File size: 31,469 Bytes
f9c5128
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
# coding=utf-8
# Copyright 2024 The Qwen team, Alibaba Group and the HuggingFace Inc. team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""RWKV079Qwen3 model configuration"""

#Never gonna give you up
from typing import Optional
from transformers.configuration_utils import PretrainedConfig#, layer_type_validation
from transformers.modeling_rope_utils import rope_config_validation
from transformers.utils import logging


logger = logging.get_logger(__name__)


# class RWKV07BMoEConfig(PretrainedConfig):
#     r"""
#     This is the configuration class to store the configuration of a [`RWKV07BMoEModel`]. It is used to instantiate a
#     RWKV079Qwen3 model according to the specified arguments, defining the model architecture. Instantiating a configuration
#     with the defaults will yield a similar configuration to that of
#     Qwen3-7B-beta [Qwen/Qwen3-7B-beta](https://huggingface.co/Qwen/Qwen3-7B-beta).

#     Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
#     documentation from [`PretrainedConfig`] for more information.


#     Args:
#         vocab_size (`int`, *optional*, defaults to 151936):
#             Vocabulary size of the RWKV079Qwen3 model. Defines the number of different tokens that can be represented by the
#             `inputs_ids` passed when calling [`RWKV07BMoEModel`]
#         hidden_size (`int`, *optional*, defaults to 4096):
#             Dimension of the hidden representations.
#         intermediate_size (`int`, *optional*, defaults to 22016):
#             Dimension of the MLP representations.
#         num_hidden_layers (`int`, *optional*, defaults to 32):
#             Number of hidden layers in the Transformer encoder.
#         num_attention_heads (`int`, *optional*, defaults to 32):
#             Number of attention heads for each attention layer in the Transformer encoder.
#         num_key_value_heads (`int`, *optional*, defaults to 32):
#             This is the number of key_value heads that should be used to implement Grouped Query Attention. If
#             `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
#             `num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When
#             converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
#             by meanpooling all the original heads within that group. For more details checkout [this
#             paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to `32`.
#         lora_rank_decay (`int`, *optional*):
#             The rank of the lora used to generate decay.
#         lora_rank_iclr (`int`, *optional*):
#             The rank of the lora used to generate the in-context learning rate.
#         lora_rank_value_residual_mix (`int`, *optional*):
#             The rank of the lora used to generate the value residual mix amount.
#         lora_rank_value_gate (`int`, *optional*):
#             The rank of the lora used to generate the gate.
#         hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
#             The non-linear activation function (function or string) in the decoder.
#         max_position_embeddings (`int`, *optional*, defaults to 32768):
#             The maximum sequence length that this model might ever be used with.
#         initializer_range (`float`, *optional*, defaults to 0.02):
#             The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
#         rms_norm_eps (`float`, *optional*, defaults to 1e-06):
#             The epsilon used by the rms normalization layers.
#         use_cache (`bool`, *optional*, defaults to `True`):
#             Whether or not the model should return the last key/values attentions (not used by all models). Only
#             relevant if `config.is_decoder=True`.
#         tie_word_embeddings (`bool`, *optional*, defaults to `False`):
#             Whether the model's input and output word embeddings should be tied.
#         rope_theta (`float`, *optional*, defaults to 10000.0):
#             The base period of the RoPE embeddings.
#         rope_scaling (`Dict`, *optional*):
#             Dictionary containing the scaling configuration for the RoPE embeddings. NOTE: if you apply new rope type
#             and you expect the model to work on longer `max_position_embeddings`, we recommend you to update this value
#             accordingly.
#             Expected contents:
#                 `rope_type` (`str`):
#                     The sub-variant of RoPE to use. Can be one of ['default', 'linear', 'dynamic', 'yarn', 'longrope',
#                     'llama3'], with 'default' being the original RoPE implementation.
#                 `factor` (`float`, *optional*):
#                     Used with all rope types except 'default'. The scaling factor to apply to the RoPE embeddings. In
#                     most scaling types, a `factor` of x will enable the model to handle sequences of length x *
#                     original maximum pre-trained length.
#                 `original_max_position_embeddings` (`int`, *optional*):
#                     Used with 'dynamic', 'longrope' and 'llama3'. The original max position embeddings used during
#                     pretraining.
#                 `attention_factor` (`float`, *optional*):
#                     Used with 'yarn' and 'longrope'. The scaling factor to be applied on the attention
#                     computation. If unspecified, it defaults to value recommended by the implementation, using the
#                     `factor` field to infer the suggested value.
#                 `beta_fast` (`float`, *optional*):
#                     Only used with 'yarn'. Parameter to set the boundary for extrapolation (only) in the linear
#                     ramp function. If unspecified, it defaults to 32.
#                 `beta_slow` (`float`, *optional*):
#                     Only used with 'yarn'. Parameter to set the boundary for interpolation (only) in the linear
#                     ramp function. If unspecified, it defaults to 1.
#                 `short_factor` (`List[float]`, *optional*):
#                     Only used with 'longrope'. The scaling factor to be applied to short contexts (<
#                     `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
#                     size divided by the number of attention heads divided by 2
#                 `long_factor` (`List[float]`, *optional*):
#                     Only used with 'longrope'. The scaling factor to be applied to long contexts (<
#                     `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
#                     size divided by the number of attention heads divided by 2
#                 `low_freq_factor` (`float`, *optional*):
#                     Only used with 'llama3'. Scaling factor applied to low frequency components of the RoPE
#                 `high_freq_factor` (`float`, *optional*):
#                     Only used with 'llama3'. Scaling factor applied to high frequency components of the RoPE
#         use_sliding_window (`bool`, *optional*, defaults to `False`):
#             Whether to use sliding window attention.
#         sliding_window (`int`, *optional*, defaults to 4096):
#             Sliding window attention (SWA) window size. If not specified, will default to `4096`.
#         max_window_layers (`int`, *optional*, defaults to 28):
#             The number of layers that use SWA (Sliding Window Attention). The bottom layers use SWA while the top use full attention.
#         attention_dropout (`float`, *optional*, defaults to 0.0):
#             The dropout ratio for the attention probabilities.

