RL-ready competition-physics dataset package (train + verified pool)
Ishaan
Darkyy
AI & ML interests
Post-Training LLMs
Recent Activity
updated a model about 4 hours ago
Darkyy/Qwen3-30b-a3b-indic-sft-epoch-2 published a model about 4 hours ago
Darkyy/Qwen3-30b-a3b-indic-sft-epoch-2 updated a model about 23 hours ago
Darkyy/qwen3-30b-a3b-indic-instruct-zero-0Organizations
None yet
models 8
Darkyy/Qwen3-30b-a3b-indic-sft-epoch-2
31B • Updated
Darkyy/qwen3-30b-a3b-indic-instruct-zero-0
31B • Updated • 94
Darkyy/MATH-GRPO
2B • Updated
Darkyy/Qwen-32B-SFT
Text Generation • 33B • Updated
Darkyy/Qwen-14B-Loop-Handling
Text Generation • 15B • Updated • 2 • 1
Darkyy/Qwen-14B-SFT
Text Generation • 15B • Updated
Darkyy/guarded_sarvam-m
Text Generation • 24B • Updated
Darkyy/guarded_gemma-3-1b-it
Text Generation • 1.0B • Updated • 3
datasets 7
Darkyy/indic-instruct-eval
Viewer • Updated • 597 • 34
Darkyy/indic-instruct
Viewer • Updated • 135k • 39
Darkyy/phy-rl-base
Viewer • Updated • 1.63k • 52
Darkyy/reasoners-1
Viewer • Updated • 27.8k • 13
Darkyy/Reasoning-SFT
Viewer • Updated • 27.8k • 7
Darkyy/multi-turn-conversations-dataset
Viewer • Updated • 1.25k • 7
Darkyy/Indic_Guard_SFT_Data
Viewer • Updated • 10.2k • 6