0-hero/r1-7B-grpo-v3.3-epoch-3
8B
•
Updated
•
1
R1-GRPO-Math-Python-Code-Experiments
Lora & full finetune experiments on r1 distills to generate python code for math problems
-
-
0-hero/r1-7B-grpo-v3.3-epoch-2
8B • Updated • 2 -
0-hero/r1-7B-grpo-v3.3-epoch-1
8B • Updated • 1 -
0-hero/r1-7B-grpo-v3.2-epoch-1
8B • Updated • 1 -
0-hero/r1-7B-grpo-v3.2-epoch-2
8B • Updated • 1 -
0-hero/r1-14B-grpo-v3.1-epoch-2
15B • Updated • 1 -
0-hero/r1-14B-grpo-v3.1-epoch-1
15B • Updated • 1 -
0-hero/r1-7B-grpo-v3.1-epoch-3
8B • Updated • 1 -
0-hero/r1-7B-grpo-v3.1-epoch-2
8B • Updated • 1 -
0-hero/r1-7B-grpo-v2-temp-1.0-60
8B • Updated • 2 -
0-hero/r1-14B-math-grpo-165
15B • Updated • 1 -
0-hero/r1-14B-math-grpo-80
15B • Updated • 1 -
0-hero/r1-7B-grpo-850
8B • Updated • 2 -
0-hero/r1-7B-grpo-710
8B • Updated • 1 -
0-hero/r1-7B-grpo-610
8B • Updated • 1 -
0-hero/r1-7B-grpo-80
8B • Updated • 1 -
0-hero/R1-7B-MATH-GRPO-FULL
8B • Updated • 1 -
0-hero/R1-14B-GRPO
15B • Updated • 3 -
0-hero/r1-7b-grpo-full
8B • Updated • 2 -
0-hero/r1-8b-grpo-full
Updated