Our benchmark for multimodal unlearning methods
Alexey Dontsov
therem
AI & ML interests
None yet
Recent Activity
upvoted a paper 3 days ago
The More Popular, The Harder to Forget: Adaptive Popularity for LLM Unlearning liked a dataset 15 days ago
AntonKorznikov/feature_stories liked a dataset 16 days ago
Ivanich/nla-eval-suiteOrganizations
models 41
therem/affect10k-critic-sft-iter78
5B • Updated • 9
therem/affect10k-rl-iter120
Updated
therem/nla-qwen2.5-3b-L24-rl-v13-av
3B • Updated • 52
therem/nla-qwen2.5-3b-L24-sft-av
3B • Updated • 19
therem/nla-qwen2.5-3b-L24-rl-iter5000-ar
2B • Updated • 17
therem/nla-qwen2.5-3b-L24-rl-v13-ar
2B • Updated • 29
therem/nla-qwen2.5-3b-L24-rl-iter4000-av
3B • Updated • 24
therem/nla-qwen2.5-3b-L24-rl-iter4000-ar
2B • Updated • 20
therem/nla-qwen2.5-3b-L24-sft-ar
2B • Updated • 21
therem/nla-qwen2.5-3b-L24-rl-iter5000-av
3B • Updated • 20
datasets 24
therem/novel-ops-impossible
Viewer • Updated • 600 • 13
therem/novel-ops-reasoning
Viewer • Updated • 1.5k • 40
therem/all_math_generations
Viewer • Updated • 52.1k • 50
therem/deepseek_ai_deepseek_math_7b_instructHuggingFaceH4_MATH_500
Updated • 6
therem/qwen3_math_ai_minervamath_4x
Viewer • Updated • 1.09k • 18
therem/qwen3_math_ai_olympiadbench_4x
Viewer • Updated • 2.7k • 10
therem/qwen3_HuggingFaceH4_MATH_500_4x
Viewer • Updated • 2k • 9
therem/qwen_math_math_ai_minervamath_8x
Viewer • Updated • 2.18k • 10
therem/qwen_math_math_ai_olympiadbench_8x
Viewer • Updated • 5.39k • 13
therem/qwen_math_HuggingFaceH4_MATH_500_8x
Viewer • Updated • 4k • 14