0k9d0h1/3b-planner-1.5b-reranker-nq-hotpotqa-filtered-tp-reranker
Text Generation • 3B • Updated • 10
Donghun Kang
0k9d0h1
·
AI & ML interests
None yet
Organizations
models 10
0k9d0h1/7b-planner-1.5b-reranker-nq-hotpotqa-filtered-tp-reranker
Text Generation • 8B • Updated • 28 •
0k9d0h1/planner-7b-2epoch
Text Generation • 8B • Updated • 7
0k9d0h1/reranker1.5b-sft
Text Generation • 2B • Updated • 51 •
0k9d0h1/reranker3b-sft
Text Generation • 3B • Updated • 16 •
0k9d0h1/searcher-easy-dataset-450step
Text Generation • 3B • Updated • 1
0k9d0h1/nq_grpo_multi_turn_200_steps
Text Generation • 3B • Updated • 4
0k9d0h1/nq_grpo_multi_turn_300_steps
Text Generation • 3B • Updated • 2
0k9d0h1/rag_sft_5epochs
Text Generation • 3B • Updated • 1
0k9d0h1/rag_sft_3epochs
Text Generation • 3B • Updated • 3