Skip to content

git

mindnlp.transformers.models.git.configuration_git

MindSpore GIT configuration.

mindnlp.transformers.models.git.configuration_git.GitConfig

Bases: PretrainedConfig

This is the configuration class to store the configuration of a [GitModel]. It is used to instantiate a GIT model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the GIT microsoft/git-base architecture.

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

PARAMETER DESCRIPTION
vision_config

Dictionary of configuration options used to initialize [GitVisionConfig].

TYPE: `dict`, *optional* DEFAULT: None

vocab_size

Vocabulary size of the GIT model. Defines the number of different tokens that can be represented by the inputs_ids passed when calling [GitModel].

TYPE: `int`, *optional*, defaults to 30522 DEFAULT: 30522

hidden_size

Dimensionality of the encoder layers and the pooler layer.

TYPE: `int`, *optional*, defaults to 768 DEFAULT: 768

num_hidden_layers

Number of hidden layers in the Transformer encoder.

TYPE: `int`, *optional*, defaults to 6 DEFAULT: 6

num_attention_heads

Number of attention heads for each attention layer in the Transformer encoder.

TYPE: `int`, *optional*, defaults to 12 DEFAULT: 12

intermediate_size

Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder.

TYPE: `int`, *optional*, defaults to 3072 DEFAULT: 3072

hidden_act

The non-linear activation function (function or string) in the encoder and pooler. If string, "gelu", "relu", "silu" and "gelu_new" are supported.

TYPE: `str` or `Callable`, *optional*, defaults to `"gelu"` DEFAULT: 'gelu'

hidden_dropout_prob

The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.

TYPE: `float`, *optional*, defaults to 0.1 DEFAULT: 0.1

attention_probs_dropout_prob

The dropout ratio for the attention probabilities.

TYPE: `float`, *optional*, defaults to 0.1 DEFAULT: 0.1

max_position_embeddings

The maximum sequence length that this model might ever be used with. Typically set this to something large just in case (e.g., 512 or 1024 or 2048).

TYPE: `int`, *optional*, defaults to 1024 DEFAULT: 1024

initializer_range

The standard deviation of the truncated_normal_initializer for initializing all weight matrices.

TYPE: `float`, *optional*, defaults to 0.02 DEFAULT: 0.02

layer_norm_eps

The epsilon used by the layer normalization layers.

TYPE: `float`, *optional*, defaults to 1e-12 DEFAULT: 1e-12

position_embedding_type

Type of position embedding. Choose one of "absolute", "relative_key", "relative_key_query". For positional embeddings use "absolute". For more information on "relative_key", please refer to Self-Attention with Relative Position Representations (Shaw et al.). For more information on "relative_key_query", please refer to Method 4 in Improve Transformer Models with Better Relative Position Embeddings (Huang et al.).

TYPE: `str`, *optional*, defaults to `"absolute"` DEFAULT: 'absolute'

use_cache

Whether or not the model should return the last key/values attentions (not used by all models).

TYPE: `bool`, *optional*, defaults to `True` DEFAULT: True

num_image_with_embedding

The number of temporal embeddings to add, in case the model is used for video captioning/VQA.

TYPE: `int`, *optional* DEFAULT: None

Example 
>>> from transformers import GitConfig, GitModel
...
>>> # Initializing a GIT microsoft/git-base style configuration
>>> configuration = GitConfig()
...
>>> # Initializing a model (with random weights) from the microsoft/git-base style configuration
>>> model = GitModel(configuration)
...
>>> # Accessing the model configuration
>>> configuration = model.config
Source code in mindnlp/transformers/models/git/configuration_git.py 
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
class GitConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`GitModel`]. It is used to instantiate a GIT model
    according to the specified arguments, defining the model architecture. Instantiating a configuration with the
    defaults will yield a similar configuration to that of the GIT
    [microsoft/git-base](https://huggingface.co/microsoft/git-base) architecture.

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

    Args:
        vision_config (`dict`, *optional*):
            Dictionary of configuration options used to initialize [`GitVisionConfig`].
        vocab_size (`int`, *optional*, defaults to 30522):
            Vocabulary size of the GIT model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`GitModel`].
        hidden_size (`int`, *optional*, defaults to 768):
            Dimensionality of the encoder layers and the pooler layer.
        num_hidden_layers (`int`, *optional*, defaults to 6):
            Number of hidden layers in the Transformer encoder.
        num_attention_heads (`int`, *optional*, defaults to 12):
            Number of attention heads for each attention layer in the Transformer encoder.
        intermediate_size (`int`, *optional*, defaults to 3072):
            Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder.
        hidden_act (`str` or `Callable`, *optional*, defaults to `"gelu"`):
            The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
            `"relu"`, `"silu"` and `"gelu_new"` are supported.
        hidden_dropout_prob (`float`, *optional*, defaults to 0.1):
            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
        attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1):
            The dropout ratio for the attention probabilities.
        max_position_embeddings (`int`, *optional*, defaults to 1024):
            The maximum sequence length that this model might ever be used with. Typically set this to something large
            just in case (e.g., 512 or 1024 or 2048).
        initializer_range (`float`, *optional*, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        layer_norm_eps (`float`, *optional*, defaults to 1e-12):
            The epsilon used by the layer normalization layers.
        position_embedding_type (`str`, *optional*, defaults to `"absolute"`):
            Type of position embedding. Choose one of `"absolute"`, `"relative_key"`, `"relative_key_query"`. For
            positional embeddings use `"absolute"`. For more information on `"relative_key"`, please refer to
            [Self-Attention with Relative Position Representations (Shaw et al.)](https://arxiv.org/abs/1803.02155).
            For more information on `"relative_key_query"`, please refer to *Method 4* in [Improve Transformer Models
            with Better Relative Position Embeddings (Huang et al.)](https://arxiv.org/abs/2009.13658).
        use_cache (`bool`, *optional*, defaults to `True`):
            Whether or not the model should return the last key/values attentions (not used by all models).
        num_image_with_embedding (`int`, *optional*):
            The number of temporal embeddings to add, in case the model is used for video captioning/VQA.

    Example:
        ```python
        >>> from transformers import GitConfig, GitModel
        ...
        >>> # Initializing a GIT microsoft/git-base style configuration
        >>> configuration = GitConfig()
        ...
        >>> # Initializing a model (with random weights) from the microsoft/git-base style configuration
        >>> model = GitModel(configuration)
        ...
        >>> # Accessing the model configuration
        >>> configuration = model.config
        ```
    """

    model_type = "git"

    def __init__(
        self,
        vision_config=None,
        vocab_size=30522,
        hidden_size=768,
        num_hidden_layers=6,
        num_attention_heads=12,
        intermediate_size=3072,
        hidden_act="gelu",
        hidden_dropout_prob=0.1,
        attention_probs_dropout_prob=0.1,
        max_position_embeddings=1024,
        initializer_range=0.02,
        layer_norm_eps=1e-12,
        pad_token_id=0,
        position_embedding_type="absolute",
        use_cache=True,
        tie_word_embeddings=False,
        bos_token_id=101,
        eos_token_id=102,
        num_image_with_embedding=None,
        **kwargs,
    ):
        super().__init__(bos_token_id=bos_token_id, eos_token_id=eos_token_id, pad_token_id=pad_token_id, **kwargs)

        if vision_config is None:
            vision_config = {}
            logger.info("vision_config is None. initializing the GitVisionConfig with default values.")

        self.vision_config = GitVisionConfig(**vision_config)
        self.vocab_size = vocab_size
        self.hidden_size = hidden_size
        self.num_hidden_layers = num_hidden_layers
        self.num_attention_heads = num_attention_heads
        self.hidden_act = hidden_act
        self.intermediate_size = intermediate_size
        self.hidden_dropout_prob = hidden_dropout_prob
        self.attention_probs_dropout_prob = attention_probs_dropout_prob
        self.max_position_embeddings = max_position_embeddings
        self.initializer_range = initializer_range
        self.layer_norm_eps = layer_norm_eps
        self.position_embedding_type = position_embedding_type
        self.use_cache = use_cache
        self.tie_word_embeddings = tie_word_embeddings
        self.num_image_with_embedding = num_image_with_embedding

        self.bos_token_id = bos_token_id
        self.eos_token_id = eos_token_id

mindnlp.transformers.models.git.configuration_git.GitVisionConfig

Bases: PretrainedConfig

This is the configuration class to store the configuration of a [GitVisionModel]. It is used to instantiate a GIT vision encoder according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the vision encoder of the GIT microsoft/git-base architecture.

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

PARAMETER DESCRIPTION
hidden_size

Dimensionality of the encoder layers and the pooler layer.

TYPE: `int`, *optional*, defaults to 768 DEFAULT: 768

intermediate_size

Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.

TYPE: `int`, *optional*, defaults to 3072 DEFAULT: 3072

num_hidden_layers

Number of hidden layers in the Transformer encoder.

TYPE: `int`, *optional*, defaults to 12 DEFAULT: 12

num_attention_heads

Number of attention heads for each attention layer in the Transformer encoder.

TYPE: `int`, *optional*, defaults to 12 DEFAULT: 12

image_size

The size (resolution) of each image.

TYPE: `int`, *optional*, defaults to 224 DEFAULT: 224

patch_size

The size (resolution) of each patch.

TYPE: `int`, *optional*, defaults to 16 DEFAULT: 16

hidden_act

The non-linear activation function (function or string) in the encoder and pooler. If string, "gelu", "relu", "selu" and "gelu_new" `"quick_gelu" are supported.

TYPE: `str` or `function`, *optional*, defaults to `"quick_gelu"` DEFAULT: 'quick_gelu'

layer_norm_eps

The epsilon used by the layer normalization layers.

TYPE: `float`, *optional*, defaults to 1e-5 DEFAULT: 1e-05

attention_dropout

The dropout ratio for the attention probabilities.

TYPE: `float`, *optional*, defaults to 0.0 DEFAULT: 0.0

initializer_range

The standard deviation of the truncated_normal_initializer for initializing all weight matrices.

TYPE: `float`, *optional*, defaults to 0.02 DEFAULT: 0.02

Example 
>>> from transformers import GitVisionConfig, GitVisionModel
...
>>> # Initializing a GitVisionConfig with microsoft/git-base style configuration
>>> configuration = GitVisionConfig()
...
>>> # Initializing a GitVisionModel (with random weights) from the microsoft/git-base style configuration
>>> model = GitVisionModel(configuration)
...
>>> # Accessing the model configuration
>>> configuration = model.config
Source code in mindnlp/transformers/models/git/configuration_git.py 
 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
class GitVisionConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`GitVisionModel`]. It is used to instantiate a GIT
    vision encoder according to the specified arguments, defining the model architecture. Instantiating a configuration
    with the defaults will yield a similar configuration to that of the vision encoder of the GIT
    [microsoft/git-base](https://huggingface.co/microsoft/git-base) architecture.

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

    Args:
        hidden_size (`int`, *optional*, defaults to 768):
            Dimensionality of the encoder layers and the pooler layer.
        intermediate_size (`int`, *optional*, defaults to 3072):
            Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
        num_hidden_layers (`int`, *optional*, defaults to 12):
            Number of hidden layers in the Transformer encoder.
        num_attention_heads (`int`, *optional*, defaults to 12):
            Number of attention heads for each attention layer in the Transformer encoder.
        image_size (`int`, *optional*, defaults to 224):
            The size (resolution) of each image.
        patch_size (`int`, *optional*, defaults to 16):
            The size (resolution) of each patch.
        hidden_act (`str` or `function`, *optional*, defaults to `"quick_gelu"`):
            The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
            `"relu"`, `"selu"` and `"gelu_new"` ``"quick_gelu"` are supported.
        layer_norm_eps (`float`, *optional*, defaults to 1e-5):
            The epsilon used by the layer normalization layers.
        attention_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio for the attention probabilities.
        initializer_range (`float`, *optional*, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.

