Implementing DeepSeek R1's GRPO algorithm from scratch
Link: https://github.com/policy-gradient/GRPO-Zero
Discussion: https://news.ycombinator.com/item?id=43674825
Implementing DeepSeek R1's GRPO algorithm from scratch
Link: https://github.com/policy-gradient/GRPO-Zero
Discussion: https://news.ycombinator.com/item?id=43674825
If you have a fediverse account, you can quote this note from your own instance. Search https://social.lansky.name/users/hn100/statuses/114334827070495177 on your instance and quote it. (Note that quoting is not supported in Mastodon.)