khazic/illada-appov2-gsm8k
Updated
🔄 In a Training Loop
khazzz1c
khazic
AI & ML interests
Reinforcement Learning，Machine Learning
Recent Activity
updated a model 4 days ago
khazic/illada-appov2-gsm8k updated a model 4 days ago
khazic/illada-appov2-math published a model 6 days ago
khazic/illada-appov2-gsm8kOrganizations
models 24
khazic/illada-appov2-math
Updated
khazic/heat-math-fork-head-ablation
Updated
khazic/gemma4_12b_it_sft
Updated
khazic/gemma4_26b_a4b_sft
Updated
khazic/heat-gsm8k-appo
Updated
khazic/heat-gsm8k-forkhead-ablation
Updated
khazic/p_eagle_kv_reuse
Updated
khazic/automodel-qwen3-8b
Updated
khazic/heat-fork-head-math
Updated
datasets 13
khazic/peagle_qwen3_8b_4node
Viewer • Updated • 457k • 520
khazic/heat-rl-espo
Updated • 2.77k
khazic/kv-eagle-wandb
Viewer • Updated • 416 • 10
khazic/converage-comp-signature
Updated • 6
khazic/converage-rk-0.1-gsm8k
Updated • 3
khazic/heat-wandb
Viewer • Updated • 4.4k • 44
khazic/summary-0426
Updated • 2
khazic/output-426
Updated • 27
khazic/heat-outputs-0423
Updated • 36
khazic/ViRL-Rubric
Viewer • Updated • 28.4k • 59