley and their team from the paper below is now fully integrated! Check out Atropos, our LLM RL Gym project: github.com/NousResearch/a… Here's a


It was fun working with the Hugging Face team to make this feature a reality! Thanks for all your work and creativity Pedro Cuenca Vaibhav (VB) Srivastav Julien Chaumond Aritra Roy Gosthipaty ! Also thanks to Nous Research Teknium (e/λ) Jade for being early adopters of custom model notebooks and working on this
