added r1 evaluation logic

This commit is contained in:
joesharratt1229 2025-02-11 03:46:56 +00:00
parent 03f87dbc07
commit a3ea4449d1
6 changed files with 208 additions and 0 deletions

13
eval/r1/yaml/algebra.yaml Normal file
View file

@ -0,0 +1,13 @@
model: deepseek/deepseek-r1
category: algebra
datasets:
- intermediate_integration
- polynomial_equations
- polynomial_multiplication
- simple_equations
- simple_integration
- complex_arithmetic
eval_dir: eval/r1
dataset_size: 50
dataset_seed: 42
developer_role: system