tp

tp140205

2

AI & ML interests

None yet

Recent Activity

updated a model 1 day ago

tp140205/mistral-7b-safebpo-noisesafety5-sba-lam0.2-c25.0

published a model 1 day ago

tp140205/mistral-7b-safebpo-noisesafety5-sba-lam0.2-c25.0

updated a model 1 day ago

tp140205/llama-3b-safebpo-flip-lsif-c30

View all activity

Organizations

None yet

tp140205 's models 230

tp140205/ROUTER-7B

0.2B • Updated Feb 6 • 2 • 1

tp140205/GRPO-7B

8B • Updated Feb 4 • 3 • 1

tp140205/ROUGE-7B

8B • Updated Feb 4 • 2 • 1

tp140205/grpo-3b

3B • Updated Jan 28 • 2

tp140205/ROUGE-ROUTER-3B

0.2B • Updated Jan 27 • 4

tp140205/ROUGE-ACTOR-3B

3B • Updated Jan 27 • 4

tp140205/arm-router-arm-3B-4gpu-bmax0.5-bmin0.5-r0.7-lr5e-5_test

tp140205/arm-actor-arm-3B-4gpu-bmax0.5-bmin0.5-r0.7-lr5e-5_test

tp140205/arm-router-arm-3B-4gpu-bmax0.8-bmin0.3-r0.7-lr5e-5_test

tp140205/arm-actor-arm-3B-4gpu-bmax0.8-bmin0.3-r0.7-lr5e-5_test

tp140205/arm-router-arm-3B-4gpu-bmax1.0-bmin0.5-r0.7-lr1e-5_test

tp140205/arm-actor-arm-3B-4gpu-bmax1.0-bmin0.5-r0.7-lr1e-5_test

tp140205/small-test-20260121_162352-step1

tp140205/small-test-20260121_153835-step2

tp140205/small-test-20260121_153835-step1

tp140205/arm-router-arm-3B-4gpu-bmax1.0-bmin0.5-r0.8-lr5e-5_test

tp140205/arm-actor-arm-3B-4gpu-bmax1.0-bmin0.5-r0.8-lr5e-5_test

tp140205/arm-router-arm-3B-4gpu-bmax1.0-bmin0.5-r0.7-lr5e-5_test

tp140205/arm-actor-arm-3B-4gpu-bmax1.0-bmin0.5-r0.7-lr5e-5_test

tp140205/arm-3B-4gpu-bmax1.0-bmin0.2-r0.7-lr5e-5-step125

tp140205/arm-3B-4gpu-bmax1.0-bmin0.2-r0.7-lr5e-5-step100

tp140205/arm-3B-4gpu-bmax1.0-bmin0.2-r0.7-lr5e-5-step75

tp140205/arm-3B-4gpu-bmax1.0-bmin0.2-r0.7-lr5e-5-step50

tp140205/arm-3B-4gpu-bmax1.0-bmin0.2-r0.7-lr5e-5-step25

tp140205/arm-3B-2gpu-bmax1.0-bmin0.2-r0.5-lr5e-5-step171

tp140205/arm-3B-2gpu-bmax1.0-bmin0.2-r0.5-lr5e-5-step150

tp140205/arm-3B-2gpu-bmax1.0-bmin0.2-r0.5-lr5e-5-step125

tp140205/arm-3B-2gpu-bmax1.0-bmin0.2-r0.5-lr5e-5-step100

tp140205/arm-3B-2gpu-bmax1.0-bmin0.2-r0.5-lr5e-5-step75

tp140205/arm-3B-2gpu-bmax1.0-bmin0.2-r0.5-lr5e-5-step50