simplescaling/s1K-1.1_tokenized
Viewer
• Updated • 1k • 123
• 1
Note s1K-1.1
Viewer
• Updated • 1k • 4
Note Teacher-generated
Viewer
• Updated • 1k • 6
Note Self-distill
Viewer
• Updated • 1k • 3
Note SKD-inspired
jaeh8nkim/s1K4Q3p6BUPFTstep1prob10
Viewer
• Updated • 1k • 7
Note RSD-generated (p_th=10%)
Viewer
• Updated • 1k • 3
Note RSD-generated (p_th=3%)
jaeh8nkim/s1K4Q3p6Bs1p17BtUPFTstep1
Viewer
• Updated • 1k • 8
Note RSD-generated (p_th=1%)
Viewer
• Updated • 1k • 2
Note RSD-generated (p_th=0.3%)
Viewer
• Updated • 1k • 3
Note RSD-generated (p_th=1%) tailored for Qwen3-1.7B
Viewer
• Updated • 1k • 3
Note RSD-generated (p_th=1%) tailored for Llama-3.2-1B-Instruct
jaeh8nkim/s1Kstudent203UP
Viewer
• Updated • 1k • 3
Note Self-distill (203 rejection sampling attempts)