Hugging Face's logo

Spaces:
yourbench
/
demo
Running on CPU Upgrade

App Files Community
1
demo / backend /tasks /create_bench_config_file.py

Commit History

update intro | fix evaluation
a86c1f9

tfrere commited on

update models
ab8d3f5

tfrere commited on

update error handling, improve upload security checks
81e0b0c

tfrere commited on

add qwen2.5 32b as the default
eee5a9a

sumuks commited on

change prompt for more creativity, and reduce overall number of questions generated
da80f69
verified

sumuks commited on

temporarily change to llama 8b to allow more scale
89c3b6d
verified

sumuks commited on

update error message and avoid double benchmark generation
7f7e436

tfrere commited on

add get available model provider to benchmark generation
0e34dc4

tfrere commited on

update lighteval results
39acd70

tfrere commited on

add prerendered documents | update filename | refactor
ffa4ae8

tfrere commited on