Active filters: stpete2
stpete2/dqn_othello_20250216
Updated
2B • Updated • 4
stpete2/Qwen2-0.5B-math-grpo
Text Generation • 0.6B • Updated • 3
stpete2/Qwen2-0.5B-math-cppo
Text Generation • 0.6B • Updated • 6
stpete2/Qwen2-0.5B-gsm8k-grpo
Text Generation • 0.6B • Updated • 5
stpete2/Qwen2-0.5B-gsm8k-cppo
Text Generation • 0.6B • Updated • 5
0.5B • Updated • 2
stpete2/Qwen2.5-0.5b-gsm8k-drgrpocppo
Text Generation • 0.6B • Updated • 10
stpete2/Qwen2.5-0.5B-gsm8k-sft
Text Generation • Updated • 7
• 2
stpete2/Qwen2.5-0.5B-gsm8k-grpo
Text Generation • Updated • 6
stpete2/Qwen2.5-0.5B-gsm8k-cppo
Text Generation • Updated • 4
stpete2/Qwen2.5-0.5B-gsm8k-drgrpo
Text Generation • Updated • 3
stpete2/Qwen2.5-0.5B-gsm8k-raftplusplus
Text Generation • Updated • 4
stpete2/Qwen2.5-0.5B-gsm8k-raftvanilla
Text Generation • Updated • 3
stpete2/Qwen2.5-0.5B-gsm8k-reinforceplusplus
Text Generation • Updated • 6
stpete2/Qwen2.5-0.5B-gsm8k-reinforcevanilla
Text Generation • Updated • 3
stpete2/Qwen2.5-1.5B-gsm8k-sft
Text Generation • Updated • 4
stpete2/Qwen2.5-1.5B-gsm8k-grpo
Text Generation • Updated • 8