Article
13
Sashank Pisupati
spisupat
AI & ML interests
AI safety, failure modes of intelligence, evaluations
Recent Activity
published a model 4 days ago
spisupat/genrm-grpo-qwen3-8b-g4 published a model 4 days ago
spisupat/genrm-grpo-qwen3-8b-4bit-baseline published a model 4 days ago
spisupat/genrm-grpo-qwen3-8b-baselineOrganizations
models 7
spisupat/genrm-grpo-qwen3-8b-g4
Updated
spisupat/genrm-grpo-qwen3-8b-4bit-baseline
Updated
spisupat/genrm-grpo-qwen3-8b-baseline
Updated
spisupat/genrm-grpo-test
Updated
spisupat/genrm-grpo-speedrun-qwen3-0.6b-cor
Updated
spisupat/genrm-grpo-speedrun-qwen3-4b-cor
Updated
spisupat/gemma-3-judge
Updated
datasets 37
spisupat/helpsteer_og_for_checker
Viewer • Updated • 47.2k • 9
spisupat/m1evalfixed_metaeval_assembled
Viewer • Updated • 108k • 9
spisupat/m2_ufall_trainvalid
Viewer • Updated • 43k • 8
spisupat/m1ufallinconsis
Viewer • Updated • 38.9k • 15
spisupat/m1ufall_metaeval_assembled
Viewer • Updated • 108k • 15
spisupat/m2_consistentimp_trainvalid
Viewer • Updated • 15.3k • 10
spisupat/m1inconsistent
Viewer • Updated • 9.3k • 7
spisupat/m1ref9to12_metaeval_assembled
Viewer • Updated • 19k • 5
spisupat/helpsteer_refined
Viewer • Updated • 53.1k • 6
spisupat/helpsteer_improve_assembled
Viewer • Updated • 18.4k • 5