leaderboard / scripts

Commit History

Add llama2, sort ShareGPT dataset by length (#18)
f0128b6
unverified

Zhiyu Wu commited on

Fix: End of file handling in `benchmark.py` (#16)
3d567c0
unverified

Zhiyu Wu Zhiyu Wu commited on

Add batching to benchmark.py (#13)
36058af
unverified

Zhiyu Wu commited on

Fix NLP evaluation result paths
dcc2472

Jae-Won Chung commited on

Better names for scripts
f5248c1

Jae-Won Chung commited on

Add aggregate_nlp_metrics.py and more precise score.csv
f98b171

Jae-Won Chung commited on

read_score
91c65f8

Zhiyu Wu commited on

Improve pegasus README.md
4a385c8

Jae-Won Chung commited on

Do not makedir when there is no dir
176e245

Jae-Won Chung commited on

Make print_metrics.py recursive
94f739f

Jae-Won Chung commited on

Update scripts/print_results.py
78fec8f

Jae-Won Chung commited on

Add print_results.py
93263f1

Jae-Won Chung commited on

Benchmarking with Pegasus (#7)
4e9ddf9
unverified

Jae-Won Chung commited on

Make outfile directory
ce6d832

Jae-Won Chung commited on

Fix benchmark.py docstring
2fb0234

Jae-Won Chung commited on

Clean up
e3571c1

Jae-Won Chung commited on