#     ```python
#     >>> from transformers import RWKV07BMoEModel, RWKV079Qwen3Config

#     >>> # Initializing a RWKV079Qwen3 style configuration
#     >>> configuration = RWKV079Qwen3Config()

#     >>> # Initializing a model from the RWKV079Qwen3-7B style configuration
#     >>> model = RWKV07BMoEModel(configuration)

#     >>> # Accessing the model configuration
#     >>> configuration = model.config
#     ```"""

#     model_type = "rwkv07b_moe"
#     keys_to_ignore_at_inference = ["past_key_values"]

#     # Default tensor parallel plan for base model `Qwen3Moe`
#     base_model_tp_plan = {
#         #NoPE-GQA
#         "layers.*.self_attn.q_proj": "colwise",
#         "layers.*.self_attn.k_proj": "colwise",
#         "layers.*.self_attn.v_proj": "colwise",
#         "layers.*.self_attn.o_proj": "rowwise",
#         #RoPE-RWKV
#         "layers.*.self_attn.receptance": "colwise",
#         "layers.*.self_attn.key": "colwise",
#         "layers.*.self_attn.value": "colwise",
#         "layers.*.self_attn.output": "rowwise",
#         "layers.*.mlp.experts.*.gate_proj": "colwise",
#         "layers.*.mlp.experts.*.up_proj": "colwise",
#         "layers.*.mlp.experts.*.down_proj": "rowwise",
#         "layers.*.mlp.gate_proj": "colwise",
#         "layers.*.mlp.up_proj": "colwise",
#         "layers.*.mlp.down_proj": "rowwise",
#     }
#     base_model_pp_plan = {
#         "embed_tokens": (["input_ids"], ["inputs_embeds"]),
#         "layers": (["hidden_states", "attention_mask"], ["hidden_states"]),
#         "norm": (["hidden_states"], ["hidden_states"]),
#     }

#     def __init__(
#         self,
#         vocab_size=151936,
#         hidden_size=4096,
#         intermediate_size=22016,
#         num_hidden_layers=32,
#         num_attention_heads=32,
#         num_key_value_heads=32,
#         lora_rank_tokenshift=None,
#         lora_rank_decay=None,
#         lora_rank_iclr=None,
#         lora_rank_value_residual_mix=None,
#         lora_rank_value_key_mix=None,
#         lora_rank_gate=None,
#         hidden_act="silu",
#         max_position_embeddings=32768,
#         initializer_range=0.02,
#         rms_norm_eps=1e-6,
#         use_cache=True,
#         tie_word_embeddings=False,
#         use_rope=True,
#         rope_theta=10000.0,
#         rope_scaling=None,
#         use_sliding_window=False,
#         sliding_window=4096,
#         max_window_layers=28,
#         first_attention_layer=9999,
#         first_post_attention_layer=9999,
#         attention_striping=1,
#         last_striping_layer=99999,
#         layer_types=None,
#         attention_dropout=0.0,
#         attention_bias=True,
#         attention_output_bias=False,
#         gate_rank_type=2,
#         balance_state=True,
#         groupnorm_att=False,
#         use_tokenshift=False,

