halfpintboy/Qwen2.5-3B-instruct-120epochs-scalinginter-gpro-babyai
3B • Updated
Sascha Sikorsky
halfpintboy
AI & ML interests
None yet
Organizations
None yet
models 21
halfpintboy/Qwen2.5-3B-instruct-50epochs-babyai-scalinginter-grpo
3B • Updated
halfpintboy/Qwen2.5-3B-instruct-babyai-scalinginter-reward-30epochs-grpo
3B • Updated • 1
halfpintboy/Qwen2.5-3B-instruct-scalinginter-reward-10epochs-babyai
3B • Updated • 1
halfpintboy/Qwen2.5-3B-instruct-ScalingInter-10epochs-babyai
3B • Updated • 1
halfpintboy/Qwen2.5-3B-5env-100epochs
3B • Updated
halfpintboy/Qwen2.5-7B-instruct-3steps-5env-remax
8B • Updated
halfpintboy/Qwen2.5-7B-instruct-3steps-5env-reinforce-plus-plus
8B • Updated
halfpintboy/Qwen2.5-7B-instruct-10steps-20rounds-5env
8B • Updated • 4
halfpintboy/Qwen2.5-7B-instruct-10steps-10rounds-5env
8B • Updated • 6
datasets 0
None public yet