bluebench / src /leaderboard /read_evals.py

Commit History

Ignore non-json files
5dc0fc8
unverified

jbnayahu commited on

.
382809d
unverified

jbnayahu commited on

Cleanup
460efe2
unverified

jbnayahu commited on

Remove model links.
6066b5d
unverified

jbnayahu commited on

Switch to read local results only.
3a4f28e
unverified

jbnayahu commited on

.
98eb96a
unverified

jbnayahu commited on

doc
5fe3b95

Clémentine commited on

simplified the template
bbd72ab

Clémentine commited on

now with a functionning backend
01ea22b

Clémentine commited on

update read
4f3c2a8

Clémentine commited on

Simplified leaderboard v0
2a860f6

Clémentine commited on

simplified some parts of the code + updated requirements
3d8dbe8

Clémentine commited on

add model architecture as column
1ba1924

Clémentine commited on

Refactor 2 - added plotting back
ceb2102

Clémentine commited on

Fix requirements for mistral models - to change once transformers gets updated.
c875275

Clémentine commited on

fix col width
16a06c4

Clémentine commited on

refacto style + rate limit
3b3db42

Clémentine commited on

Fix TruthfulQA NaN scores to 0
992b592

Clémentine commited on

refacto part 1
8b1f7a0

Clémentine commited on