khazzz1c's picture

In a Training Loop 🔄

khazzz1c

khazic

·

https://github.com/khazic

AI & ML interests

Reinforcement Learning，Machine Learning

Recent Activity

updated a dataset 3 days ago

khazic/converage-rk-0.1-gsm8k

published a dataset 3 days ago

khazic/converage-rk-0.1-gsm8k

updated a model 8 days ago

khazic/appo-simpson5

View all activity

Organizations

models 10

khazic/appo-simpson5

Updated 8 days ago

khazic/output-426

Updated 20 days ago

khazic/heat-outputs

khazic/rubrics_sft_qwen3_vl-v16-20260323-073955

khazic/rubrics_sft_qwen3_vl_ckpt1200

khazic/Albatross

khazic/kkk

khazic/eagle

Updated Nov 20, 2025

khazic/heat

Updated Nov 19, 2025

khazic/Ariadne

Updated Oct 5, 2025 • 1

datasets 9

khazic/converage-rk-0.1-gsm8k

Updated 3 days ago • 27

khazic/heat-wandb

Viewer • Updated 14 days ago • 4.4k • 62

khazic/summary-0426

Updated 20 days ago • 27

khazic/output-426

Updated 20 days ago • 234

khazic/heat-outputs-0423

Updated 24 days ago • 128

khazic/ViRL-Rubric

Viewer • Updated Feb 10 • 28.4k • 100

khazic/embed

Updated Jan 13 • 43

khazic/CrossLingMind_DataSet

Preview • Updated Oct 16, 2025 • 19

khazic/xhs_50k

Viewer • Updated Jun 7, 2024 • 52.4k • 21 • 2