Reinforcement Fine Tuning Expert Needed for GRPO
Upwork
Remoto
•7 hours ago
•No application
About
I need help running my reinforcement fine tuning (GRPO). Reward function and dataset are ready but I need help setting up properly for maximum throughput on the machine used (4x or 8x H200). Then you need to be an expert at reinforcement learning to view results and make tweaks to training setup such as hyper parameters and reward function.
Sign In 
United Kingdom
Canada
Mexico
United States
Argentina
Brazil
Peru
Japan
South Korea
United Arab Emirates
France
Germany
Italy
Portugal
Spain
Sweden
Switzerland
Australia