    Example:
        ```python
        >>> from transformers import GitVisionConfig, GitVisionModel
        ...
        >>> # Initializing a GitVisionConfig with microsoft/git-base style configuration
        >>> configuration = GitVisionConfig()
        ...
        >>> # Initializing a GitVisionModel (with random weights) from the microsoft/git-base style configuration
        >>> model = GitVisionModel(configuration)
        ...
        >>> # Accessing the model configuration
        >>> configuration = model.config
        ```
    """

    model_type = "git_vision_model"

    def __init__(
        self,
        hidden_size=768,
        intermediate_size=3072,
        num_hidden_layers=12,
        num_attention_heads=12,
        num_channels=3,
        image_size=224,
        patch_size=16,
        hidden_act="quick_gelu",
        layer_norm_eps=1e-5,
        attention_dropout=0.0,
        initializer_range=0.02,
        **kwargs,
    ):
        super().__init__(**kwargs)

        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.num_channels = num_channels
        self.patch_size = patch_size
        self.image_size = image_size
        self.initializer_range = initializer_range
        self.attention_dropout = attention_dropout
        self.layer_norm_eps = layer_norm_eps
        self.hidden_act = hidden_act

    @classmethod
    def from_pretrained(cls, pretrained_model_name_or_path: Union[str, os.PathLike], **kwargs) -> "PretrainedConfig":
        # cls._set_token_in_kwargs(kwargs)

        config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs)

        # get the vision config dict if we are loading from GITConfig
        if config_dict.get("model_type") == "git":
            config_dict = config_dict["vision_config"]

        if "model_type" in config_dict and hasattr(cls, "model_type") and config_dict["model_type"] != cls.model_type:
            logger.warning(
                f"You are using a model of type {config_dict['model_type']} to instantiate a model of type "
                f"{cls.model_type}. This is not supported for all configurations of models and can yield errors."
            )

        return cls.from_dict(config_dict, **kwargs)

mindnlp.transformers.models.git.modeling_git

MindSpore GIT model.

mindnlp.transformers.models.git.modeling_git.GitEmbeddings

Bases: Module

Construct the embeddings from word and position embeddings.

Source code in mindnlp/transformers/models/git/modeling_git.py 
 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
class GitEmbeddings(nn.Module):
    """Construct the embeddings from word and position embeddings."""

    def __init__(self, config):
        super().__init__()
        self.word_embeddings = nn.Embedding(config.vocab_size, config.hidden_size, padding_idx=config.pad_token_id)
        self.position_embeddings = nn.Embedding(config.max_position_embeddings, config.hidden_size)

        # self.LayerNorm is not snake-cased to stick with TensorFlow model variable name and be able to load
        # any TensorFlow checkpoint file
        self.LayerNorm = nn.LayerNorm([config.hidden_size], eps=config.layer_norm_eps)
        self.dropout = nn.Dropout(p=config.hidden_dropout_prob)
        # position_ids (1, len position emb) is contiguous in memory and exported when serialized
        self.position_embedding_type = getattr(config, "position_embedding_type", "absolute")
        self.position_ids = ops.arange(config.max_position_embeddings).broadcast_to((1, -1))

    def forward(
        self,
        input_ids: Optional[mindspore.Tensor] = None,
        position_ids: Optional[mindspore.Tensor] = None,
        inputs_embeds: Optional[mindspore.Tensor] = None,
        past_key_values_length: int = 0,
    ) -> mindspore.Tensor:
        if input_ids is not None:
            input_shape = input_ids.shape
        else:
            input_shape = inputs_embeds.shape[:-1]

        seq_length = input_shape[1]

        if position_ids is None:
            position_ids = self.position_ids[:, past_key_values_length : seq_length + past_key_values_length]

        if inputs_embeds is None:
            embeddings = self.word_embeddings(input_ids)
        else:
            embeddings = inputs_embeds

        if self.position_embedding_type == "absolute":
            position_embeddings = self.position_embeddings(position_ids)
            embeddings += position_embeddings
        embeddings = self.LayerNorm(embeddings)
        embeddings = self.dropout(embeddings)
        return embeddings

mindnlp.transformers.models.git.modeling_git.GitForCausalLM

Bases: GitPreTrainedModel

Source code in mindnlp/transformers/models/git/modeling_git.py 
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
class GitForCausalLM(GitPreTrainedModel):
    _tied_weights_keys = ["output.weight"]

    def __init__(self, config):
        super().__init__(config)

        self.git = GitModel(config)
        self.output = nn.Linear(config.hidden_size, config.vocab_size)

        # Initialize weights and apply final processing
        self.post_init()

    def get_output_embeddings(self):
        return self.output

    def set_output_embeddings(self, new_embeddings):
        self.output = new_embeddings

    def forward(
        self,
        input_ids: Optional[mindspore.Tensor] = None,
        attention_mask: Optional[mindspore.Tensor] = None,
        position_ids: Optional[mindspore.Tensor] = None,
        pixel_values: Optional[mindspore.Tensor] = None,
        head_mask: Optional[mindspore.Tensor] = None,
        inputs_embeds: Optional[mindspore.Tensor] = None,
        labels: Optional[mindspore.Tensor] = None,
        past_key_values: Optional[List[mindspore.Tensor]] = None,
        use_cache: Optional[bool] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
    ) -> Union[Tuple[mindspore.Tensor], CausalLMOutputWithPast]:
        r"""
        Args:
            labels (`mindspore.Tensor` of shape `(batch_size, sequence_length)`, *optional*):
                Labels for computing the left-to-right language modeling loss (next word prediction). Indices should be in
                `[-100, 0, ..., config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are
                ignored (masked), the loss is only computed for the tokens with labels n `[0, ..., config.vocab_size]`
            past_key_values (`tuple(tuple(mindspore.Tensor))` of length `config.n_layers` with each tuple having 4
                tensors of shape `(batch_size, num_heads, sequence_length - 1, embed_size_per_head)`):
                Contains precomputed key and value hidden states of the attention blocks. Can be used to speed up decoding.

                If `past_key_values` are used, the user can optionally input only the last `decoder_input_ids` (those that
                don't have their past key value states given to this model) of shape `(batch_size, 1)` instead of all
                `decoder_input_ids` of shape `(batch_size, sequence_length)`.
            use_cache (`bool`, *optional*):
                If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding
                (see`past_key_values`).

        Returns:
            `Union[Tuple[mindspore.Tensor], CausalLMOutputWithPast]`

        Example:
            Image captioning example:
            ```python
            >>> from transformers import AutoProcessor, AutoModelForCausalLM
            >>> import requests
            >>> from PIL import Image
            ...
            >>> processor = AutoProcessor.from_pretrained("microsoft/git-base-coco")
            >>> model = AutoModelForCausalLM.from_pretrained("microsoft/git-base-coco")
            ...
            >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
            >>> image = Image.open(requests.get(url, stream=True).raw)
            ...
            >>> pixel_values = processor(images=image, return_tensors="pt").pixel_values
            ...
            >>> generated_ids = model.generate(pixel_values=pixel_values, max_length=50)
            >>> generated_caption = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
            >>> print(generated_caption)
            two cats sleeping on a pink blanket next to remotes.
            ```

            Visual question answering (VQA) example:

            ```python
            >>> from transformers import AutoProcessor, AutoModelForCausalLM
            >>> from huggingface_hub import hf_hub_download
            >>> from PIL import Image
            ...
            >>> processor = AutoProcessor.from_pretrained("microsoft/git-base-textvqa")
            >>> model = AutoModelForCausalLM.from_pretrained("microsoft/git-base-textvqa")
            ...
            >>> file_path = hf_hub_download(repo_id="nielsr/textvqa-sample", filename="bus.png", repo_type="dataset")
            >>> image = Image.open(file_path).convert("RGB")
            ...
            >>> pixel_values = processor(images=image, return_tensors="pt").pixel_values
            ...
            >>> question = "what does the front of the bus say at the top?"
            ...
            >>> input_ids = processor(text=question, add_special_tokens=False).input_ids
            >>> input_ids = [processor.tokenizer.cls_token_id] + input_ids
            >>> input_ids = mindspore.Tensor(input_ids).unsqueeze(0)
            ...
            >>> generated_ids = model.generate(pixel_values=pixel_values, input_ids=input_ids, max_length=50)
            >>> print(processor.batch_decode(generated_ids, skip_special_tokens=True))
            ['what does the front of the bus say at the top? special']
            ```

            Video captioning example:

            ```python
            >>> import av
            >>> import numpy as np
            >>> from PIL import Image
            >>> from huggingface_hub import hf_hub_download
            >>> from transformers import AutoProcessor, AutoModelForCausalLM
            ...
            >>> processor = AutoProcessor.from_pretrained("microsoft/git-base-vatex")
            >>> model = AutoModelForCausalLM.from_pretrained("microsoft/git-base-vatex")
            ...
            >>> # set seed for reproducability
            >>> np.random.seed(45)
            ...
            ...
            >>> def read_video_pyav(container, indices):
            ...     '''
            ...     Decode the video with PyAV decoder.
            ...     Args:
            ...         container (`av.container.input.InputContainer`): PyAV container.
            ...         indices (`List[int]`): List of frame indices to decode.
            ...     Returns:
            ...         result (np.ndarray): np array of decoded frames of shape (num_frames, height, width, 3).
            ...     '''
            ...     frames = []
            ...     container.seek(0)
            ...     start_index = indices[0]
            ...     end_index = indices[-1]
            ...     for i, frame in enumerate(container.decode(video=0)):
            ...         if i > end_index:
            ...             break
            ...         if i >= start_index and i in indices:
            ...             frames.append(frame)
            ...     return np.stack([x.to_ndarray(format="rgb24") for x in frames])
            ...
            ...
            >>> def sample_frame_indices(clip_len, frame_sample_rate, seg_len):
            ...     '''
            ...     Sample a given number of frame indices from the video.
            ...     Args:
            ...         clip_len (`int`): Total number of frames to sample.
            ...         frame_sample_rate (`int`): Sample every n-th frame.
            ...         seg_len (`int`): Maximum allowed index of sample's last frame.
            ...     Returns:
            ...         indices (`List[int]`): List of sampled frame indices
            ...     '''
            ...     converted_len = int(clip_len * frame_sample_rate)
            ...     end_idx = np.random.randint(converted_len, seg_len)
            ...     start_idx = end_idx - converted_len
            ...     indices = np.linspace(start_idx, end_idx, num=clip_len)
            ...     indices = np.clip(indices, start_idx, end_idx - 1).astype(np.int64)
            ...     return indices
            ...
            ...
            >>> # load video
            >>> file_path = hf_hub_download(
            ...     repo_id="nielsr/video-demo", filename="eating_spaghetti.mp4", repo_type="dataset"
            ... )
            >>> container = av.open(file_path)
            ...
            >>> # sample frames
            >>> num_frames = model.config.num_image_with_embedding
            >>> indices = sample_frame_indices(
            ...     clip_len=num_frames, frame_sample_rate=4, seg_len=container.streams.video[0].frames
            ... )
            >>> frames = read_video_pyav(container, indices)
            ...
            >>> pixel_values = processor(images=list(frames), return_tensors="pt").pixel_values
            ...
            >>> generated_ids = model.generate(pixel_values=pixel_values, max_length=50)
            ...
            >>> print("Generated caption:", processor.batch_decode(generated_ids, skip_special_tokens=True))
            Generated caption: ['a woman is sitting at a table and she is talking about the food she is holding.']
            ```
        """
        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
        if labels is not None:
            use_cache = False

        outputs = self.git(
            input_ids,
            attention_mask=attention_mask,
            position_ids=position_ids,
            pixel_values=pixel_values,
            head_mask=head_mask,
            inputs_embeds=inputs_embeds,
            past_key_values=past_key_values,
            use_cache=use_cache,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
        )

        sequence_output = outputs[0]
        logits = self.output(sequence_output)

        loss = None
        if labels is not None:
            # we are doing next-token prediction; shift prediction scores and input ids by one
            num_image_tokens = self.git.encoder.layer[0].attention.self.image_patch_tokens
            shifted_logits = logits[:, num_image_tokens:-1, :]
            labels = labels[:, 1:]
            loss = ops.cross_entropy(shifted_logits.view(-1, self.config.vocab_size), labels.view(-1))

        if not return_dict:
            output = (logits,) + outputs[1:]
            return ((loss,) + output) if loss is not None else output

        return CausalLMOutputWithPast(
            loss=loss,
            logits=logits,
            past_key_values=outputs.past_key_values,
            hidden_states=outputs.hidden_states,
            attentions=outputs.attentions,
        )

    def prepare_inputs_for_generation(
        self, input_ids, past_key_values=None, attention_mask=None, use_cache=None, **kwargs
    ):
        # cut decoder_input_ids if past_key_values is used
        if past_key_values is not None:
            input_ids = input_ids[:, -1:]

