Qwen3-8B-school-of-reward-hacks-sft is an open-source language model fine-tuned for tasks related to reward modeling and reinforcement learning. It is intended for researchers and developers working on AI alignment and reward-based systems, offering open weights and local deployment.
Latest indexed changes and source events
longtermrisk/Qwen3-8B-school-of-reward-hacks-sft discovered by the PulseGate indexer
Other apps tracked under the same category.
