6 repos
HyperPotatoNeo/prime-values
Async value functions and replay-buffer critic training for PRIME-RL
17
2,183 commits
mixedbread-ai/prime-rl-fork-public
Private PrimeRL integration branch for Qwen3.8 Flash Next
0
2,379 commits
PrimeIntellect-ai/prime-rl
Agentic RL Training at Scale
2,030
2,402 commits
HyperPotatoNeo/attention-matching-rl
No description
3
1,656 commits
PrimeIntellect-ai/prime-diloco
prime is a framework for efficient, globally distributed training of AI models over the internet.
855
309 commits
PrimeIntellect-ai/renderers
Programmable chat templates for LLM training and inference.
156
126 commits