        # if model is used as a decoder in encoder-decoder model, the decoder attention mask is created on the fly
        input_shape = input_ids.shape
        if attention_mask is None:
            attention_mask = input_ids.new_ones(input_shape)

        return {
            "input_ids": input_ids,
            "attention_mask": attention_mask,
            "pixel_values": kwargs.get("pixel_values", None),
            "past_key_values": past_key_values,
            "use_cache": use_cache,
        }

    def _reorder_cache(self, past_key_values, beam_idx):
        reordered_past = ()
        for layer_past in past_key_values:
            reordered_past += (
                tuple(past_state.index_select(0, beam_idx) for past_state in layer_past),
            )
        return reordered_past

mindnlp.transformers.models.git.modeling_git.GitForCausalLM.forward(input_ids=None, attention_mask=None, position_ids=None, pixel_values=None, head_mask=None, inputs_embeds=None, labels=None, past_key_values=None, use_cache=None, output_attentions=None, output_hidden_states=None, return_dict=None)

PARAMETER DESCRIPTION
labels

Labels for computing the left-to-right language modeling loss (next word prediction). Indices should be in [-100, 0, ..., config.vocab_size] (see input_ids docstring) Tokens with indices set to -100 are ignored (masked), the loss is only computed for the tokens with labels n [0, ..., config.vocab_size]

TYPE: `mindspore.Tensor` of shape `(batch_size, sequence_length)`, *optional* DEFAULT: None

use_cache

If set to True, past_key_values key value states are returned and can be used to speed up decoding (seepast_key_values).

TYPE: `bool`, *optional* DEFAULT: None

RETURNS DESCRIPTION
Union[Tuple[Tensor], CausalLMOutputWithPast]

Union[Tuple[mindspore.Tensor], CausalLMOutputWithPast]
Example

Image captioning example: 

>>> from transformers import AutoProcessor, AutoModelForCausalLM
>>> import requests
>>> from PIL import Image
...
>>> processor = AutoProcessor.from_pretrained("microsoft/git-base-coco")
>>> model = AutoModelForCausalLM.from_pretrained("microsoft/git-base-coco")
...
>>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
>>> image = Image.open(requests.get(url, stream=True).raw)
...
>>> pixel_values = processor(images=image, return_tensors="pt").pixel_values
...
>>> generated_ids = model.generate(pixel_values=pixel_values, max_length=50)
>>> generated_caption = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
>>> print(generated_caption)
two cats sleeping on a pink blanket next to remotes.

Visual question answering (VQA) example:

>>> from transformers import AutoProcessor, AutoModelForCausalLM
>>> from huggingface_hub import hf_hub_download
>>> from PIL import Image
...
>>> processor = AutoProcessor.from_pretrained("microsoft/git-base-textvqa")
>>> model = AutoModelForCausalLM.from_pretrained("microsoft/git-base-textvqa")
...
>>> file_path = hf_hub_download(repo_id="nielsr/textvqa-sample", filename="bus.png", repo_type="dataset")
>>> image = Image.open(file_path).convert("RGB")
...
>>> pixel_values = processor(images=image, return_tensors="pt").pixel_values
...
>>> question = "what does the front of the bus say at the top?"
...
>>> input_ids = processor(text=question, add_special_tokens=False).input_ids
>>> input_ids = [processor.tokenizer.cls_token_id] + input_ids
>>> input_ids = mindspore.Tensor(input_ids).unsqueeze(0)
...
>>> generated_ids = model.generate(pixel_values=pixel_values, input_ids=input_ids, max_length=50)
>>> print(processor.batch_decode(generated_ids, skip_special_tokens=True))
['what does the front of the bus say at the top? special']

Video captioning example:

>>> import av
>>> import numpy as np
>>> from PIL import Image
>>> from huggingface_hub import hf_hub_download
>>> from transformers import AutoProcessor, AutoModelForCausalLM
...
>>> processor = AutoProcessor.from_pretrained("microsoft/git-base-vatex")
>>> model = AutoModelForCausalLM.from_pretrained("microsoft/git-base-vatex")
...
>>> # set seed for reproducability
>>> np.random.seed(45)
...
...
>>> def read_video_pyav(container, indices):
...     '''
...     Decode the video with PyAV decoder.
...     Args:
...         container (`av.container.input.InputContainer`): PyAV container.
...         indices (`List[int]`): List of frame indices to decode.
...     Returns:
...         result (np.ndarray): np array of decoded frames of shape (num_frames, height, width, 3).
...     '''
...     frames = []
...     container.seek(0)
...     start_index = indices[0]
...     end_index = indices[-1]
...     for i, frame in enumerate(container.decode(video=0)):
...         if i > end_index:
...             break
...         if i >= start_index and i in indices:
...             frames.append(frame)
...     return np.stack([x.to_ndarray(format="rgb24") for x in frames])
...
...
>>> def sample_frame_indices(clip_len, frame_sample_rate, seg_len):
...     '''
...     Sample a given number of frame indices from the video.
...     Args:
...         clip_len (`int`): Total number of frames to sample.
...         frame_sample_rate (`int`): Sample every n-th frame.
...         seg_len (`int`): Maximum allowed index of sample's last frame.
...     Returns:
...         indices (`List[int]`): List of sampled frame indices
...     '''
...     converted_len = int(clip_len * frame_sample_rate)
...     end_idx = np.random.randint(converted_len, seg_len)
...     start_idx = end_idx - converted_len
...     indices = np.linspace(start_idx, end_idx, num=clip_len)
...     indices = np.clip(indices, start_idx, end_idx - 1).astype(np.int64)
...     return indices
...
...
>>> # load video
>>> file_path = hf_hub_download(
...     repo_id="nielsr/video-demo", filename="eating_spaghetti.mp4", repo_type="dataset"
... )
>>> container = av.open(file_path)
...
>>> # sample frames
>>> num_frames = model.config.num_image_with_embedding
>>> indices = sample_frame_indices(
...     clip_len=num_frames, frame_sample_rate=4, seg_len=container.streams.video[0].frames
... )
>>> frames = read_video_pyav(container, indices)
...
>>> pixel_values = processor(images=list(frames), return_tensors="pt").pixel_values
...
>>> generated_ids = model.generate(pixel_values=pixel_values, max_length=50)
...
>>> print("Generated caption:", processor.batch_decode(generated_ids, skip_special_tokens=True))
Generated caption: ['a woman is sitting at a table and she is talking about the food she is holding.']
Source code in mindnlp/transformers/models/git/modeling_git.py 
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
def forward(
    self,
    input_ids: Optional[mindspore.Tensor] = None,
    attention_mask: Optional[mindspore.Tensor] = None,
    position_ids: Optional[mindspore.Tensor] = None,
    pixel_values: Optional[mindspore.Tensor] = None,
    head_mask: Optional[mindspore.Tensor] = None,
    inputs_embeds: Optional[mindspore.Tensor] = None,
    labels: Optional[mindspore.Tensor] = None,
    past_key_values: Optional[List[mindspore.Tensor]] = None,
    use_cache: Optional[bool] = None,
    output_attentions: Optional[bool] = None,
    output_hidden_states: Optional[bool] = None,
    return_dict: Optional[bool] = None,
) -> Union[Tuple[mindspore.Tensor], CausalLMOutputWithPast]:
    r"""
    Args:
        labels (`mindspore.Tensor` of shape `(batch_size, sequence_length)`, *optional*):
            Labels for computing the left-to-right language modeling loss (next word prediction). Indices should be in
            `[-100, 0, ..., config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are
            ignored (masked), the loss is only computed for the tokens with labels n `[0, ..., config.vocab_size]`
        past_key_values (`tuple(tuple(mindspore.Tensor))` of length `config.n_layers` with each tuple having 4
            tensors of shape `(batch_size, num_heads, sequence_length - 1, embed_size_per_head)`):
            Contains precomputed key and value hidden states of the attention blocks. Can be used to speed up decoding.

            If `past_key_values` are used, the user can optionally input only the last `decoder_input_ids` (those that
            don't have their past key value states given to this model) of shape `(batch_size, 1)` instead of all
            `decoder_input_ids` of shape `(batch_size, sequence_length)`.
        use_cache (`bool`, *optional*):
            If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding
            (see`past_key_values`).

    Returns:
        `Union[Tuple[mindspore.Tensor], CausalLMOutputWithPast]`

    Example:
        Image captioning example:
        ```python
        >>> from transformers import AutoProcessor, AutoModelForCausalLM
        >>> import requests
        >>> from PIL import Image
        ...
        >>> processor = AutoProcessor.from_pretrained("microsoft/git-base-coco")
        >>> model = AutoModelForCausalLM.from_pretrained("microsoft/git-base-coco")
        ...
        >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
        >>> image = Image.open(requests.get(url, stream=True).raw)
        ...
        >>> pixel_values = processor(images=image, return_tensors="pt").pixel_values
        ...
        >>> generated_ids = model.generate(pixel_values=pixel_values, max_length=50)
        >>> generated_caption = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
        >>> print(generated_caption)
        two cats sleeping on a pink blanket next to remotes.
        ```

        Visual question answering (VQA) example:

        ```python
        >>> from transformers import AutoProcessor, AutoModelForCausalLM
        >>> from huggingface_hub import hf_hub_download
        >>> from PIL import Image
        ...
        >>> processor = AutoProcessor.from_pretrained("microsoft/git-base-textvqa")
        >>> model = AutoModelForCausalLM.from_pretrained("microsoft/git-base-textvqa")
        ...
        >>> file_path = hf_hub_download(repo_id="nielsr/textvqa-sample", filename="bus.png", repo_type="dataset")
        >>> image = Image.open(file_path).convert("RGB")
        ...
        >>> pixel_values = processor(images=image, return_tensors="pt").pixel_values
        ...
        >>> question = "what does the front of the bus say at the top?"
        ...
        >>> input_ids = processor(text=question, add_special_tokens=False).input_ids
        >>> input_ids = [processor.tokenizer.cls_token_id] + input_ids
        >>> input_ids = mindspore.Tensor(input_ids).unsqueeze(0)
        ...
        >>> generated_ids = model.generate(pixel_values=pixel_values, input_ids=input_ids, max_length=50)
        >>> print(processor.batch_decode(generated_ids, skip_special_tokens=True))
        ['what does the front of the bus say at the top? special']
        ```

        Video captioning example:

        ```python
        >>> import av
        >>> import numpy as np
        >>> from PIL import Image
        >>> from huggingface_hub import hf_hub_download
        >>> from transformers import AutoProcessor, AutoModelForCausalLM
        ...
        >>> processor = AutoProcessor.from_pretrained("microsoft/git-base-vatex")
        >>> model = AutoModelForCausalLM.from_pretrained("microsoft/git-base-vatex")
        ...
        >>> # set seed for reproducability
        >>> np.random.seed(45)
        ...
        ...
        >>> def read_video_pyav(container, indices):
        ...     '''
        ...     Decode the video with PyAV decoder.
        ...     Args:
        ...         container (`av.container.input.InputContainer`): PyAV container.
        ...         indices (`List[int]`): List of frame indices to decode.
        ...     Returns:
        ...         result (np.ndarray): np array of decoded frames of shape (num_frames, height, width, 3).
        ...     '''
        ...     frames = []
        ...     container.seek(0)
        ...     start_index = indices[0]
        ...     end_index = indices[-1]
        ...     for i, frame in enumerate(container.decode(video=0)):
        ...         if i > end_index:
        ...             break
        ...         if i >= start_index and i in indices:
        ...             frames.append(frame)
        ...     return np.stack([x.to_ndarray(format="rgb24") for x in frames])
        ...
        ...
        >>> def sample_frame_indices(clip_len, frame_sample_rate, seg_len):
        ...     '''
        ...     Sample a given number of frame indices from the video.
        ...     Args:
        ...         clip_len (`int`): Total number of frames to sample.
        ...         frame_sample_rate (`int`): Sample every n-th frame.
        ...         seg_len (`int`): Maximum allowed index of sample's last frame.
        ...     Returns:
        ...         indices (`List[int]`): List of sampled frame indices
        ...     '''
        ...     converted_len = int(clip_len * frame_sample_rate)
        ...     end_idx = np.random.randint(converted_len, seg_len)
        ...     start_idx = end_idx - converted_len
        ...     indices = np.linspace(start_idx, end_idx, num=clip_len)
        ...     indices = np.clip(indices, start_idx, end_idx - 1).astype(np.int64)
        ...     return indices
        ...
        ...
        >>> # load video
        >>> file_path = hf_hub_download(
        ...     repo_id="nielsr/video-demo", filename="eating_spaghetti.mp4", repo_type="dataset"
        ... )
        >>> container = av.open(file_path)
        ...
        >>> # sample frames
        >>> num_frames = model.config.num_image_with_embedding
        >>> indices = sample_frame_indices(
        ...     clip_len=num_frames, frame_sample_rate=4, seg_len=container.streams.video[0].frames
        ... )
        >>> frames = read_video_pyav(container, indices)
        ...
        >>> pixel_values = processor(images=list(frames), return_tensors="pt").pixel_values
        ...
        >>> generated_ids = model.generate(pixel_values=pixel_values, max_length=50)
        ...
        >>> print("Generated caption:", processor.batch_decode(generated_ids, skip_special_tokens=True))
        Generated caption: ['a woman is sitting at a table and she is talking about the food she is holding.']
        ```
    """
    return_dict = return_dict if return_dict is not None else self.config.use_return_dict
    if labels is not None:
        use_cache = False

    outputs = self.git(
        input_ids,
        attention_mask=attention_mask,
        position_ids=position_ids,
        pixel_values=pixel_values,
        head_mask=head_mask,
        inputs_embeds=inputs_embeds,
        past_key_values=past_key_values,
        use_cache=use_cache,
        output_attentions=output_attentions,
        output_hidden_states=output_hidden_states,
        return_dict=return_dict,
    )

    sequence_output = outputs[0]
    logits = self.output(sequence_output)

    loss = None
    if labels is not None:
        # we are doing next-token prediction; shift prediction scores and input ids by one
        num_image_tokens = self.git.encoder.layer[0].attention.self.image_patch_tokens
        shifted_logits = logits[:, num_image_tokens:-1, :]
        labels = labels[:, 1:]
        loss = ops.cross_entropy(shifted_logits.view(-1, self.config.vocab_size), labels.view(-1))

    if not return_dict:
        output = (logits,) + outputs[1:]
        return ((loss,) + output) if loss is not None else output

    return CausalLMOutputWithPast(
        loss=loss,
        logits=logits,
        past_key_values=outputs.past_key_values,
        hidden_states=outputs.hidden_states,
        attentions=outputs.attentions,
    )

mindnlp.transformers.models.git.modeling_git.GitModel

Bases: GitPreTrainedModel

Source code in mindnlp/transformers/models/git/modeling_git.py 
 946
 947
 948
 949
 950
 951
 952
 953
 954
 955
 956
 957
 958
 959
 960
 961
 962
 963
 964
 965
 966
 967
 968
 969
 970
 971
 972
 973
 974
 975
 976
 977
 978
 979
 980
 981
 982
 983
 984
 985
 986
 987
 988
 989
 990
 991
 992
 993
 994
 995
 996
 997
 998
 999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
class GitModel(GitPreTrainedModel):
    def __init__(self, config):
        super().__init__(config)
        self.config = config

        self.embeddings = GitEmbeddings(config)
        self.image_encoder = GitVisionModel(config.vision_config)
        self.encoder = GitEncoder(config)

        self.visual_projection = GitProjection(config)

        if config.num_image_with_embedding is not None:
            self.img_temperal_embedding = (
                Parameter(ops.zeros(1, 1, config.vision_config.hidden_size), 'img_temperal_embedding_' + str(_))
                for _ in range(config.num_image_with_embedding)
            )

        # Initialize weights and apply final processing
        self.post_init()

    def get_input_embeddings(self):
        return self.embeddings.word_embeddings

    def set_input_embeddings(self, value):
        self.embeddings.word_embeddings = value

    def _prune_heads(self, heads_to_prune):
        """
        Prunes heads of the model. heads_to_prune: dict of {layer_num: list of heads to prune in this layer} See base
        class PreTrainedModel
        """
        for layer, heads in heads_to_prune.items():
            self.encoder.layer[layer].attention.prune_heads(heads)

    def _generate_future_mask(self, size: int, dtype: mindspore.dtype) -> mindspore.Tensor:
        # Default mask is for forward direction. Flip for backward direction.
        mask = ops.triu(ops.ones(size, size, dtype=dtype), diagonal=1)
        mask = mask.masked_fill(mask == 1, float("-inf"))
        return mask

    def create_attention_mask(self, tgt, memory, tgt_mask, past_key_values_length, memory_key_padding_mask=None):
        num_tgt = tgt.shape[1]
        num_memory = memory.shape[1]
        dtype = tgt.dtype
        top_left = ops.zeros((num_memory, num_memory), dtype=dtype)
        top_right = ops.full(
            (num_memory, num_tgt + past_key_values_length),
            float("-inf"),
            dtype=dtype,
        )
        bottom_left = ops.zeros(
            (num_tgt, num_memory),
            dtype=dtype,
        )

        if past_key_values_length > 0:
            tgt_mask = ops.zeros(
                (tgt_mask.shape[0], tgt_mask.shape[0] + past_key_values_length),
                dtype=dtype,
            )

        left = ops.cat((top_left, bottom_left), axis=0)
        right = ops.cat((top_right, tgt_mask.astype(dtype)), axis=0)

        full_attention_mask = ops.cat((left, right), axis=1)[None, :]

        if memory_key_padding_mask is None:
            if memory.shape[1] == 0:
                memory_key_padding_mask = ops.full((memory.shape[0], 1), fill_value=False, dtype=mindspore.bool_)
            else:
                memory_key_padding_mask = ops.full((memory.shape[0], memory.shape[1]), fill_value=False, dtype=mindspore.bool_)
        # if it is False, it means valid. That is, it is not a padding
        if memory_key_padding_mask.dtype != mindspore.bool_:
            raise ValueError("Memory key padding mask must be a boolean tensor.")
        zero_negative_infinity = ops.zeros_like(memory_key_padding_mask, dtype=tgt.dtype)
        zero_negative_infinity[memory_key_padding_mask] = float("-inf")
        full_attention_mask = full_attention_mask.broadcast_to(
            (memory_key_padding_mask.shape[0], num_memory + num_tgt, num_memory + past_key_values_length + num_tgt)
        )
        full_attention_mask = full_attention_mask.copy()
        if num_memory != 0:
            origin_left = full_attention_mask[:, :, :num_memory]
            update = zero_negative_infinity[:, None, :]
            full_attention_mask[:, :, :num_memory] = origin_left + update
        else:
            origin_left = full_attention_mask[:, :, :]
            update = zero_negative_infinity[:, None, :]
            full_attention_mask[:, :, :] = origin_left + update

        # add axis for multi-head
        full_attention_mask = full_attention_mask[:, None, :, :]

        return full_attention_mask

    def forward(
        self,
        input_ids: Optional[mindspore.Tensor] = None,
        attention_mask: Optional[mindspore.Tensor] = None,
        position_ids: Optional[mindspore.Tensor] = None,
        pixel_values: Optional[mindspore.Tensor] = None,
        head_mask: Optional[mindspore.Tensor] = None,
        inputs_embeds: Optional[mindspore.Tensor] = None,
        past_key_values: Optional[List[mindspore.Tensor]] = None,
        use_cache: Optional[bool] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
    ) -> Union[Tuple[mindspore.Tensor], BaseModelOutputWithPooling]:
        r"""
        Args:
            past_key_values (`tuple(tuple(mindspore.Tensor))` of length `config.n_layers` with each tuple having 4 tensors
                of shape `(batch_size, num_heads, sequence_length - 1, embed_size_per_head)`):

                - Contains precomputed key and value hidden states of the attention blocks. Can be used to speed up decoding.
                - If `past_key_values` are used, the user can optionally input only the last `decoder_input_ids` (those that
                don't have their past key value states given to this model) of shape `(batch_size, 1)` instead of all
                `decoder_input_ids` of shape `(batch_size, sequence_length)`.
            use_cache (`bool`, *optional*):
                If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see
                `past_key_values`).

        Returns:
            `Union[Tuple[mindspore.Tensor], BaseModelOutputWithPooling]`

        Example:
            ```python
            >>> from transformers import AutoProcessor, AutoModel
            >>> import requests
            >>> from PIL import Image
            ...
            >>> processor = AutoProcessor.from_pretrained("microsoft/git-base")
            >>> model = AutoModel.from_pretrained("microsoft/git-base")
            ...
            >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
            >>> image = Image.open(requests.get(url, stream=True).raw)
            ...
            >>> text = "this is an image of two cats"
            ...
            >>> inputs = processor(text, images=image, return_tensors="pt")
            ...
            >>> outputs = model(**inputs)
            >>> last_hidden_state = outputs.last_hidden_state
            ```
        """
        output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
        output_hidden_states = (
            output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
        )
        use_cache = use_cache if use_cache is not None else self.config.use_cache
        return_dict = return_dict if return_dict is not None else self.config.use_return_dict

        if input_ids is not None and inputs_embeds is not None:
            raise ValueError("You cannot specify both input_ids and inputs_embeds at the same time")
        elif input_ids is not None:
            self.warn_if_padding_and_no_attention_mask(input_ids, attention_mask)
            input_shape = input_ids.shape
        elif inputs_embeds is not None:
            input_shape = inputs_embeds.shape[:-1]
        else:
            raise ValueError("You have to specify either input_ids or inputs_embeds")

        seq_length = input_shape[1]

        # past_key_values_length
        past_key_values_length = past_key_values[0][0].shape[2] if past_key_values is not None else 0

        # Prepare head mask if needed
        # 1.0 in head_mask indicate we keep the head
        # attention_probs has shape bsz x n_heads x N x N
        # input head_mask has shape [num_heads] or [num_hidden_layers x num_heads]
        # and head_mask is converted to shape [num_hidden_layers x batch x num_heads x seq_length x seq_length]
        head_mask = self.get_head_mask(head_mask, self.config.num_hidden_layers)

        projected_visual_features = None
        if pixel_values is not None:
            if pixel_values.ndim == 4:
                # here we assume pixel_values is of shape (batch_size, num_channels, height, width)
                visual_features = self.image_encoder(pixel_values).last_hidden_state

            elif pixel_values.ndim == 5:
                # here we assume pixel_values is of shape (batch_size, num_frames, num_channels, height, width)
                visual_features = []
                for frame_idx in range(pixel_values.shape[1]):
                    visual_features_frame = self.image_encoder(pixel_values[:, frame_idx, :, :]).last_hidden_state
                    visual_features_frame += self.img_temperal_embedding[frame_idx]
                    visual_features.append(visual_features_frame)

