Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs
Paper
• 2410.18451 • Published
• 20
Skywork-Reward-Model
Skywork reward model series
-
Skywork/Skywork-Reward-Gemma-2-27B-v0.2
Text Classification • 27B • Updated • 820 • 33Note A new version of our 27B reward model trained on Skywork-Reward-Preference-80K-v0.2, the decontaminated version of Skywork-Reward-Preference-80K-v0.1
Skywork/Skywork-Reward-Llama-3.1-8B-v0.2
Text Classification • 8B • Updated • 20.2k • 39Note A new version of our 8B reward model trained on Skywork-Reward-Preference-80K-v0.2, the decontaminated version of Skywork-Reward-Preference-80K-v0.1
-
Skywork/Skywork-Reward-Gemma-2-27B
Text Classification • 27B • Updated • 43 • 48 -
Skywork/Skywork-Reward-Llama-3.1-8B
Text Classification • 8B • Updated • 995 • 31