evalscope 0.16.2__py3-none-any.whl → 0.16.3__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Potentially problematic release.
This version of evalscope might be problematic. Click here for more details.
- evalscope/models/adapters/base_adapter.py +0 -2
- evalscope/version.py +2 -2
- {evalscope-0.16.2.dist-info → evalscope-0.16.3.dist-info}/METADATA +1 -1
- {evalscope-0.16.2.dist-info → evalscope-0.16.3.dist-info}/RECORD +9 -9
- tests/cli/test_run.py +3 -3
- {evalscope-0.16.2.dist-info → evalscope-0.16.3.dist-info}/LICENSE +0 -0
- {evalscope-0.16.2.dist-info → evalscope-0.16.3.dist-info}/WHEEL +0 -0
- {evalscope-0.16.2.dist-info → evalscope-0.16.3.dist-info}/entry_points.txt +0 -0
- {evalscope-0.16.2.dist-info → evalscope-0.16.3.dist-info}/top_level.txt +0 -0
|
@@ -54,8 +54,6 @@ def initialize_model_adapter(task_cfg: 'TaskConfig', benchmark: 'DataAdapter', b
|
|
|
54
54
|
|
|
55
55
|
if 'server' not in model_adapter_cls_str:
|
|
56
56
|
model_adapter_cls_str = 'server'
|
|
57
|
-
logger.info(
|
|
58
|
-
f'Using {model_adapter_cls.__name__} for api model evaluation for benchmark {benchmark.name}.')
|
|
59
57
|
|
|
60
58
|
# init server model adapter
|
|
61
59
|
model_adapter_cls = get_model_adapter(model_adapter_cls_str)
|
evalscope/version.py
CHANGED
|
@@ -5,7 +5,7 @@ evalscope/constants.py,sha256=1CYghe0fGccyiVgzMIHd2HIb6lOo9fmB-8pH_l99iI4,4014
|
|
|
5
5
|
evalscope/run.py,sha256=ss7ECL4dq18ur9qFOWqCNIsckXQWWl1EsVaJxDPBVq8,7000
|
|
6
6
|
evalscope/run_arena.py,sha256=WXPCT0L-b_KvLBQ9KnrVW6y8icdDcqVhaXjTZMpS8k8,8572
|
|
7
7
|
evalscope/summarizer.py,sha256=nZOaXfaSaXht8GAVik_Pvz2YL0Gv24UG45mMklyBkvA,5938
|
|
8
|
-
evalscope/version.py,sha256=
|
|
8
|
+
evalscope/version.py,sha256=zdIprYl0JT22Bpk3tCmkfp1QLsi0mvROpxeTcgkCNHI,119
|
|
9
9
|
evalscope/app/__init__.py,sha256=HWLXld_JXcBDsdL4L_4E8JsKyuBwwPUSwlejKnZ3HKc,579
|
|
10
10
|
evalscope/app/app.py,sha256=QyO0RFfkLeOVzx-Mr8br3bYPwii2O_eVGmNgwCGHkac,29863
|
|
11
11
|
evalscope/app/arguments.py,sha256=1wHTLeFx1G94cKXYOeOVe_wTiOY2D929UctIRGOtRaQ,699
|
|
@@ -340,7 +340,7 @@ evalscope/models/local_model.py,sha256=UWsmZlWpT8JNGjijzZQKirvq4YywBkKOS9G-U2cux
|
|
|
340
340
|
evalscope/models/model.py,sha256=MxvJAUNkuT7IA3bchnmJDur_YCKj9ShOD2Uq40dBcGc,6308
|
|
341
341
|
evalscope/models/register.py,sha256=WiylzfL-vb6Bl3H3_RdIaBabVOAc9tiuhsQzYJDVzTg,1948
|
|
342
342
|
evalscope/models/adapters/__init__.py,sha256=zmldx8yC_KTI8NDRcxNLyPzv19wc57UvOVvzwyuYnG4,647
|
|
343
|
-
evalscope/models/adapters/base_adapter.py,sha256=
|
|
343
|
+
evalscope/models/adapters/base_adapter.py,sha256=TfINK84g4mqmHcnqvvHmk-MXRN2Pkan4yVlVd4j0nVY,3166
|
|
344
344
|
evalscope/models/adapters/bfcl_adapter.py,sha256=KtreuJ21X1lcUGGhVgW3U62p3P65_oydMdBPtE5um-I,10332
|
|
345
345
|