                # finally, concatenate all features along sequence dimension
                visual_features = ops.cat(visual_features, axis=1)

            else:
                raise ValueError("pixel_values must be of rank 4 or 5")

            projected_visual_features = self.visual_projection(visual_features)

        embedding_output = self.embeddings(
            input_ids=input_ids,
            position_ids=position_ids,
            inputs_embeds=inputs_embeds,
            past_key_values_length=past_key_values_length,
        )

        if projected_visual_features is None:
            projected_visual_features = ops.zeros(
                (embedding_output.shape[0], 0, embedding_output.shape[2]),
                dtype=embedding_output.dtype,
            )

        # Repeat visual features to match embedding batch size.
        projected_visual_features = projected_visual_features.repeat(
            embedding_output.shape[0] // projected_visual_features.shape[0], 1, 1
        )

        # concatenate patch token and text token embeddings
        hidden_states = ops.cat((projected_visual_features, embedding_output), axis=1)

        # By default, an additive causal mask is created
        # for masking the future (one direction).
        tgt_mask = self._generate_future_mask(seq_length, embedding_output.dtype)

        # Create an attention mask of shape (batch_size, 1, tgt_seq_len, src_seq_len)
        combined_attention_mask = self.create_attention_mask(
            tgt=embedding_output,
            memory=projected_visual_features,
            tgt_mask=tgt_mask,
            past_key_values_length=past_key_values_length,
        )

        if attention_mask is not None:
            # if the user provides an attention mask, we add it to the default one
            # [bsz, seq_len] -> [bsz, 1, tgt_seq_len, src_seq_len]
            expanded_attn_mask = _prepare_4d_attention_mask(
                attention_mask, embedding_output.dtype, tgt_len=input_shape[-1]
            )
            if past_key_values_length > 0:
                expanded_attn_mask = expanded_attn_mask[:, :, -past_key_values_length:, :]
            else:
                combined_attention_mask[:, :, -input_shape[1] :, -input_shape[1] :] += expanded_attn_mask

        encoder_outputs = self.encoder(
            hidden_states,
            attention_mask=combined_attention_mask,
            head_mask=head_mask,
            past_key_values=past_key_values,
            use_cache=use_cache,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
            pixel_values_present=pixel_values is not None,
        )
        sequence_output = encoder_outputs[0]

        if not return_dict:
            return (sequence_output,) + encoder_outputs[1:]

        return BaseModelOutputWithPast(
            last_hidden_state=sequence_output,
            past_key_values=encoder_outputs.past_key_values,
            hidden_states=encoder_outputs.hidden_states,
            attentions=encoder_outputs.attentions,
        )

mindnlp.transformers.models.git.modeling_git.GitModel.forward(input_ids=None, attention_mask=None, position_ids=None, pixel_values=None, head_mask=None, inputs_embeds=None, past_key_values=None, use_cache=None, output_attentions=None, output_hidden_states=None, return_dict=None)

PARAMETER DESCRIPTION
use_cache

If set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_key_values).

TYPE: `bool`, *optional* DEFAULT: None

RETURNS DESCRIPTION
Union[Tuple[Tensor], BaseModelOutputWithPooling]

Union[Tuple[mindspore.Tensor], BaseModelOutputWithPooling]
Example 
>>> from transformers import AutoProcessor, AutoModel
>>> import requests
>>> from PIL import Image
...
>>> processor = AutoProcessor.from_pretrained("microsoft/git-base")
>>> model = AutoModel.from_pretrained("microsoft/git-base")
...
>>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
>>> image = Image.open(requests.get(url, stream=True).raw)
...
>>> text = "this is an image of two cats"
...
>>> inputs = processor(text, images=image, return_tensors="pt")
...
>>> outputs = model(**inputs)
>>> last_hidden_state = outputs.last_hidden_state
Source code in mindnlp/transformers/models/git/modeling_git.py 
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
def forward(
    self,
    input_ids: Optional[mindspore.Tensor] = None,
    attention_mask: Optional[mindspore.Tensor] = None,
    position_ids: Optional[mindspore.Tensor] = None,
    pixel_values: Optional[mindspore.Tensor] = None,
    head_mask: Optional[mindspore.Tensor] = None,
    inputs_embeds: Optional[mindspore.Tensor] = None,
    past_key_values: Optional[List[mindspore.Tensor]] = None,
    use_cache: Optional[bool] = None,
    output_attentions: Optional[bool] = None,
    output_hidden_states: Optional[bool] = None,
    return_dict: Optional[bool] = None,
) -> Union[Tuple[mindspore.Tensor], BaseModelOutputWithPooling]:
    r"""
    Args:
        past_key_values (`tuple(tuple(mindspore.Tensor))` of length `config.n_layers` with each tuple having 4 tensors
            of shape `(batch_size, num_heads, sequence_length - 1, embed_size_per_head)`):

            - Contains precomputed key and value hidden states of the attention blocks. Can be used to speed up decoding.
            - If `past_key_values` are used, the user can optionally input only the last `decoder_input_ids` (those that
            don't have their past key value states given to this model) of shape `(batch_size, 1)` instead of all
            `decoder_input_ids` of shape `(batch_size, sequence_length)`.
        use_cache (`bool`, *optional*):
            If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see
            `past_key_values`).

    Returns:
        `Union[Tuple[mindspore.Tensor], BaseModelOutputWithPooling]`

    Example:
        ```python
        >>> from transformers import AutoProcessor, AutoModel
        >>> import requests
        >>> from PIL import Image
        ...
        >>> processor = AutoProcessor.from_pretrained("microsoft/git-base")
        >>> model = AutoModel.from_pretrained("microsoft/git-base")
        ...
        >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
        >>> image = Image.open(requests.get(url, stream=True).raw)
        ...
        >>> text = "this is an image of two cats"
        ...
        >>> inputs = processor(text, images=image, return_tensors="pt")
        ...
        >>> outputs = model(**inputs)
        >>> last_hidden_state = outputs.last_hidden_state
        ```
    """
    output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
    output_hidden_states = (
        output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
    )
    use_cache = use_cache if use_cache is not None else self.config.use_cache
    return_dict = return_dict if return_dict is not None else self.config.use_return_dict

    if input_ids is not None and inputs_embeds is not None:
        raise ValueError("You cannot specify both input_ids and inputs_embeds at the same time")
    elif input_ids is not None:
        self.warn_if_padding_and_no_attention_mask(input_ids, attention_mask)
        input_shape = input_ids.shape
    elif inputs_embeds is not None:
        input_shape = inputs_embeds.shape[:-1]
    else:
        raise ValueError("You have to specify either input_ids or inputs_embeds")

    seq_length = input_shape[1]

    # past_key_values_length
    past_key_values_length = past_key_values[0][0].shape[2] if past_key_values is not None else 0

    # Prepare head mask if needed
    # 1.0 in head_mask indicate we keep the head
    # attention_probs has shape bsz x n_heads x N x N
    # input head_mask has shape [num_heads] or [num_hidden_layers x num_heads]
    # and head_mask is converted to shape [num_hidden_layers x batch x num_heads x seq_length x seq_length]
    head_mask = self.get_head_mask(head_mask, self.config.num_hidden_layers)

    projected_visual_features = None
    if pixel_values is not None:
        if pixel_values.ndim == 4:
            # here we assume pixel_values is of shape (batch_size, num_channels, height, width)
            visual_features = self.image_encoder(pixel_values).last_hidden_state

        elif pixel_values.ndim == 5:
            # here we assume pixel_values is of shape (batch_size, num_frames, num_channels, height, width)
            visual_features = []
            for frame_idx in range(pixel_values.shape[1]):
                visual_features_frame = self.image_encoder(pixel_values[:, frame_idx, :, :]).last_hidden_state
                visual_features_frame += self.img_temperal_embedding[frame_idx]
                visual_features.append(visual_features_frame)

            # finally, concatenate all features along sequence dimension
            visual_features = ops.cat(visual_features, axis=1)

        else:
            raise ValueError("pixel_values must be of rank 4 or 5")

        projected_visual_features = self.visual_projection(visual_features)

    embedding_output = self.embeddings(
        input_ids=input_ids,
        position_ids=position_ids,
        inputs_embeds=inputs_embeds,
        past_key_values_length=past_key_values_length,
    )

    if projected_visual_features is None:
        projected_visual_features = ops.zeros(
            (embedding_output.shape[0], 0, embedding_output.shape[2]),
            dtype=embedding_output.dtype,
        )

    # Repeat visual features to match embedding batch size.
    projected_visual_features = projected_visual_features.repeat(
        embedding_output.shape[0] // projected_visual_features.shape[0], 1, 1
    )

    # concatenate patch token and text token embeddings
    hidden_states = ops.cat((projected_visual_features, embedding_output), axis=1)

    # By default, an additive causal mask is created
    # for masking the future (one direction).
    tgt_mask = self._generate_future_mask(seq_length, embedding_output.dtype)

    # Create an attention mask of shape (batch_size, 1, tgt_seq_len, src_seq_len)
    combined_attention_mask = self.create_attention_mask(
        tgt=embedding_output,
        memory=projected_visual_features,
        tgt_mask=tgt_mask,
        past_key_values_length=past_key_values_length,
    )

    if attention_mask is not None:
        # if the user provides an attention mask, we add it to the default one
        # [bsz, seq_len] -> [bsz, 1, tgt_seq_len, src_seq_len]
        expanded_attn_mask = _prepare_4d_attention_mask(
            attention_mask, embedding_output.dtype, tgt_len=input_shape[-1]
        )
        if past_key_values_length > 0:
            expanded_attn_mask = expanded_attn_mask[:, :, -past_key_values_length:, :]
        else:
            combined_attention_mask[:, :, -input_shape[1] :, -input_shape[1] :] += expanded_attn_mask

    encoder_outputs = self.encoder(
        hidden_states,
        attention_mask=combined_attention_mask,
        head_mask=head_mask,
        past_key_values=past_key_values,
        use_cache=use_cache,
        output_attentions=output_attentions,
        output_hidden_states=output_hidden_states,
        return_dict=return_dict,
        pixel_values_present=pixel_values is not None,
    )
    sequence_output = encoder_outputs[0]

    if not return_dict:
        return (sequence_output,) + encoder_outputs[1:]

    return BaseModelOutputWithPast(
        last_hidden_state=sequence_output,
        past_key_values=encoder_outputs.past_key_values,
        hidden_states=encoder_outputs.hidden_states,
        attentions=encoder_outputs.attentions,
    )

mindnlp.transformers.models.git.modeling_git.GitPreTrainedModel

Bases: PreTrainedModel

An abstract class to handle weights initialization and a simple interface for downloading and loading pretrained models.