#         decoder_sparse_step=1,
#         moe_intermediate_size=768,
#         num_experts_per_tok=8,
#         num_experts=128,
#         norm_topk_prob=False,
#         output_router_logits=False,
#         router_aux_loss_coef=0.001,
#         mlp_only_layers=None,
#         **kwargs,
#     ):
#         self.vocab_size = vocab_size
#         self.max_position_embeddings = max_position_embeddings
#         self.hidden_size = hidden_size
#         self.intermediate_size = intermediate_size
#         self.num_hidden_layers = num_hidden_layers
#         self.num_attention_heads = num_attention_heads
#         self.use_sliding_window = use_sliding_window
#         self.sliding_window = sliding_window if use_sliding_window else None
#         self.max_window_layers = max_window_layers
#         self.first_attention_layer = first_attention_layer
#         self.first_post_attention_layer = first_post_attention_layer
#         self.attention_striping = attention_striping
#         self.last_striping_layer = last_striping_layer

#         # for backward compatibility
#         if num_key_value_heads is None:
#             num_key_value_heads = num_attention_heads

#         self.num_key_value_heads = num_key_value_heads
#         self.lora_rank_tokenshift = lora_rank_tokenshift
#         self.lora_rank_decay = lora_rank_decay
#         self.lora_rank_iclr = lora_rank_iclr
#         self.lora_rank_value_residual_mix = lora_rank_value_residual_mix
#         self.lora_rank_gate = lora_rank_gate
#         self.hidden_act = hidden_act
#         self.initializer_range = initializer_range
#         self.rms_norm_eps = rms_norm_eps
#         self.use_cache = use_cache
#         self.use_rope = use_rope
#         self.rope_theta = rope_theta
#         self.rope_scaling = rope_scaling
#         self.attention_dropout = attention_dropout
#         # Validate the correctness of rotary position embeddings parameters
#         # BC: if there is a 'type' field, move it to 'rope_type'.
#         if self.rope_scaling is not None and "type" in self.rope_scaling:
#             self.rope_scaling["rope_type"] = self.rope_scaling["type"]
#         self.rope_parameters = rope_scaling
#         #rope_config_validation(self)

#         self.layer_types = layer_types
#         if self.layer_types is None:
#             self.layer_types = [
#                 "sliding_attention"
#                 if self.sliding_window is not None and i >= self.max_window_layers
#                 else "full_attention"
#                 for i in range(self.num_hidden_layers)
#             ]
#        #layer_type_validation(self.layer_types)

#         self.attention_bias = attention_bias
#         self.attention_output_bias = attention_output_bias
#         self.gate_rank_type = gate_rank_type
#         self.balance_state = balance_state
#         self.groupnorm_att = groupnorm_att
#         self.use_tokenshift = use_tokenshift

#         # MoE arguments
#         self.decoder_sparse_step = decoder_sparse_step
#         self.moe_intermediate_size = moe_intermediate_size
#         self.num_experts_per_tok = num_experts_per_tok
#         self.num_experts = num_experts
#         self.norm_topk_prob = norm_topk_prob
#         self.output_router_logits = output_router_logits
#         self.router_aux_loss_coef = router_aux_loss_coef
#         self.mlp_only_layers = [] if mlp_only_layers is None else mlp_only_layers

