Hahmdong/AT-qwen2.5-7b-hhrlhf-5120-sft-base
8B • Updated • 2
Dongyoon Hahm PRO
Hahmdong
·
AI & ML interests
AI Safety
Organizations
Hahmdong/AT-qwen2.5-7b-hhrlhf-40960-rm-ppo-iter4-step-100
8B • Updated • 2
Hahmdong/AT-qwen2.5-7b-hhrlhf-40960-rm-ppo-iter4-step-80
8B • Updated • 2
Hahmdong/AT-qwen2.5-7b-hhrlhf-40960-rm-ppo-iter4-step-70
8B • Updated • 2
Hahmdong/AT-qwen2.5-7b-hhrlhf-40960-rm-ppo-iter4-step-60
8B • Updated • 2
Hahmdong/AT-qwen2.5-7b-hhrlhf-40960-rm-ppo-iter4-step-50
8B • Updated • 2
Hahmdong/AT-qwen2.5-7b-hhrlhf-20480-rm-iter4
7B • Updated • 3
Hahmdong/AT-qwen2.5-7b-hhrlhf-40960-rm-ppo-iter3-step-90
8B • Updated • 2
Hahmdong/AT-qwen2.5-7b-hhrlhf-40960-rm-ppo-iter3-step-80
8B • Updated • 2
Hahmdong/web-llama
Updated
Hahmdong/webrl-glm
Feature Extraction • 9B • Updated • 6
Hahmdong/webrl-qwen
Text Generation • 8B • Updated • 8
Hahmdong/webrl-llama
8B • Updated • 2
Hahmdong/webrl-gemma
Image-Text-to-Text • 12B • Updated • 4