 Nicholas Carlini
|
be07d215b2
Improve evaluations for several tests
|
7 ay önce |
|
Nicholas Carlini
|
656a597d01
Add support for incremental builds of results
|
8 ay önce |
|
Nicholas Carlini
|
872a90b3ae
Minor changes
|
10 ay önce |
|
Nicholas Carlini
|
364120ea26
Update to final run config
|
10 ay önce |
|
Nicholas Carlini
|
7169652815
Minor tweaks
|
10 ay önce |
|
Nicholas Carlini
|
23c2965686
Add podman option
|
10 ay önce |
|
Nicholas Carlini
|
e50ca985fc
A bunch of changes for release
|
10 ay önce |
|
Nicholas Carlini
|
e676a59407
Produce logfile of runs
|
11 ay önce |
|
Nicholas Carlini
|
0ca90d3609
Add summary of each test
|
11 ay önce |
|
Nicholas Carlini
|
1d173a1627
Prepare description addition
|
11 ay önce |
 srxzr
|
521ed3896c
adding preample and also new tests
|
11 ay önce |
|
Nicholas Carlini
|
5656488a16
Add ability for llm to work with interactive processes
|
11 ay önce |
|
Nicholas Carlini
|
e425c714aa
More tests, fixes to models
|
11 ay önce |
|
Nicholas Carlini
|
7f830465f3
Add tags to each test
|
11 ay önce |
|
Nicholas Carlini
|
0737c24c6f
Split llms across files, a few new tests
|
11 ay önce |
|
Nicholas Carlini
|
70e5ca5889
A bunch of tests
|
11 ay önce |
