Abhishek Rao

abhishekraok

·

AI & ML interests

Program synthesis, RL and LLMs.

Recent Activity

new activity about 21 hours ago

allenai/Dolci-Think-SFT-32B:Benchmark contamination: MATH test (205 items), ifeval_mt, IFBench, MMLU and GPQA overlap

new activity about 21 hours ago

allenai/Dolci-Think-SFT-7B:Benchmark contamination: MATH test (205 items), ifeval_mt, IFBench, MMLU and GPQA overlap

updated a dataset about 1 month ago

abhishekraok/wandering-light-stack-pbe-world-v3

View all activity

Organizations

abhishekraok 's models 4

abhishekraok/wandering-light-deep-corpus-v1-smollm2-360m-sft

Updated Aug 25 • 1

abhishekraok/proposer-basicfns-opt125m-sft2k

0.1B • Updated Aug 11 • 12

abhishekraok/induction-basicfns-opt125m-longsft

Reinforcement Learning • 0.1B • Updated Aug 11 • 13

abhishekraok/induction-basicfns-opt125m-sft434k-rl-6k-with-lp

0.1B • Updated Apr 22 • 9