Arvind Rajasekaran

arvindcr4

·

AI & ML interests

None yet

Organizations

None yet

spaces 1

TinkerRL-Bench Demo

TinkerRL-Bench reproducibility study (Group 6 viva)

models 42

arvindcr4/tinker-rl-w1_deepseek-v31-base-deepseek-v3.1-base-s42

arvindcr4/tinker-rl-frontier_gsm8k_nemotron-120b-nemotron-120b

Reinforcement Learning • Updated Apr 19

arvindcr4/tinker-rl-frontier_gsm8k_deepseek-v3.1-deepseek-v3.1

Reinforcement Learning • Updated Apr 19

arvindcr4/tinker-rl-arch_gsm8k_kimi-k2-kimi-k2

Reinforcement Learning • Updated Apr 19

arvindcr4/tinker-rl-w2_qwen3-8b_g4-qwen3-8b-s42

Reinforcement Learning • Updated Apr 19

arvindcr4/tinker-rl-w2_qwen3-8b_g32-qwen3-8b-s42

Reinforcement Learning • Updated Apr 19

arvindcr4/tinker-rl-w2_qwen3-8b_g2-qwen3-8b-s42

Reinforcement Learning • Updated Apr 19

arvindcr4/tinker-rl-w2_qwen3-8b_g16-qwen3-8b-s42

Reinforcement Learning • Updated Apr 19

arvindcr4/tinker-rl-w1_qwen3-8b-base-qwen3-8b-base-s42-run1

Reinforcement Learning • Updated Apr 19

arvindcr4/tinker-rl-w1_qwen3-8b-base-qwen3-8b-base-s42-run2

Reinforcement Learning • Updated Apr 19

datasets 2

arvindcr4/tinker-rl-bench-checkpoints

Viewer • Updated Apr 19 • 94 • 28

arvindcr4/tinker-rl-bench-wandb

Viewer • Updated Apr 19 • 9.59k • 23