#         super().__init__(
#             tie_word_embeddings=tie_word_embeddings,
#             **kwargs,
#         )
from typing import Optional, TypedDict
class RopeParameters(TypedDict):
    """
    Args:
        rope_theta (`float`):
            The base period of the RoPE embeddings.
        rope_type (`str`, *optional*, defaults to "default"):
            The sub-variant of RoPE to use. Can be one of ['default', 'linear', 'dynamic', 'yarn', 'longrope',
            'llama3'], with 'default' being the original RoPE implementation.
        factor (`float`, *optional*):
            Used with all rope types except 'default'. The scaling factor to apply to the RoPE embeddings. In
            most scaling types, a `factor` of x will enable the model to handle sequences of length x *
            original maximum pre-trained length.
        original_max_position_embeddings (`int`, *optional*):
            Used with 'dynamic', 'longrope' and 'llama3'. The original max position embeddings used during
            pretraining.
        attention_factor (`float`, *optional*):
            Used with 'yarn' and 'longrope'. The scaling factor to be applied on the attention
            computation. If unspecified, it defaults to value recommended by the implementation, using the
            `factor` field to infer the suggested value.
        beta_fast (`float`, *optional*):
            Only used with 'yarn'. Parameter to set the boundary for extrapolation (only) in the linear
            ramp function. If unspecified, it defaults to 32.
        beta_slow (`float`, *optional*):
            Only used with 'yarn'. Parameter to set the boundary for interpolation (only) in the linear
            ramp function. If unspecified, it defaults to 1.
        short_factor (`list[float]`, *optional*):
            Only used with 'longrope'. The scaling factor to be applied to short contexts (<
            `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
            size divided by the number of attention heads divided by 2
        long_factor (`list[float]`, *optional*):
            Only used with 'longrope'. The scaling factor to be applied to long contexts (<
            `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
            size divided by the number of attention heads divided by 2
        low_freq_factor (`float`, *optional*):
            Only used with 'llama3'. Scaling factor applied to low frequency components of the RoPE
        high_freq_factor (`float`, *optional*):
            Only used with 'llama3'. Scaling factor applied to high frequency components of the RoPE
    """

    rope_theta: float
    rope_type: Optional[str]
    factor: Optional[float]
    original_max_position_embeddings: Optional[int]
    attention_factor: Optional[float]
    beta_fast: Optional[float]
    beta_slow: Optional[float]
    short_factor: Optional[list[float]]
    long_factor: Optional[list[float]]
    low_freq_factor: Optional[float]
    high_freq_factor: Optional[float]

class Qwen3VLMoeTextConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`Qwen3VLMoeTextModel`]. It is used to instantiate a
    Qwen3-VL-MOE model according to the specified arguments, defining the model architecture. Instantiating a configuration
    with the defaults will yield a similar configuration to that of
    Qwen3-VL-30B-A3B-Instruct [Qwen/Qwen3-VL-30B-A3B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-30B-A3B-Instruct).

    Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the
    documentation from [`PreTrainedConfig`] for more information.

    Args:
        vocab_size (`int`, *optional*, defaults to 151936):
            Vocabulary size of the Qwen2MoE model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`Qwen2MoeModel`]
        hidden_size (`int`, *optional*, defaults to 2048):
            Dimension of the hidden representations.
        intermediate_size (`int`, *optional*, defaults to 5632):
            Dimension of the MLP representations.
        num_hidden_layers (`int`, *optional*, defaults to 24):
            Number of hidden layers in the Transformer encoder.
        num_attention_heads (`int`, *optional*, defaults to 16):
            Number of attention heads for each attention layer in the Transformer encoder.
        num_key_value_heads (`int`, *optional*, defaults to 16):
            This is the number of key_value heads that should be used to implement Grouped Query Attention. If
            `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
            `num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When
            converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
            by meanpooling all the original heads within that group. For more details checkout [this
            paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to `32`.
        hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
            The non-linear activation function (function or string) in the decoder.
        max_position_embeddings (`int`, *optional*, defaults to 128000):
            The maximum sequence length that this model might ever be used with.
        initializer_range (`float`, *optional*, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        rms_norm_eps (`float`, *optional*, defaults to 1e-06):
            The epsilon used by the rms normalization layers.
        use_cache (`bool`, *optional*, defaults to `True`):
            Whether or not the model should return the last key/values attentions (not used by all models). Only
            relevant if `config.is_decoder=True`.
        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
            Whether the model's input and output word embeddings should be tied.
        attention_bias (`bool`, defaults to `False`, *optional*, defaults to `False`):
            Whether to use a bias in the query, key, value and output projection layers during self-attention.
        attention_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio for the attention probabilities.
        decoder_sparse_step (`int`, *optional*, defaults to 1):
            The frequency of the MoE layer.
        moe_intermediate_size (`int`, *optional*, defaults to 1408):
            Intermediate size of the routed expert.
        num_experts_per_tok (`int`, *optional*, defaults to 4):
            Number of selected experts.
        num_experts (`int`, *optional*, defaults to 60):
            Number of routed experts.
        mlp_only_layers (`List[int]`, *optional*, defaults to `[]`):
            Indicate which layers use Qwen3VLMoeMLP rather than Qwen3VLMoeSparseMoeBlock
            The list contains layer index, from 0 to num_layers-1 if we have num_layers layers
            If `mlp_only_layers` is empty, `decoder_sparse_step` is used to determine the sparsity.
        rope_parameters (`RopeParameters`, *optional*):
            Dictionary containing the configuration parameters for the RoPE embeddings. The dictionaty should contain
            a value for `rope_theta` and optionally parameters used for scaling in case you want to use RoPE
            with longer `max_position_embeddings`.
        head_dim (`int`, *optional*):
            The dimension of the head. If not specified, will default to `hidden_size // num_attention_heads`.

