Off- and on-policy SFT and RL for the Qwen and Olmo series, for studying how post-training changes the weights (Ongoing)
-
XudongZhu/Qwen3-1.7B-Base-SFT-OnPolicy
Text Generation • 2B • Updated • 265 • 1 -
XudongZhu/Qwen3-1.7B-Base-SFT-OffPolicy
Text Generation • 2B • Updated • 252 • 1 -
XudongZhu/Qwen3-1.7B-Base-SFT-OnPolicy-BF16Delta
Text Generation • 2B • Updated • 264 • 1 -
XudongZhu/Qwen3-1.7B-Base-SFT-OffPolicy-BF16Delta
Text Generation • 2B • Updated • 265 • 1