| .. |
|
groups
|
[Update] Add RULER 64k config (#1709)
|
2024-11-25 19:35:27 +08:00 |
|
agent_bench.py
|
[Format] Add config lints (#892)
|
2024-05-14 15:35:58 +08:00 |
|
charm_reason.py
|
[Sync] Sync with internal codes 2024.06.28 (#1279)
|
2024-06-28 14:16:34 +08:00 |
|
chat_OC15_multi_faceted.py
|
[Sync] bump version (#1204)
|
2024-05-28 23:09:59 +08:00 |
|
chat_OC15.py
|
[Format] Add config lints (#892)
|
2024-05-14 15:35:58 +08:00 |
|
cibench.py
|
[Format] Add config lints (#892)
|
2024-05-14 15:35:58 +08:00 |
|
code_passk.py
|
[Format] Add config lints (#892)
|
2024-05-14 15:35:58 +08:00 |
|
compassbench_v1_1_objective_public.py
|
[Sync] Sync with internal codes 2024.06.28 (#1279)
|
2024-06-28 14:16:34 +08:00 |
|
compassbench_v1_1_objective.py
|
[Sync] Sync with internal codes 2024.06.28 (#1279)
|
2024-06-28 14:16:34 +08:00 |
|
compassbench_v1_3_objective.py
|
[Update] Compassbench v1.3 (#1396)
|
2024-08-12 19:09:19 +08:00 |
|
compassbench_v1_objective.py
|
[Sync] update github workflow (#1156)
|
2024-05-14 22:42:23 +08:00 |
|
contamination.py
|
[Format] Add config lints (#892)
|
2024-05-14 15:35:58 +08:00 |
|
example.py
|
Add en and zh groups to longbench summarizer; Fix longbench overall score (#1216)
|
2024-07-26 11:50:41 +08:00 |
|
infinitebench.py
|
[Format] Add config lints (#892)
|
2024-05-14 15:35:58 +08:00 |
|
internlm2_keyset.py
|
[Format] Add config lints (#892)
|
2024-05-14 15:35:58 +08:00 |
|
lawbench.py
|
[Format] Add config lints (#892)
|
2024-05-14 15:35:58 +08:00 |
|
leaderboard.py
|
[Format] Add config lints (#892)
|
2024-05-14 15:35:58 +08:00 |
|
leval.py
|
[Sync] Add InternLM2 Keyset Evaluation Demo (#807)
|
2024-01-17 13:48:12 +08:00 |
|
longbench.py
|
[Sync] Add InternLM2 Keyset Evaluation Demo (#807)
|
2024-01-17 13:48:12 +08:00 |
|
longeval_v2.py
|
[Sync] Sync with internal codes 2023.01.08 (#777)
|
2024-01-08 14:07:24 +00:00 |
|
lveval.py
|
[Format] Add config lints (#892)
|
2024-05-14 15:35:58 +08:00 |
|
math_agent.py
|
[Format] Add config lints (#892)
|
2024-05-14 15:35:58 +08:00 |
|
math_baseline.py
|
[Format] Add config lints (#892)
|
2024-05-14 15:35:58 +08:00 |
|
mathbench_v1.py
|
[Format] Add config lints (#892)
|
2024-05-14 15:35:58 +08:00 |
|
mathbench.py
|
[Format] Add config lints (#892)
|
2024-05-14 15:35:58 +08:00 |
|
medium.py
|
[Format] Add config lints (#892)
|
2024-05-14 15:35:58 +08:00 |
|
mmlu_pro.py
|
[Sync] Sync with internal codes 2024.06.28 (#1279)
|
2024-06-28 14:16:34 +08:00 |
|
needlebench.py
|
[Feature] Add long context evaluation for base models (#1666)
|
2024-11-08 10:53:29 +08:00 |
|
plugineval.py
|
[Format] Add config lints (#892)
|
2024-05-14 15:35:58 +08:00 |
|
ruler.py
|
[Update] Add RULER 64k config (#1709)
|
2024-11-25 19:35:27 +08:00 |
|
scicode.py
|
[Feature] Add SciCode summarizer config (#1514)
|
2024-09-10 16:06:02 +08:00 |
|
small.py
|
[Format] Add config lints (#892)
|
2024-05-14 15:35:58 +08:00 |
|
subjective.py
|
[Sync] update github token (#475)
|
2023-10-13 06:50:54 -05:00 |
|
teval.py
|
[Format] Add config lints (#892)
|
2024-05-14 15:35:58 +08:00 |
|
tiny.py
|
[Format] Add config lints (#892)
|
2024-05-14 15:35:58 +08:00 |
