Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
sequelbox 
posted an update about 17 hours ago
Post
850
SNEAK PREVIEW: Tachibana 2! A new high-difficulty code-reasoning dataset to use and challenge deepseek-ai/DeepSeek-R1 - harder prompts, complex requirements, deeper technical skill.

Link here: sequelbox/Tachibana2-DeepSeek-R1-PREVIEW

All responses generated by DeepSeek's R1 model, all prompts synthetically generated by Llama 3.1 405b Instruct.

excited to bring out the full dataset for everyone's use as soon as I can! more to come soon.
In this post