transformers 4.57.4__py3-none-any.whl → 4.57.6__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.
- transformers/__init__.py +1 -1
- transformers/models/qwen2_5_vl/configuration_qwen2_5_vl.py +3 -1
- transformers/models/qwen2_vl/configuration_qwen2_vl.py +3 -1
- transformers/training_args.py +3 -3
- {transformers-4.57.4.dist-info → transformers-4.57.6.dist-info}/METADATA +1 -1
- {transformers-4.57.4.dist-info → transformers-4.57.6.dist-info}/RECORD +10 -10
- {transformers-4.57.4.dist-info → transformers-4.57.6.dist-info}/WHEEL +0 -0
- {transformers-4.57.4.dist-info → transformers-4.57.6.dist-info}/entry_points.txt +0 -0
- {transformers-4.57.4.dist-info → transformers-4.57.6.dist-info}/licenses/LICENSE +0 -0
- {transformers-4.57.4.dist-info → transformers-4.57.6.dist-info}/top_level.txt +0 -0
transformers/__init__.py
CHANGED
|
@@ -18,7 +18,7 @@
|
|
|
18
18
|
# to defer the actual importing for when the objects are requested. This way `import transformers` provides the names
|
|
19
19
|
# in the namespace without actually importing anything (and especially none of the backends).
|
|
20
20
|
|
|
21
|
-
__version__ = "4.57.
|
|
21
|
+
__version__ = "4.57.6"
|
|
22
22
|
|
|
23
23
|
from pathlib import Path
|
|
24
24
|
from typing import TYPE_CHECKING
|
|
@@ -340,7 +340,7 @@ class Qwen2_5_VLConfig(PretrainedConfig):
|
|
|
340
340
|
def __setattr__(self, key, value):
|
|
341
341
|
if (
|
|
342
342
|
(text_config := super().__getattribute__("__dict__").get("text_config")) is not None
|
|
343
|
-
and key not in ["dtype", "_attn_implementation_internal"]
|
|
343
|
+
and key not in ["_name_or_path", "model_type", "dtype", "_attn_implementation_internal"]
|
|
344
344
|
and key in text_config.__dict__
|
|
345
345
|
):
|
|
346
346
|
setattr(text_config, key, value)
|
|
@@ -349,6 +349,8 @@ class Qwen2_5_VLConfig(PretrainedConfig):
|
|
|
349
349
|
|
|
350
350
|
def __getattribute__(self, key):
|
|
351
351
|
if "text_config" in super().__getattribute__("__dict__") and key not in [
|
|
352
|
+
"_name_or_path",
|
|
353
|
+
"model_type",
|
|
352
354
|
"dtype",
|
|
353
355
|
"_attn_implementation_internal",
|
|
354
356
|
]:
|
|
@@ -329,7 +329,7 @@ class Qwen2VLConfig(PretrainedConfig):
|
|
|
329
329
|
def __setattr__(self, key, value):
|
|
330
330
|
if (
|
|
331
331
|
(text_config := super().__getattribute__("__dict__").get("text_config")) is not None
|
|
332
|
-
and key not in ["dtype", "_attn_implementation_internal"]
|
|
332
|
+
and key not in ["_name_or_path", "model_type", "dtype", "_attn_implementation_internal"]
|
|
333
333
|
and key in text_config.__dict__
|
|
334
334
|
):
|
|
335
335
|
setattr(text_config, key, value)
|
|
@@ -338,6 +338,8 @@ class Qwen2VLConfig(PretrainedConfig):
|
|
|
338
338
|
|
|
339
339
|
def __getattribute__(self, key):
|
|
340
340
|
if "text_config" in super().__getattribute__("__dict__") and key not in [
|
|
341
|
+
"_name_or_path",
|
|
342
|
+
"model_type",
|
|
341
343
|
"dtype",
|
|
342
344
|
"_attn_implementation_internal",
|
|
343
345
|
]:
|
transformers/training_args.py
CHANGED
|
@@ -303,7 +303,7 @@ class TrainingArguments:
|
|
|
303
303
|
`max_steps` is reached.
|
|
304
304
|
lr_scheduler_type (`str` or [`SchedulerType`], *optional*, defaults to `"linear"`):
|
|
305
305
|
The scheduler type to use. See the documentation of [`SchedulerType`] for all possible values.
|
|
306
|
-
lr_scheduler_kwargs (
|
|
306
|
+
lr_scheduler_kwargs (`dict` or `str`, *optional*, defaults to `None`):
|
|
307
307
|
The extra arguments for the lr_scheduler. See the documentation of each scheduler for possible values.
|
|
308
308
|
warmup_ratio (`float`, *optional*, defaults to 0.0):
|
|
309
309
|
Ratio of total training steps used for a linear warmup from 0 to `learning_rate`.
