AIPlans/Qwen3-0.6B-ORPO
Text Generation • Updated • 10
Post Training Versions - Qwen 0.6B
Different versions of Qwen 0.6b, where the only difference is the post training method used. The post training database will be the HelpSteer2 dataset
-
-
AIPlans/Qwen3-0.6B-DPO_NOTLORA
Text Generation • 0.6B • Updated • 5 -
AIPlans/Qwen3-0.6B-GRPO_Epoch2
Text Generation • 0.6B • Updated • 6 -
AIPlans/Qwen3-0.6B-ReMax
Reinforcement Learning • 0.6B • Updated • 10 • 2 -
AIPlans/Qwen3-0.6B-IPO
Reinforcement Learning • 0.6B • Updated • 21 • 1 -
AIPlans/Qwen3-0.6B-KTO
Text Generation • Updated • 8 • 1 -
AIPlans/Qwen3-0.6B-PPO
Text Generation • 0.6B • Updated • 90 • • 1