    ```python
    >>> from transformers import Qwen3VLMoeForConditionalGeneration, Qwen3VLMoeConfig

    >>> # Initializing a Qwen3VLMoe style configuration
    >>> configuration = Qwen3VLMoeConfig()

    >>> # Initializing a model from the Qwen3-VL-30B-A3B style configuration
    >>> model = Qwen3VLMoeForConditionalGeneration(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```"""

    model_type = "qwen3_vl_moe_text"
    base_config_key = "text_config"
    keys_to_ignore_at_inference = ["past_key_values"]
    # Default tensor parallel plan for base model `Qwen3VLMoe`
    base_model_tp_plan = {
        "layers.*.self_attn.q_proj": "colwise",
        "layers.*.self_attn.k_proj": "colwise",
        "layers.*.self_attn.v_proj": "colwise",
        "layers.*.self_attn.o_proj": "rowwise",
        "layers.*.mlp.gate_proj": "colwise",
        "layers.*.mlp.up_proj": "colwise",
        "layers.*.mlp.down_proj": "rowwise",
    }
    base_model_pp_plan = {
        "embed_tokens": (["input_ids"], ["inputs_embeds"]),
        "layers": (["hidden_states", "attention_mask"], ["hidden_states"]),
        "norm": (["hidden_states"], ["hidden_states"]),
    }

    def __init__(
        self,
        vocab_size: Optional[int] = 151936,
        hidden_size: Optional[int] = 2048,
        intermediate_size: Optional[int] = 5632,
        num_hidden_layers: Optional[int] = 24,
        num_attention_heads: Optional[int] = 16,
        num_key_value_heads: Optional[int] = 16,
        hidden_act: Optional[str] = "silu",
        max_position_embeddings: Optional[int] = 128000,
        initializer_range: Optional[float] = 0.02,
        rms_norm_eps: Optional[float] = 1e-6,
        use_cache: Optional[bool] = True,
        tie_word_embeddings: Optional[bool] = False,
        attention_bias: Optional[bool] = False,
        attention_dropout: Optional[float] = 0.0,
        decoder_sparse_step: Optional[int] = 1,
        moe_intermediate_size: Optional[int] = 1408,
        num_experts_per_tok: Optional[int] = 4,
        num_experts: Optional[int] = 60,
        mlp_only_layers: Optional[list[int]] = None,
        rope_parameters: Optional[RopeParameters] = None,
        head_dim: Optional[int] = None,
        **kwargs,
    ):
        self.vocab_size = vocab_size
        self.max_position_embeddings = max_position_embeddings
        self.hidden_size = hidden_size
        self.intermediate_size = intermediate_size
        self.num_hidden_layers = num_hidden_layers
        self.num_attention_heads = num_attention_heads

        self.layer_types = None

        # for backward compatibility
        if num_key_value_heads is None:
            num_key_value_heads = num_attention_heads

        self.num_key_value_heads = num_key_value_heads
        self.hidden_act = hidden_act
        self.initializer_range = initializer_range
        self.rms_norm_eps = rms_norm_eps
        self.use_cache = use_cache
        self.attention_bias = attention_bias
        self.attention_dropout = attention_dropout
        self.head_dim = head_dim or hidden_size // num_attention_heads
        # Try to set `rope_scaling` if available, otherwise use `rope_parameters`
        rope_scaling = kwargs.pop("rope_scaling", None)
        self.rope_parameters = rope_scaling or rope_parameters

        self.sliding_window = None
        self.max_window_layers = 0

        if self.layer_types is None:
            self.layer_types = [
                "sliding_attention"
                if self.sliding_window is not None and i >= self.max_window_layers
                else "full_attention"
                for i in range(self.num_hidden_layers)
            ]

        # Validate the correctness of rotary position embeddings parameters
        rope_theta = kwargs.get("rope_theta", 5000000.0)
       # standardize_rope_params(self, rope_theta=rope_theta)
        rope_config_validation(self, ignore_keys={"mrope_section", "mrope_interleaved"})