|
|
@@ -928,8 +928,8 @@ class TrainingArguments:
|
|
|
928
928
|
default="linear",
|
|
929
929
|
metadata={"help": "The scheduler type to use."},
|
|
930
930
|
)
|
|
931
|
-
lr_scheduler_kwargs: Union[dict
|
|
932
|
-
|
|
931
|
+
lr_scheduler_kwargs: Optional[Union[dict, str]] = field(
|
|
932
|
+
default=None,
|
|
933
933
|
metadata={
|
|
934
934
|
"help": (
|
|
935
935
|
"Extra parameters for the lr_scheduler such as {'num_cycles': 1} for the cosine with hard restarts."
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: transformers
|
|
3
|
-
Version: 4.57.
|
|
3
|
+
Version: 4.57.6
|
|
4
4
|
Summary: State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow
|
|
5
5
|
Home-page: https://github.com/huggingface/transformers
|
|
6
6
|
Author: The Hugging Face team (past and future) with the help of all our contributors (https://github.com/huggingface/transformers/graphs/contributors)
|
|
@@ -1,4 +1,4 @@
|
|
|
1
|
-
transformers/__init__.py,sha256=
|
|
1
|
+
transformers/__init__.py,sha256=qoy1TaSIz0O6N7mVW7bA2E0gANsDBval8cILaEJILQQ,47000
|
|
2
2
|
transformers/activations.py,sha256=PdWoGx5eDFNxJW8A7-wZ31IlVCAxhzfbHgNDCpjPQmQ,13109
|
|
3
3
|
transformers/activations_tf.py,sha256=TGmah3loMs_pERwxpjWb5-AUeHLoBAyDxFYWVuLC7FU,4729
|
|
4
4
|
transformers/audio_utils.py,sha256=wDhFAweo28mpXu2OQTdw80gU-jgFgSHKny7ujdDfqVg,54284
|
|
@@ -57,7 +57,7 @@ transformers/trainer_callback.py,sha256=YkfU5q-2K7G2RcmdaDLnajZOdSXiaCNKSsmJAot8
|
|
|
57
57
|
transformers/trainer_pt_utils.py,sha256=MfApM3Cv-9DaHDOmFCdX-BpNT7v5AZrriSlYUNLC54Q,61426
|
|
58
58
|
transformers/trainer_seq2seq.py,sha256=XnhGbtAwI0F4E9ynU5L80I4DP1DJeP8rOU1C6YzXE9E,18001
|
|
59
59
|
transformers/trainer_utils.py,sha256=IOMtBe8i82arnOkcbb7CKQsuRvjadJ1S7uuvakNJvY4,34254
|
|
60
|
-
transformers/training_args.py,sha256=
|
|
60
|
+
transformers/training_args.py,sha256=RExMVhe4ngWuSjHePE9_wfYxFJapv37zV6ppvjqir_8,162917
|
|
61
61
|
transformers/training_args_seq2seq.py,sha256=J9_vJQR4VxWAHWVbRmxjXHSRLd6KSe8inisIVezlbXI,3896
|
|
62
62
|
transformers/training_args_tf.py,sha256=4WYwTKApwnjndGhEDL_NNOtvQ6VIa5w_ZZEBzAAN4Qg,14604
|
|
63
63
|
transformers/video_processing_utils.py,sha256=Bn3JWf6ADVpaWrOcVLU4F6S1lCTzFDZ2fXNhwgs7pAk,41231
|
|
@@ -1608,7 +1608,7 @@ transformers/models/qwen2_5_omni/modeling_qwen2_5_omni.py,sha256=gwhVB40MCxWaRwQ
|
|
|
1608
1608
|
transformers/models/qwen2_5_omni/modular_qwen2_5_omni.py,sha256=jhG7Cdm3bRkHBOG2pz2gERVj_DN41MJ5z9ShOXEbf1s,191129
|
|
1609
1609
|
transformers/models/qwen2_5_omni/processing_qwen2_5_omni.py,sha256=CEBbeuYqjcQSqMl1cq2dFi0LldzJ1IlS25c3g_XilFg,17110
|
|
1610
1610
|
transformers/models/qwen2_5_vl/__init__.py,sha256=8-dsgLIeeE3n90n6F0XOu-tBZ-80Wotz89pjZi5GqjQ,1065
|
|
1611
|
-
transformers/models/qwen2_5_vl/configuration_qwen2_5_vl.py,sha256
|
|
1611
|
+