evalscope/models/adapters/chat_adapter.py,sha256=PAClyBL_nQ1I1kmjeeZ3sdC-y5ZmfFj8rjCigh_vr40,7885
|
|
346
346
|
evalscope/models/adapters/choice_adapter.py,sha256=4fuz3MFEqK8ln4mMs3goMCdRPBwYmmgN70HTdr_sW_U,8005
|
|
@@ -457,7 +457,7 @@ tests/aigc/test_t2i.py,sha256=Dqug3rV7EIkj6uwBjgj5UMj8ZrpGSznSHfn2g8J_P3M,3860
|
|
|
457
457
|
tests/cli/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
|
|
458
458
|
tests/cli/test_all.py,sha256=yo1ysDM90dI_kWxKKPOf-BsYneeRYRJa5uh6_7SDZ3Y,4332
|
|
459
459
|
tests/cli/test_collection.py,sha256=jIGQNQO4msJE9w4Ms5qxtuhkHVukeLcHvBF2dzHCKCI,4207
|
|
460
|
-
tests/cli/test_run.py,sha256=
|
|
460
|
+
tests/cli/test_run.py,sha256=98OPX7h2_fDmGtQHJWzGA2pjd_vhgKkTIEYgeLMkRo4,18640
|
|
461
461
|
tests/perf/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
|
|
462
462
|
tests/perf/test_perf.py,sha256=VbXsqiqgQY3R3bVKizYQmP04UPluUS26MO6YhTzMs48,4848
|
|
463
463
|
tests/rag/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
@@ -470,9 +470,9 @@ tests/swift/test_run_swift_vlm_eval.py,sha256=C8DftjewnZaerQWfERI70bU3sQLWQ-ejZU
|
|
|
470
470
|
tests/swift/test_run_swift_vlm_jugde_eval.py,sha256=THZEXUOSqm9rWslwJHmZyh-Ytv5c_QKpgRW5J2s_69E,6017
|
|
471
471
|
tests/vlm/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
|
|
472
472
|
tests/vlm/test_vlmeval.py,sha256=UqRiBPMU3vRtLIG1Qu4ZVhyUQx-zGYQuLCgobwf-7a4,3176
|
|
473
|
-
evalscope-0.16.
|
|
474
|
-
evalscope-0.16.
|
|
475
|
-
evalscope-0.16.
|
|
476
|
-
evalscope-0.16.
|
|
477
|
-
evalscope-0.16.
|
|
478
|
-
evalscope-0.16.
|
|
473
|
+
evalscope-0.16.3.dist-info/LICENSE,sha256=K_2M03pN0PxVMyx9IQUKsHGhhDMkw5ryQ02rlMvzj3I,11416
|
|
474
|
+
evalscope-0.16.3.dist-info/METADATA,sha256=6PnfUd1rJfGeAJ-7KowXFFbwP8xVw7r9-3u6HRlJHic,36533
|
|
475
|
+
evalscope-0.16.3.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
|
|
476
|
+
evalscope-0.16.3.dist-info/entry_points.txt,sha256=Qr4oTgGhg_K-iUtKwVH6lWUhFHDUiH9trIqydHGTEug,56
|
|
477
|
+
evalscope-0.16.3.dist-info/top_level.txt,sha256=Yv0iprOqZQ4rfUO-AWJp7Ni6m0Twxny1yvZwO-8hUDM,16
|
|
478
|
+
evalscope-0.16.3.dist-info/RECORD,,
|
tests/cli/test_run.py
CHANGED
|
@@ -305,8 +305,8 @@ class TestRun(unittest.TestCase):
|
|
|
305
305
|
# 'arc',
|
|
306
306
|
# 'ceval',
|
|
307
307
|
# 'hellaswag',
|
|
308
|
-
'general_mcq',
|
|
309
|
-
|
|
308
|
+
# 'general_mcq',
|
|
309
|
+
'general_qa',
|
|
310
310
|
# 'super_gpqa',
|
|
311
311
|
# 'mmlu_redux',
|
|
312
312
|
# 'maritime_bench',
|
|
@@ -396,7 +396,7 @@ class TestRun(unittest.TestCase):
|
|
|
396
396
|
# 'extra_headers':{'key': 'value'},
|
|
397
397
|
},
|
|
398
398
|
ignore_errors=False,
|
|
399
|
-
|
|
399
|
+
use_cache='outputs/test_2'
|
|
400
400
|
)
|
|
401
401
|
|
|
402
402
|
run_task(task_cfg=task_cfg)
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|