Source code in mindnlp/transformers/models/git/modeling_git.py 
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
class GitPreTrainedModel(PreTrainedModel):
    """
    An abstract class to handle weights initialization and a simple interface for downloading and loading pretrained
    models.
    """

    config_class = GitConfig
    base_model_prefix = "git"
    supports_gradient_checkpointing = True

    def _init_weights(self, cell):
        """Initialize the weights"""
        if isinstance(cell, GitVisionEmbeddings):
            cell.class_embedding.set_data(initializer(Normal(self.config.initializer_range),
                                                        cell.class_embedding.shape, cell.class_embedding.dtype))
            cell.patch_embedding.weight.set_data(initializer(Normal(self.config.initializer_range),
                                                                cell.patch_embedding.weight.shape, cell.patch_embedding.weight.dtype))
            cell.position_embedding.weight.set_data(initializer(Normal(self.config.initializer_range),
                                                                cell.position_embedding.weight.shape, cell.position_embedding.weight.dtype))
        if isinstance(cell, nn.Linear):
            # Slightly different from the TF version which uses truncated_normal for initialization
            # cf https://github.com/pytorch/pytorch/pull/5617
            cell.weight.set_data(initializer(Normal(self.config.initializer_range), cell.weight.shape, cell.weight.dtype))
            if cell.bias:
                cell.bias.set_data(initializer('zeros', cell.bias.shape, cell.bias.dtype))
        elif isinstance(cell, nn.Embedding):
            cell.weight.set_data(initializer(Normal(self.config.initializer_range), cell.weight.shape, cell.weight.dtype))
            if cell.padding_idx:
                cell.weight.data[cell.padding_idx] = 0
        elif isinstance(cell, nn.LayerNorm):
            cell.bias.set_data(initializer('zeros', cell.bias.shape, cell.bias.dtype))
            cell.weight.set_data(initializer('ones', cell.weight.shape, cell.weight.dtype))

mindnlp.transformers.models.git.modeling_git.GitVisionAttention

Bases: Module

Multi-headed attention from 'Attention Is All You Need' paper

Source code in mindnlp/transformers/models/git/modeling_git.py 
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
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
class GitVisionAttention(nn.Module):
    """Multi-headed attention from 'Attention Is All You Need' paper"""

    def __init__(self, config):
        super().__init__()
        self.config = config
        self.embed_dim = config.hidden_size
        self.num_heads = config.num_attention_heads
        self.head_dim = self.embed_dim // self.num_heads
        if self.head_dim * self.num_heads != self.embed_dim:
            raise ValueError(
                f"embed_dim must be divisible by num_heads (got `embed_dim`: {self.embed_dim} and `num_heads`:"
                f" {self.num_heads})."
            )
        self.scale = self.head_dim**-0.5
        self.dropout = config.attention_dropout

        self.k_proj = nn.Linear(self.embed_dim, self.embed_dim)
        self.v_proj = nn.Linear(self.embed_dim, self.embed_dim)
        self.q_proj = nn.Linear(self.embed_dim, self.embed_dim)
        self.out_proj = nn.Linear(self.embed_dim, self.embed_dim)

    def _shape(self, tensor: mindspore.Tensor, seq_len: int, bsz: int):
        return tensor.view(bsz, seq_len, self.num_heads, self.head_dim).swapaxes(1, 2)

    def forward(
        self,
        hidden_states: mindspore.Tensor,
        attention_mask: Optional[mindspore.Tensor] = None,
        causal_attention_mask: Optional[mindspore.Tensor] = None,
        output_attentions: Optional[bool] = False,
    ) -> Tuple[mindspore.Tensor, Optional[mindspore.Tensor], Optional[Tuple[mindspore.Tensor]]]:
        """Input shape: Batch x Time x Channel"""

        bsz, tgt_len, embed_dim = hidden_states.shape

        # get query proj
        query_states = self.q_proj(hidden_states) * self.scale
        key_states = self._shape(self.k_proj(hidden_states), -1, bsz)
        value_states = self._shape(self.v_proj(hidden_states), -1, bsz)

        proj_shape = (bsz * self.num_heads, -1, self.head_dim)
        query_states = self._shape(query_states, tgt_len, bsz).view(*proj_shape)
        key_states = key_states.view(*proj_shape)
        value_states = value_states.view(*proj_shape)

        src_len = key_states.shape[1]
        attn_weights = ops.bmm(query_states, key_states.swapaxes(1, 2))

        if attn_weights.shape != (bsz * self.num_heads, tgt_len, src_len):
            raise ValueError(
                f"Attention weights should be of size {(bsz * self.num_heads, tgt_len, src_len)}, but is"
                f" {attn_weights.shape}"
            )

        # apply the causal_attention_mask first
        if causal_attention_mask is not None:
            if causal_attention_mask.shape != (bsz, 1, tgt_len, src_len):
                raise ValueError(
                    f"Attention mask should be of size {(bsz, 1, tgt_len, src_len)}, but is"
                    f" {causal_attention_mask.shape}"
                )
            attn_weights = attn_weights.view(bsz, self.num_heads, tgt_len, src_len) + causal_attention_mask
            attn_weights = attn_weights.view(bsz * self.num_heads, tgt_len, src_len)

        if attention_mask is not None:
            if attention_mask.shape != (bsz, 1, tgt_len, src_len):
                raise ValueError(
                    f"Attention mask should be of size {(bsz, 1, tgt_len, src_len)}, but is {attention_mask.shape}"
                )
            attn_weights = attn_weights.view(bsz, self.num_heads, tgt_len, src_len) + attention_mask
            attn_weights = attn_weights.view(bsz * self.num_heads, tgt_len, src_len)

        attn_weights = ops.softmax(attn_weights, axis=-1)

        if output_attentions:
            # this operation is a bit akward, but it's required to
            # make sure that attn_weights keeps its gradient.
            # In order to do so, attn_weights have to reshaped
            # twice and have to be reused in the following
            attn_weights_reshaped = attn_weights.view(bsz, self.num_heads, tgt_len, src_len)
            attn_weights = attn_weights_reshaped.view(bsz * self.num_heads, tgt_len, src_len)
        else:
            attn_weights_reshaped = None

        attn_probs = ops.dropout(attn_weights, p=self.dropout, training=self.training)

        attn_output = ops.bmm(attn_probs, value_states)

        if attn_output.shape != (bsz * self.num_heads, tgt_len, self.head_dim):
            raise ValueError(
                f"`attn_output` should be of size {(bsz, self.num_heads, tgt_len, self.head_dim)}, but is"
                f" {attn_output.shape}"
            )

        attn_output = attn_output.view(bsz, self.num_heads, tgt_len, self.head_dim)
        attn_output = attn_output.swapaxes(1, 2)
        attn_output = attn_output.reshape(bsz, tgt_len, embed_dim)

        attn_output = self.out_proj(attn_output)

        return attn_output, attn_weights_reshaped

mindnlp.transformers.models.git.modeling_git.GitVisionAttention.forward(hidden_states, attention_mask=None, causal_attention_mask=None, output_attentions=False)

Input shape: Batch x Time x Channel

Source code in mindnlp/transformers/models/git/modeling_git.py 
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
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
def forward(
    self,
    hidden_states: mindspore.Tensor,
    attention_mask: Optional[mindspore.Tensor] = None,
    causal_attention_mask: Optional[mindspore.Tensor] = None,
    output_attentions: Optional[bool] = False,
) -> Tuple[mindspore.Tensor, Optional[mindspore.Tensor], Optional[Tuple[mindspore.Tensor]]]:
    """Input shape: Batch x Time x Channel"""

    bsz, tgt_len, embed_dim = hidden_states.shape

    # get query proj
    query_states = self.q_proj(hidden_states) * self.scale
    key_states = self._shape(self.k_proj(hidden_states), -1, bsz)
    value_states = self._shape(self.v_proj(hidden_states), -1, bsz)

    proj_shape = (bsz * self.num_heads, -1, self.head_dim)
    query_states = self._shape(query_states, tgt_len, bsz).view(*proj_shape)
    key_states = key_states.view(*proj_shape)
    value_states = value_states.view(*proj_shape)

    src_len = key_states.shape[1]
    attn_weights = ops.bmm(query_states, key_states.swapaxes(1, 2))

    if attn_weights.shape != (bsz * self.num_heads, tgt_len, src_len):
        raise ValueError(
            f"Attention weights should be of size {(bsz * self.num_heads, tgt_len, src_len)}, but is"
            f" {attn_weights.shape}"
        )

    # apply the causal_attention_mask first
    if causal_attention_mask is not None:
        if causal_attention_mask.shape != (bsz, 1, tgt_len, src_len):
            raise ValueError(
                f"Attention mask should be of size {(bsz, 1, tgt_len, src_len)}, but is"
                f" {causal_attention_mask.shape}"
            )
        attn_weights = attn_weights.view(bsz, self.num_heads, tgt_len, src_len) + causal_attention_mask
        attn_weights = attn_weights.view(bsz * self.num_heads, tgt_len, src_len)

    if attention_mask is not None:
        if attention_mask.shape != (bsz, 1, tgt_len, src_len):
            raise ValueError(
                f"Attention mask should be of size {(bsz, 1, tgt_len, src_len)}, but is {attention_mask.shape}"
            )
        attn_weights = attn_weights.view(bsz, self.num_heads, tgt_len, src_len) + attention_mask
        attn_weights = attn_weights.view(bsz * self.num_heads, tgt_len, src_len)

    attn_weights = ops.softmax(attn_weights, axis=-1)

    if output_attentions:
        # this operation is a bit akward, but it's required to
        # make sure that attn_weights keeps its gradient.
        # In order to do so, attn_weights have to reshaped
        # twice and have to be reused in the following
        attn_weights_reshaped = attn_weights.view(bsz, self.num_heads, tgt_len, src_len)
        attn_weights = attn_weights_reshaped.view(bsz * self.num_heads, tgt_len, src_len)
    else:
        attn_weights_reshaped = None

    attn_probs = ops.dropout(attn_weights, p=self.dropout, training=self.training)

    attn_output = ops.bmm(attn_probs, value_states)

    if attn_output.shape != (bsz * self.num_heads, tgt_len, self.head_dim):
        raise ValueError(
            f"`attn_output` should be of size {(bsz, self.num_heads, tgt_len, self.head_dim)}, but is"
            f" {attn_output.shape}"
        )

    attn_output = attn_output.view(bsz, self.num_heads, tgt_len, self.head_dim)
    attn_output = attn_output.swapaxes(1, 2)
    attn_output = attn_output.reshape(bsz, tgt_len, embed_dim)

    attn_output = self.out_proj(attn_output)

    return attn_output, attn_weights_reshaped

mindnlp.transformers.models.git.modeling_git.GitVisionEncoder

Bases: Module

Transformer encoder consisting of config.num_hidden_layers self attention layers. Each layer is a [GitVisionEncoderLayer].

PARAMETER DESCRIPTION
config

GitVisionConfig

TYPE: GitVisionConfig

Source code in mindnlp/transformers/models/git/modeling_git.py 
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
class GitVisionEncoder(nn.Module):
    """
    Transformer encoder consisting of `config.num_hidden_layers` self attention layers. Each layer is a
    [`GitVisionEncoderLayer`].

    Args:
        config: GitVisionConfig
    """

    def __init__(self, config: GitVisionConfig):
        super().__init__()
        self.config = config
        self.layers = nn.ModuleList([GitVisionEncoderLayer(config) for _ in range(config.num_hidden_layers)])
        self.gradient_checkpointing = False

    def forward(
        self,
        inputs_embeds,
        attention_mask: Optional[mindspore.Tensor] = None,
        causal_attention_mask: Optional[mindspore.Tensor] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
    ) -> Union[Tuple, BaseModelOutput]:
        r"""
        Args:
            inputs_embeds (`mindspore.Tensor` of shape `(batch_size, sequence_length, hidden_size)`):
                Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation.
                This is useful if you want more control over how to convert `input_ids` indices into associated vectors
                than the model's internal embedding lookup matrix.
            attention_mask (`mindspore.Tensor` of shape `(batch_size, sequence_length)`, *optional*):
                Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:

                - 1 for tokens that are **not masked**,
                - 0 for tokens that are **masked**.

                [What are attention masks?](../glossary#attention-mask)
            causal_attention_mask (`mindspore.Tensor` of shape `(batch_size, sequence_length)`, *optional*):
                Causal mask for the text model. Mask values selected in `[0, 1]`:

                - 1 for tokens that are **not masked**,
                - 0 for tokens that are **masked**.

