Saksham Loonker

SLoonker

·

saksham-loonker

AI & ML interests

I am very interested in RL and other post-training, as well as building Efficient LLMs for Sparse Resources.

Recent Activity

liked a dataset about 23 hours ago

r0b0tlab/qwen3.8-max-glm5.2-kimi-k3-distillation

liked a dataset 2 days ago

israellaguan/codex-tool-use-trajectories

liked a model 3 months ago

Qwen/Qwen3.8-27B

View all activity

Organizations

None yet

SLoonker 's datasets 15

SLoonker/Nemotron-Ultra-1000x

Viewer • Updated Jun 15 • 979 • 46

SLoonker/Deepseek-V4-Distill-Combined-14000x

Viewer • Updated May 14 • 14k • 88 • 2

SLoonker/Deepseek-V4-Flash-11000x

Viewer • Updated May 14 • 11.2k • 68 • 2

SLoonker/GPT-5.5-Distill-1.6k

Viewer • Updated May 10 • 1.7k • 197 • 5

SLoonker/GLM-5.1-Reasoning-1M-Cleaned-Denumbered

Viewer • Updated May 4 • 254k • 139

SLoonker/Grok-Code-Fast-1-Distillation-Done-By-GPT5.4

Viewer • Updated Apr 25 • 500 • 40 • 2

SLoonker/Mistral-Small-4-Reasoning-315x

Viewer • Updated Mar 23 • 315 • 8

SLoonker/Kimi-K2.5-Reasoning-300x

Viewer • Updated Mar 18 • 300 • 9

SLoonker/RL-Claude-Reasoning-SFT

Viewer • Updated Mar 5 • 2.21k • 52 • 2

SLoonker/RL-Claude-Reasoning-GRPO-Prompts

Viewer • Updated Mar 5 • 2.21k • 19

SLoonker/RL-Ling-Coding-DPO

Viewer • Updated Mar 5 • 2.84k • 10

SLoonker/RL-Claude-Creative-Writing-SFT

Viewer • Updated Mar 5 • 818 • 3.02k • 1

SLoonker/RL-STEM-DPO

Viewer • Updated Mar 5 • 1.51k • 11

SLoonker/RL-Claude-Creative-Writing-DPO

Viewer • Updated Mar 5 • 818 • 1.47k

SLoonker/RL-OpenCodeReasoning-DPO

Viewer • Updated Mar 5 • 2.75k • 21