Post
262
Skywork-Reward-V2π₯ Reward models by Skywork AI.
Skywork/skywork-reward-v2-685cc86ce5d9c9e4be500c84
β¨ 0.6B - 8B
β¨ Trained on 26M human-LLM preference pairs
β¨ 0.6B > 27B in many tasks
Skywork/skywork-reward-v2-685cc86ce5d9c9e4be500c84
β¨ 0.6B - 8B
β¨ Trained on 26M human-LLM preference pairs
β¨ 0.6B > 27B in many tasks