                [What are attention masks?](../glossary#attention-mask)
            output_attentions (`bool`, *optional*):
                Whether or not to return the attentions tensors of all attention layers. See `attentions` under
                returned tensors for more detail.
            output_hidden_states (`bool`, *optional*):
                Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors
                for more detail.
            return_dict (`bool`, *optional*):
                Whether or not to return a [`~utils.ModelOutput`] instead of a plain tuple.
        """
        output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
        output_hidden_states = (
            output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
        )
        return_dict = return_dict if return_dict is not None else self.config.use_return_dict

        encoder_states = () if output_hidden_states else None
        all_attentions = () if output_attentions else None

        hidden_states = inputs_embeds
        for idx, encoder_layer in enumerate(self.layers):
            if output_hidden_states:
                encoder_states = encoder_states + (hidden_states,)
            if self.gradient_checkpointing and self.training:
                layer_outputs = self._gradient_checkpointing_func(
                    encoder_layer.__call__,
                    hidden_states,
                    attention_mask,
                    causal_attention_mask,
                    output_attentions,
                )
            else:
                layer_outputs = encoder_layer(
                    hidden_states,
                    attention_mask,
                    causal_attention_mask,
                    output_attentions=output_attentions,
                )

            hidden_states = layer_outputs[0]

            if output_attentions:
                all_attentions = all_attentions + (layer_outputs[1],)

        if output_hidden_states:
            encoder_states = encoder_states + (hidden_states,)

        if not return_dict:
            return tuple(v for v in [hidden_states, encoder_states, all_attentions] if v is not None)
        return BaseModelOutput(
            last_hidden_state=hidden_states, hidden_states=encoder_states, attentions=all_attentions
        )

mindnlp.transformers.models.git.modeling_git.GitVisionEncoder.forward(inputs_embeds, attention_mask=None, causal_attention_mask=None, output_attentions=None, output_hidden_states=None, return_dict=None)

PARAMETER DESCRIPTION
inputs_embeds

Optionally, instead of passing input_ids you can choose to directly pass an embedded representation. This is useful if you want more control over how to convert input_ids indices into associated vectors than the model's internal embedding lookup matrix.

TYPE: `mindspore.Tensor` of shape `(batch_size, sequence_length, hidden_size)`

attention_mask

Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:

  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.

What are attention masks?

TYPE: `mindspore.Tensor` of shape `(batch_size, sequence_length)`, *optional* DEFAULT: None

causal_attention_mask

Causal mask for the text model. Mask values selected in [0, 1]:

  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.

What are attention masks?

TYPE: `mindspore.Tensor` of shape `(batch_size, sequence_length)`, *optional* DEFAULT: None

output_attentions

Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.

TYPE: `bool`, *optional* DEFAULT: None

output_hidden_states

Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.

TYPE: `bool`, *optional* DEFAULT: None

return_dict

Whether or not to return a [~utils.ModelOutput] instead of a plain tuple.

TYPE: `bool`, *optional* DEFAULT: None

Source code in mindnlp/transformers/models/git/modeling_git.py 
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
def forward(
    self,
    inputs_embeds,
    attention_mask: Optional[mindspore.Tensor] = None,
    causal_attention_mask: Optional[mindspore.Tensor] = None,
    output_attentions: Optional[bool] = None,
    output_hidden_states: Optional[bool] = None,
    return_dict: Optional[bool] = None,
) -> Union[Tuple, BaseModelOutput]:
    r"""
    Args:
        inputs_embeds (`mindspore.Tensor` of shape `(batch_size, sequence_length, hidden_size)`):
            Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation.
            This is useful if you want more control over how to convert `input_ids` indices into associated vectors
            than the model's internal embedding lookup matrix.
        attention_mask (`mindspore.Tensor` of shape `(batch_size, sequence_length)`, *optional*):
            Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:

            - 1 for tokens that are **not masked**,
            - 0 for tokens that are **masked**.

            [What are attention masks?](../glossary#attention-mask)
        causal_attention_mask (`mindspore.Tensor` of shape `(batch_size, sequence_length)`, *optional*):
            Causal mask for the text model. Mask values selected in `[0, 1]`:

            - 1 for tokens that are **not masked**,
            - 0 for tokens that are **masked**.

            [What are attention masks?](../glossary#attention-mask)
        output_attentions (`bool`, *optional*):
            Whether or not to return the attentions tensors of all attention layers. See `attentions` under
            returned tensors for more detail.
        output_hidden_states (`bool`, *optional*):
            Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors
            for more detail.
        return_dict (`bool`, *optional*):
            Whether or not to return a [`~utils.ModelOutput`] instead of a plain tuple.
    """
    output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
    output_hidden_states = (
        output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
    )
    return_dict = return_dict if return_dict is not None else self.config.use_return_dict

    encoder_states = () if output_hidden_states else None
    all_attentions = () if output_attentions else None

    hidden_states = inputs_embeds
    for idx, encoder_layer in enumerate(self.layers):
        if output_hidden_states:
            encoder_states = encoder_states + (hidden_states,)
        if self.gradient_checkpointing and self.training:
            layer_outputs = self._gradient_checkpointing_func(
                encoder_layer.__call__,
                hidden_states,
                attention_mask,
                causal_attention_mask,
                output_attentions,
            )
        else:
            layer_outputs = encoder_layer(
                hidden_states,
                attention_mask,
                causal_attention_mask,
                output_attentions=output_attentions,
            )

        hidden_states = layer_outputs[0]

        if output_attentions:
            all_attentions = all_attentions + (layer_outputs[1],)

    if output_hidden_states:
        encoder_states = encoder_states + (hidden_states,)

    if not return_dict:
        return tuple(v for v in [hidden_states, encoder_states, all_attentions] if v is not None)
    return BaseModelOutput(
        last_hidden_state=hidden_states, hidden_states=encoder_states, attentions=all_attentions
    )

mindnlp.transformers.models.git.modeling_git.GitVisionEncoderLayer

Bases: Module

Source code in mindnlp/transformers/models/git/modeling_git.py 
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
class GitVisionEncoderLayer(nn.Module):
    def __init__(self, config: GitVisionConfig):
        super().__init__()
        self.embed_dim = config.hidden_size
        self.self_attn = GitVisionAttention(config)
        self.layer_norm1 = nn.LayerNorm([self.embed_dim], eps=config.layer_norm_eps)
        self.mlp = GitVisionMLP(config)
        self.layer_norm2 = nn.LayerNorm([self.embed_dim], eps=config.layer_norm_eps)

    def forward(
        self,
        hidden_states: mindspore.Tensor,
        attention_mask: mindspore.Tensor,
        causal_attention_mask: mindspore.Tensor,
        output_attentions: Optional[bool] = False,
    ) -> Tuple[mindspore.Tensor]:
        """
        Args:
            hidden_states (`mindspore.Tensor`): input to the layer of shape `(batch, seq_len, embed_dim)`
            attention_mask (`mindspore.Tensor`): attention mask of size
                `(batch, 1, tgt_len, src_len)` where padding elements are indicated by very large negative values.
                `(config.encoder_attention_heads,)`.
            output_attentions (`bool`, *optional*):
                Whether or not to return the attentions tensors of all attention layers. See `attentions` under
                returned tensors for more detail.
        """
        residual = hidden_states

        hidden_states = self.layer_norm1(hidden_states)
        hidden_states, attn_weights = self.self_attn(
            hidden_states=hidden_states,
            attention_mask=attention_mask,
            causal_attention_mask=causal_attention_mask,
            output_attentions=output_attentions,
        )
        hidden_states = residual + hidden_states

        residual = hidden_states
        hidden_states = self.layer_norm2(hidden_states)
        hidden_states = self.mlp(hidden_states)
        hidden_states = residual + hidden_states

        outputs = (hidden_states,)

        if output_attentions:
            outputs += (attn_weights,)

        return outputs

mindnlp.transformers.models.git.modeling_git.GitVisionEncoderLayer.forward(hidden_states, attention_mask, causal_attention_mask, output_attentions=False)

PARAMETER DESCRIPTION
hidden_states

input to the layer of shape (batch, seq_len, embed_dim)

TYPE: `mindspore.Tensor`

attention_mask

attention mask of size (batch, 1, tgt_len, src_len) where padding elements are indicated by very large negative values. (config.encoder_attention_heads,).

TYPE: `mindspore.Tensor`

output_attentions

Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.

TYPE: `bool`, *optional* DEFAULT: False

Source code in mindnlp/transformers/models/git/modeling_git.py 
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
def forward(
    self,
    hidden_states: mindspore.Tensor,
    attention_mask: mindspore.Tensor,
    causal_attention_mask: mindspore.Tensor,
    output_attentions: Optional[bool] = False,
) -> Tuple[mindspore.Tensor]:
    """
    Args:
        hidden_states (`mindspore.Tensor`): input to the layer of shape `(batch, seq_len, embed_dim)`
        attention_mask (`mindspore.Tensor`): attention mask of size
            `(batch, 1, tgt_len, src_len)` where padding elements are indicated by very large negative values.
            `(config.encoder_attention_heads,)`.
        output_attentions (`bool`, *optional*):
            Whether or not to return the attentions tensors of all attention layers. See `attentions` under
            returned tensors for more detail.
    """
    residual = hidden_states

    hidden_states = self.layer_norm1(hidden_states)
    hidden_states, attn_weights = self.self_attn(
        hidden_states=hidden_states,
        attention_mask=attention_mask,
        causal_attention_mask=causal_attention_mask,
        output_attentions=output_attentions,
    )
    hidden_states = residual + hidden_states

    residual = hidden_states
    hidden_states = self.layer_norm2(hidden_states)
    hidden_states = self.mlp(hidden_states)
    hidden_states = residual + hidden_states

    outputs = (hidden_states,)

    if output_attentions:
        outputs += (attn_weights,)

    return outputs

mindnlp.transformers.models.git.modeling_git.GitVisionModel

Bases: GitPreTrainedModel

Source code in mindnlp/transformers/models/git/modeling_git.py 
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
class GitVisionModel(GitPreTrainedModel):
    config_class = GitVisionConfig
    main_input_name = "pixel_values"

    # Copied from transformers.models.clip.modeling_clip.CLIPVisionModel.__init__ with CLIP->Git
    def __init__(self, config: GitVisionConfig):
        super().__init__(config)
        self.vision_model = GitVisionTransformer(config)
        # Initialize weights and apply final processing
        self.post_init()

    def get_input_embeddings(self) -> nn.Module:
        return self.vision_model.embeddings.patch_embedding

    def forward(
        self,
        pixel_values: Optional[mindspore.Tensor] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
    ) -> Union[Tuple, BaseModelOutput]:
        r"""
        Returns:
            `Union[Tuple, BaseModelOutput]`

        Example:
            ```python
            >>> from PIL import Image
            >>> import requests
            >>> from transformers import AutoProcessor, GitVisionModel
            ...
            >>> processor = AutoProcessor.from_pretrained("microsoft/git-base")
            >>> model = GitVisionModel.from_pretrained("microsoft/git-base")
            ...
            >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
            >>> image = Image.open(requests.get(url, stream=True).raw)
            ...
            >>> inputs = processor(images=image, return_tensors="pt")
            ...
            >>> outputs = model(**inputs)
            >>> last_hidden_state = outputs.last_hidden_state
            ```
        """
        return_dict = return_dict if return_dict is not None else self.config.use_return_dict

        return self.vision_model(
            pixel_values=pixel_values,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
        )

mindnlp.transformers.models.git.modeling_git.GitVisionModel.forward(pixel_values=None, output_attentions=None, output_hidden_states=None, return_dict=None)

RETURNS DESCRIPTION
Union[Tuple, BaseModelOutput]

