mirror of
https://github.com/open-thought/reasoning-gym.git
synced 2026-04-19 12:58:07 +00:00
added r1 evaluation logic
This commit is contained in:
parent
03f87dbc07
commit
a3ea4449d1
6 changed files with 208 additions and 0 deletions
25
eval/r1/yaml/algorithmic.yaml
Normal file
25
eval/r1/yaml/algorithmic.yaml
Normal file
|
|
@ -0,0 +1,25 @@
|
|||
model: deepseek/deepseek-r1
|
||||
category: algorithmic
|
||||
datasets:
|
||||
- base_conversion
|
||||
- binary_matrix
|
||||
- caesar _cipher
|
||||
- group_anagrams
|
||||
- isomorphic_strings
|
||||
- letter_counting
|
||||
- letter_jumble
|
||||
- number_filtering
|
||||
- number_sorting
|
||||
- palindrome
|
||||
- ransom_note
|
||||
- rotate_matrix
|
||||
- sentence_reordering
|
||||
- spell_backward
|
||||
- spiral_matrix
|
||||
- word_ladder
|
||||
- word_sequence_reversal
|
||||
- word_sorting
|
||||
eval_dir: eval/r1
|
||||
dataset_size: 50
|
||||
dataset_seed: 42
|
||||
developer_role: system
|
||||
Loading…
Add table
Add a link
Reference in a new issue