forkjoin-ai/buleyean-rl-deepseek-r1-7b-trainer
0
Buleyean RL -- deepseek-r1-7b Training
Training deepseek-ai/DeepSeek-R1-Distill-Qwen-7B with Buleyean rejection loss on A100.
Copyright 2026 forkjoin.ai
Training deepseek-ai/DeepSeek-R1-Distill-Qwen-7B with Buleyean rejection loss on A100.
Copyright 2026 forkjoin.ai