Spaces:

Duplicated from yourbench/demo

heboya8
/

demo

Paused

App Files Files Community

demo / backend /tasks

2 contributors

History: 26 commits

sumuks's picture

Update backend/tasks/get_available_model_provider.py

4724e8f verified 6 months ago

__init__.py

45 Bytes

first commit 6 months ago
create_bench.py

12.5 kB

update error message and avoid double benchmark generation 6 months ago
create_bench_config_file.py

12.9 kB

change prompt for more creativity, and reduce overall number of questions generated 6 months ago
evaluation_task.py

17.1 kB

add llama 8b to models to evaluate as a baseline 6 months ago
get_available_model_provider.py

5.26 kB

Update backend/tasks/get_available_model_provider.py 6 months ago