|
benchmarks
|
.
|
2025-05-11 00:41:07 +08:00 |
|
multi_modal
|
.
|
2025-05-11 00:41:07 +08:00 |
|
retrieval
|
.
|
2025-05-11 00:41:07 +08:00 |
|
tonic_validate
|
.
|
2025-05-11 00:41:07 +08:00 |
|
__init__.py
|
.
|
2025-05-11 00:41:07 +08:00 |
|
answer_relevancy.py
|
.
|
2025-05-11 00:41:07 +08:00 |
|
base.py
|
.
|
2025-05-11 00:41:07 +08:00 |
|
batch_runner.py
|
.
|
2025-05-11 00:41:07 +08:00 |
|
context_relevancy.py
|
.
|
2025-05-11 00:41:07 +08:00 |
|
correctness.py
|
.
|
2025-05-11 00:41:07 +08:00 |
|
dataset_generation.py
|
.
|
2025-05-11 00:41:07 +08:00 |
|
eval_utils.py
|
.
|
2025-05-11 00:41:07 +08:00 |
|
faithfulness.py
|
.
|
2025-05-11 00:41:07 +08:00 |
|
guideline.py
|
.
|
2025-05-11 00:41:07 +08:00 |
|
notebook_utils.py
|
.
|
2025-05-11 00:41:07 +08:00 |
|
pairwise.py
|
.
|
2025-05-11 00:41:07 +08:00 |
|
relevancy.py
|
.
|
2025-05-11 00:41:07 +08:00 |
|
semantic_similarity.py
|
.
|
2025-05-11 00:41:07 +08:00 |