        # MoE arguments
        self.decoder_sparse_step = decoder_sparse_step
        self.moe_intermediate_size = moe_intermediate_size
        self.num_experts_per_tok = num_experts_per_tok
        self.num_experts = num_experts
        self.mlp_only_layers = [] if mlp_only_layers is None else mlp_only_layers

        super().__init__(tie_word_embeddings=tie_word_embeddings, **kwargs)


class Qwen3VLMoeVisionConfig(PretrainedConfig):
    model_type = "qwen3_vl_moe"
    base_config_key = "vision_config"

    def __init__(
        self,
        depth=27,
        hidden_size=1152,
        hidden_act="gelu_pytorch_tanh",
        intermediate_size=4304,
        num_heads=16,
        in_channels=3,
        patch_size=16,
        spatial_merge_size=2,
        temporal_patch_size=2,
        out_hidden_size=3584,
        num_position_embeddings=2304,
        deepstack_visual_indexes=[8, 16, 24],
        initializer_range=0.02,
        **kwargs,
    ):
        super().__init__(**kwargs)

        self.depth = depth
        self.hidden_size = hidden_size
        self.hidden_act = hidden_act
        self.intermediate_size = intermediate_size
        self.num_heads = num_heads
        self.in_channels = in_channels
        self.patch_size = patch_size
        self.spatial_merge_size = spatial_merge_size
        self.temporal_patch_size = temporal_patch_size
        self.out_hidden_size = out_hidden_size
        self.num_position_embeddings = num_position_embeddings
        self.initializer_range = initializer_range
        self.deepstack_visual_indexes = deepstack_visual_indexes


class RWKV07BMoEConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`Qwen3VLMoeModel`]. It is used to instantiate a
    Qwen3-VL-MOE model according to the specified arguments, defining the model architecture. Instantiating a configuration
    with the defaults will yield a similar configuration to that of
    Qwen3-VL-30B-A3B-Instruct [Qwen/Qwen3-VL-30B-A3B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-30B-A3B-Instruct).

    Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the
    documentation from [`PreTrainedConfig`] for more information.


    Args:
        text_config (`Union[PreTrainedConfig, dict]`, *optional*, defaults to `Qwen3VLMoeTextConfig`):
            The config object or dictionary of the text backbone.
        vision_config (`Union[PreTrainedConfig, dict]`,  *optional*, defaults to `Qwen3VLMoeVisionConfig`):
            The config object or dictionary of the vision backbone.
        image_token_id (`int`, *optional*, defaults to 151655):
            The image token index to encode the image prompt.
        video_token_id (`int`, *optional*, defaults to 151656):
            The video token index to encode the image prompt.
        vision_start_token_id (`int`, *optional*, defaults to 151652):
            The start token index to encode the image prompt.
        vision_end_token_id (`int`, *optional*, defaults to 151653):
            The end token index to encode the image prompt.
        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
            Whether to tie the word embeddings.

    ```python
    >>> from transformers import Qwen3VLMoeForConditionalGeneration, Qwen3VLMoeConfig

    >>> # Initializing a Qwen3-VL-MOE style configuration
    >>> configuration = Qwen3VLMoeConfig()

    >>> # Initializing a model from the Qwen3-VL-30B-A3B style configuration
    >>> model = Qwen3VLMoeForConditionalGeneration(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```"""

    model_type = "rwkv07b_moe"
    sub_configs = {"vision_config": Qwen3VLMoeVisionConfig, "text_config": Qwen3VLMoeTextConfig}
    keys_to_ignore_at_inference = ["past_key_values"]

    def __init__(
        self,
        text_config=None,
        vision_config=None,
        image_token_id=151655,
        video_token_id=151656,
        vision_start_token_id=151652,
        vision_end_token_id=151653,
        tie_word_embeddings=False,
        **kwargs,
    ):
        if isinstance(vision_config, dict):
            self.vision_config = self.sub_configs["vision_config"](**vision_config)
        elif vision_config is None:
            self.vision_config = self.sub_configs["vision_config"]()

        if isinstance(text_config, dict):
            self.text_config = self.sub_configs["text_config"](**text_config)
        elif text_config is None:
            self.text_config = self.sub_configs["text_config"]()

        self.image_token_id = image_token_id
        self.video_token_id = video_token_id
        self.vision_start_token_id = vision_start_token_id
        self.vision_end_token_id = vision_end_token_id
        super().__init__(**kwargs, tie_word_embeddings=tie_word_embeddings)


__all__ = ["Qwen3VLMoeConfig", "Qwen3VLMoeTextConfig"]