Content
@
https://warpcast.com/~/channel/to-me
0 reply
0 recast
0 reaction
Kevin
@qiw
UC Berkeley open-sourced a 14B model that rivals OpenAI o3-mini and o1 on coding! They applied RL to Deepseek-R1-Distilled-Qwen-14B on 24K coding problems. It only costs 32 H100 for 2.5 weeks (~$26,880)! It's truly open-source. They released everything: the model, training code, dataset, and a detailed blog (links in the thread). Finally, a powerful coding model we can run locally. I hope Sam can open-source something better than this.
0 reply
0 recast
0 reaction
