RL-Only Domain Adaptation from Base Models via Off-Policy Seeding
-
FreedomIntelligence/HuatuoGPT-3-7B-Pangu
Text Generation • 8B • Updated • 39 -
FreedomIntelligence/HuatuoGPT-3-8B
Text Generation • 8B • Updated • 1.9k • • 10 -
FreedomIntelligence/HuatuoGPT-3-9B
Image-Text-to-Text • 9B • Updated • 1.72k • 12 -
FreedomIntelligence/HuatuoGPT-3-27B
Image-Text-to-Text • 3.05M • Updated • 1.95k • 10