consolidate eval scripts to have single eval.py

This commit is contained in:
Andreas Koepf 2025-02-25 16:13:22 +01:00
parent bea806fe3c
commit e7ae82a831
12 changed files with 104 additions and 337 deletions

View file

@ -0,0 +1,24 @@
model: deepseek/deepseek-r1
category: algorithmic
datasets:
- 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