transformers/models/qwen2_5_vl/configuration_qwen2_5_vl.py,sha256=ckFVe5PFCn6BM5PpPvL0V3OvLq-sn1f1beCYaS6pFQA,18562
|
|
1612
1612
|
transformers/models/qwen2_5_vl/modeling_qwen2_5_vl.py,sha256=9QUVIzABRfZt4IB2XAa9gIA1DBVpLAltLDjnP-nQMJk,82355
|
|
1613
1613
|
transformers/models/qwen2_5_vl/modular_qwen2_5_vl.py,sha256=8T5rkMDA9BKurCAWBm5l57ktOWxBWYgM3QSRSWmkDog,49601
|
|
1614
1614
|
transformers/models/qwen2_5_vl/processing_qwen2_5_vl.py,sha256=aogQe4UyDKnuEVRzFTDbWEugSKEq_x66sve9x3BiGE0,14907
|
|
@@ -1620,7 +1620,7 @@ transformers/models/qwen2_moe/__init__.py,sha256=TZM20WtUr1UyV-hDDgq5B-qFT4aUulM
|
|
|
1620
1620
|
transformers/models/qwen2_moe/configuration_qwen2_moe.py,sha256=3BBfpz3Pu3DuaCuTtWaFdY_JK5QrLVWrW-Ri-Ky205I,13228
|
|
1621
1621
|
transformers/models/qwen2_moe/modeling_qwen2_moe.py,sha256=LGeqEeHF9qDHi0qCanRAqV5W1FbQgauvXvcqsvYetrg,54846
|
|
1622
1622
|
transformers/models/qwen2_vl/__init__.py,sha256=MtNDD6sEQws-WTLwPxUL5UNd-UyDPrDh8yWzIAsRp-U,1131
|
|
1623
|
-
transformers/models/qwen2_vl/configuration_qwen2_vl.py,sha256=
|
|
1623
|
+
transformers/models/qwen2_vl/configuration_qwen2_vl.py,sha256=BoXLC18Nb_w5zLRduzbGyfIaBZ3tqKRuNUUroeC4qrA,17192
|
|
1624
1624
|
transformers/models/qwen2_vl/image_processing_qwen2_vl.py,sha256=eCCg_MoQfnVgXgjZt3QoXKKwMW-Fe8AiXHeXlHBez08,26381
|
|
1625
1625
|
transformers/models/qwen2_vl/image_processing_qwen2_vl_fast.py,sha256=Cb-psX33w_DGFZvDQAjuUPIdJHLNW65-XCG6HKE6Qjw,12723
|
|
1626
1626
|
transformers/models/qwen2_vl/modeling_qwen2_vl.py,sha256=8y_bho4BRBTzvKL8yOcWX8nkm1fpRptPOvmiQ2QK4Ps,74168
|
|
@@ -2238,9 +2238,9 @@ transformers/utils/quantization_config.py,sha256=MK8CU9pBIqA8TXWMraDfrM3YndtyW39
|
|
|
2238
2238
|
transformers/utils/sentencepiece_model_pb2.py,sha256=WcMZRm2-571XwxSfo-6FZih9fDy_Zl5mMwqrDrC1Dlg,50663
|
|
2239
2239
|
transformers/utils/sentencepiece_model_pb2_new.py,sha256=ahaV--amhGIL3nXFCTHqezqxuGXm8SHr_C3Zvj7KbAY,6598
|
|
2240
2240
|
transformers/utils/versions.py,sha256=C-Tqr4qGSHH64ygIBCSo8gA6azz7Dbzh8zdc_yjMkX8,4337
|
|
2241
|
-
transformers-4.57.
|
|
2242
|
-
transformers-4.57.
|
|
2243
|
-
transformers-4.57.
|
|
2244
|
-
transformers-4.57.
|
|
2245
|
-
transformers-4.57.
|
|
2246
|
-
transformers-4.57.
|
|
2241
|
+
transformers-4.57.6.dist-info/licenses/LICENSE,sha256=d_1HEN757DwPYiWADgI18VpCWr1KiwNVkSf814JhIEk,11418
|
|
2242
|
+
transformers-4.57.6.dist-info/METADATA,sha256=kWAQRKdP4CVxqCU1Z1Tbuqnh0-PdPCI3JUwV6QPkIeM,43991
|
|
2243
|
+
transformers-4.57.6.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
|
|
2244
|
+
transformers-4.57.6.dist-info/entry_points.txt,sha256=Zra3dVQyt6Q3fU_suoD3gF81JV3WeV8gH66vzoev408,144
|
|
2245
|
+
transformers-4.57.6.dist-info/top_level.txt,sha256=GLBaeTo_CSdhnHvbxQ0kzpEHdlLuA_33foIogaWxntI,13
|
|
2246
|
+
transformers-4.57.6.dist-info/RECORD,,
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|