途中過程で実験したやつなど(チームレポジトリ作成前に自分のところにuploadしたものが主なものです)
Taiki METOKI
Ta1k1
AI & ML interests
None yet
Recent Activity
upvoted a paper 2 days ago
LEV: Thinking Fast and Deep with Looped Decision Models liked a Space 2 months ago
openadmet/cyp-challenge liked a Space 3 months ago
sepiq-2026/SEPIQ-2026-ChallengeOrganizations
models 21
Ta1k1/llm_2025_exp003_grpo_v5
Updated
Ta1k1/llm_2025_exp001_grpo
Text Generation • Updated • 8
Ta1k1/llm_2025_exp001
Text Generation • Updated • 10
Ta1k1/qwen3-vl-pr-generator
Updated
Ta1k1/llava-calm2-siglip-finetuning_v3
Updated
Ta1k1/llava-calm2-siglip-finetuning_v2
Image-Text-to-Text • 7B • Updated • 10
Ta1k1/llava-calm2-siglip-finetuning
Image-Text-to-Text • 7B • Updated • 12
Ta1k1/Qwen3-32B-SFT-OmniMath-8epoch
33B • Updated • 6
Ta1k1/Qwen3-32B-SFT-AIME
33B • Updated • 5
Ta1k1/Qwen3-32B-SFT-MATH
33B • Updated • 10
datasets 12
Ta1k1/AIME2024
Viewer • Updated • 29 • 19
Ta1k1/HLE_text_200
Viewer • Updated • 200 • 1.34k
Ta1k1/Open-R1-Math_DESC
Viewer • Updated • 10k • 21
Ta1k1/HLE_200-3
Viewer • Updated • 600 • 9.32k
Ta1k1/OMNI_MATH_10000
Viewer • Updated • 10k • 34
Ta1k1/omni_math_2000
Viewer • Updated • 2k • 8
Ta1k1/omni_math_
Viewer • Updated • 4.43k • 6
Ta1k1/OMNI_MATH_split
Viewer • Updated • 1k • 10
Ta1k1/aime_1983-2024_split
Viewer • Updated • 933 • 19
Ta1k1/omni_math_think_answer
Viewer • Updated • 1k • 14