Union[Tuple, BaseModelOutput]
Example 
>>> from PIL import Image
>>> import requests
>>> from transformers import AutoProcessor, GitVisionModel
...
>>> processor = AutoProcessor.from_pretrained("microsoft/git-base")
>>> model = GitVisionModel.from_pretrained("microsoft/git-base")
...
>>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
>>> image = Image.open(requests.get(url, stream=True).raw)
...
>>> inputs = processor(images=image, return_tensors="pt")
...
>>> outputs = model(**inputs)
>>> last_hidden_state = outputs.last_hidden_state
Source code in mindnlp/transformers/models/git/modeling_git.py 
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
def forward(
    self,
    pixel_values: Optional[mindspore.Tensor] = None,
    output_attentions: Optional[bool] = None,
    output_hidden_states: Optional[bool] = None,
    return_dict: Optional[bool] = None,
) -> Union[Tuple, BaseModelOutput]:
    r"""
    Returns:
        `Union[Tuple, BaseModelOutput]`

    Example:
        ```python
        >>> from PIL import Image
        >>> import requests
        >>> from transformers import AutoProcessor, GitVisionModel
        ...
        >>> processor = AutoProcessor.from_pretrained("microsoft/git-base")
        >>> model = GitVisionModel.from_pretrained("microsoft/git-base")
        ...
        >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
        >>> image = Image.open(requests.get(url, stream=True).raw)
        ...
        >>> inputs = processor(images=image, return_tensors="pt")
        ...
        >>> outputs = model(**inputs)
        >>> last_hidden_state = outputs.last_hidden_state
        ```
    """
    return_dict = return_dict if return_dict is not None else self.config.use_return_dict

    return self.vision_model(
        pixel_values=pixel_values,
        output_attentions=output_attentions,
        output_hidden_states=output_hidden_states,
        return_dict=return_dict,
    )

mindnlp.transformers.models.git.modeling_git.GitVisionModelOutput dataclass

Bases: ModelOutput

Base class for vision model's outputs that also contains image embeddings of the pooling of the last hidden states.

PARAMETER DESCRIPTION
image_embeds

The image embeddings obtained by applying the projection layer to the pooler_output.

TYPE: `mindspore.Tensor` of shape `(batch_size, output_dim)` *optional* returned when model is initialized with `with_projection=True` DEFAULT: None

last_hidden_state

Sequence of hidden-states at the output of the last layer of the model.

TYPE: `mindspore.Tensor` of shape `(batch_size, sequence_length, hidden_size)` DEFAULT: None

hidden_states
  • Tuple of mindspore.Tensor (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape (batch_size, sequence_length, hidden_size).
  • Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.

TYPE: `tuple(mindspore.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True` DEFAULT: None

attentions
  • Tuple of mindspore.Tensor (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).
  • Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

TYPE: `tuple(mindspore.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True` DEFAULT: None

Source code in mindnlp/transformers/models/git/modeling_git.py 
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
@dataclass
# Copied from transformers.models.clip.modeling_clip.CLIPVisionModelOutput with CLIP->Git
class GitVisionModelOutput(ModelOutput):
    """
    Base class for vision model's outputs that also contains image embeddings of the pooling of the last hidden states.

    Args:
        image_embeds (`mindspore.Tensor` of shape `(batch_size, output_dim)` *optional* returned when model is initialized with `with_projection=True`):
            The image embeddings obtained by applying the projection layer to the pooler_output.
        last_hidden_state (`mindspore.Tensor` of shape `(batch_size, sequence_length, hidden_size)`):
            Sequence of hidden-states at the output of the last layer of the model.
        hidden_states (`tuple(mindspore.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):

            - Tuple of `mindspore.Tensor` (one for the output of the embeddings, if the model has an embedding layer, +
            one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.
            - Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
        attentions (`tuple(mindspore.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):

            - Tuple of `mindspore.Tensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
            sequence_length)`.
            - Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
            heads.
    """

    image_embeds: Optional[mindspore.Tensor] = None
    last_hidden_state: mindspore.Tensor = None
    hidden_states: Optional[Tuple[mindspore.Tensor, ...]] = None
    attentions: Optional[Tuple[mindspore.Tensor, ...]] = None

mindnlp.transformers.models.git.modeling_git.GitVisionTransformer

Bases: Module

Source code in mindnlp/transformers/models/git/modeling_git.py 
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
class GitVisionTransformer(nn.Module):
    # Copied from transformers.models.clip.modeling_clip.CLIPVisionTransformer.__init__ with CLIPEncoder->GitVisionEncoder, CLIP->Git
    def __init__(self, config: GitVisionConfig):
        super().__init__()
        self.config = config
        embed_dim = config.hidden_size

        self.embeddings = GitVisionEmbeddings(config)
        self.pre_layrnorm = nn.LayerNorm([embed_dim], eps=config.layer_norm_eps)
        self.encoder = GitVisionEncoder(config)
        self.post_layernorm = nn.LayerNorm([embed_dim], eps=config.layer_norm_eps)

    def forward(
        self,
        pixel_values: Optional[mindspore.Tensor] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
    ) -> Union[Tuple, BaseModelOutput]:
        r"""

        Returns:
            `Union[Tuple, BaseModelOutput]`
        """
        output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
        output_hidden_states = (
            output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
        )
        return_dict = return_dict if return_dict is not None else self.config.use_return_dict

        if pixel_values is None:
            raise ValueError("You have to specify pixel_values")

        hidden_states = self.embeddings(pixel_values)
        hidden_states = self.pre_layrnorm(hidden_states)

        encoder_outputs = self.encoder(
            inputs_embeds=hidden_states,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
        )

        last_hidden_state = encoder_outputs[0]

        last_hidden_state = self.post_layernorm(last_hidden_state)

        if not return_dict:
            return (last_hidden_state,) + encoder_outputs[1:]

        return BaseModelOutput(
            last_hidden_state=last_hidden_state,
            hidden_states=encoder_outputs.hidden_states,
            attentions=encoder_outputs.attentions,
        )

mindnlp.transformers.models.git.modeling_git.GitVisionTransformer.forward(pixel_values=None, output_attentions=None, output_hidden_states=None, return_dict=None)

RETURNS DESCRIPTION
Union[Tuple, BaseModelOutput]

Union[Tuple, BaseModelOutput]
Source code in mindnlp/transformers/models/git/modeling_git.py 
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
def forward(
    self,
    pixel_values: Optional[mindspore.Tensor] = None,
    output_attentions: Optional[bool] = None,
    output_hidden_states: Optional[bool] = None,
    return_dict: Optional[bool] = None,
) -> Union[Tuple, BaseModelOutput]:
    r"""

    Returns:
        `Union[Tuple, BaseModelOutput]`
    """
    output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
    output_hidden_states = (
        output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
    )
    return_dict = return_dict if return_dict is not None else self.config.use_return_dict

    if pixel_values is None:
        raise ValueError("You have to specify pixel_values")

    hidden_states = self.embeddings(pixel_values)
    hidden_states = self.pre_layrnorm(hidden_states)

    encoder_outputs = self.encoder(
        inputs_embeds=hidden_states,
        output_attentions=output_attentions,
        output_hidden_states=output_hidden_states,
        return_dict=return_dict,
    )

    last_hidden_state = encoder_outputs[0]

    last_hidden_state = self.post_layernorm(last_hidden_state)

    if not return_dict:
        return (last_hidden_state,) + encoder_outputs[1:]

    return BaseModelOutput(
        last_hidden_state=last_hidden_state,
        hidden_states=encoder_outputs.hidden_states,
        attentions=encoder_outputs.attentions,
    )

mindnlp.transformers.models.git.processing_git

Image/Text processor class for GIT

mindnlp.transformers.models.git.processing_git.GitProcessor

Bases: ProcessorMixin

Constructs a GIT processor which wraps a CLIP image processor and a BERT tokenizer into a single processor.

[GitProcessor] offers all the functionalities of [CLIPImageProcessor] and [BertTokenizerFast]. See the [~GitProcessor.__call__] and [~GitProcessor.decode] for more information.

PARAMETER DESCRIPTION
image_processor

The image processor is a required input.

TYPE: [`AutoImageProcessor`]

tokenizer

The tokenizer is a required input.

TYPE: [`AutoTokenizer`]

Source code in mindnlp/transformers/models/git/processing_git.py 
 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
class GitProcessor(ProcessorMixin):
    r"""
    Constructs a GIT processor which wraps a CLIP image processor and a BERT tokenizer into a single processor.

    [`GitProcessor`] offers all the functionalities of [`CLIPImageProcessor`] and [`BertTokenizerFast`]. See the
    [`~GitProcessor.__call__`] and [`~GitProcessor.decode`] for more information.

    Args:
        image_processor ([`AutoImageProcessor`]):
            The image processor is a required input.
        tokenizer ([`AutoTokenizer`]):
            The tokenizer is a required input.
    """

    attributes = ["image_processor", "tokenizer"]
    image_processor_class = "AutoImageProcessor"
    tokenizer_class = "AutoTokenizer"

    def __init__(self, image_processor, tokenizer):
        super().__init__(image_processor, tokenizer)
        self.current_processor = self.image_processor

    def __call__(self, text=None, images=None, return_tensors=None, **kwargs):
        """
        Main method to prepare for the model one or several sequences(s) and image(s). This method forwards the `text`
        and `kwargs` arguments to BertTokenizerFast's [`~BertTokenizerFast.__call__`] if `text` is not `None` to encode
        the text. To prepare the image(s), this method forwards the `images` and `kwrags` arguments to
        CLIPImageProcessor's [`~CLIPImageProcessor.__call__`] if `images` is not `None`. Please refer to the doctsring
        of the above two methods for more information.

        Args:
            text (`str`, `List[str]`, `List[List[str]]`):
                The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings
                (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set
                `is_split_into_words=True` (to lift the ambiguity with a batch of sequences).
            images (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `List[PIL.Image.Image]`, `List[np.ndarray]`, `List[torch.Tensor]`):
                The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch
                tensor. Both channels-first and channels-last formats are supported.

            return_tensors (`str` or [`~utils.TensorType`], *optional*):
                If set, will return tensors of a particular framework. Acceptable values are:

                - `'tf'`: Return TensorFlow `tf.constant` objects.
                - `'pt'`: Return PyTorch `torch.Tensor` objects.
                - `'np'`: Return NumPy `np.ndarray` objects.
                - `'jax'`: Return JAX `jnp.ndarray` objects.

        Returns:
            [`BatchEncoding`]:
                A [`BatchEncoding`] with the following fields:

                - **input_ids** -- List of token ids to be fed to a model. Returned when `text` is not `None`.
                - **attention_mask** -- List of indices specifying which tokens should be attended to by the model (when
                `return_attention_mask=True` or if *"attention_mask"* is in `self.model_input_names` and if `text` is not
                `None`).
                - **pixel_values** -- Pixel values to be fed to a model. Returned when `images` is not `None`.
        """
        tokenizer_kwargs, image_processor_kwargs = {}, {}
        if kwargs:
            tokenizer_kwargs = {k: v for k, v in kwargs.items() if k not in self.image_processor._valid_processor_keys}
            image_processor_kwargs = {
                k: v for k, v in kwargs.items() if k in self.image_processor._valid_processor_keys
            }

        if text is None and images is None:
            raise ValueError("You have to specify either text or images. Both cannot be none.")

        if text is not None:
            encoding = self.tokenizer(text, return_tensors=return_tensors, **tokenizer_kwargs)

        if images is not None:
            image_features = self.image_processor(images, return_tensors=return_tensors, **image_processor_kwargs)

        if text is not None and images is not None:
            encoding["pixel_values"] = image_features.pixel_values
            return encoding
        elif text is not None:
            return encoding
        else:
            return BatchEncoding(data={**image_features}, tensor_type=return_tensors)

    def batch_decode(self, *args, **kwargs):
        """
        This method forwards all its arguments to BertTokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please
        refer to the docstring of this method for more information.
        """
        return self.tokenizer.batch_decode(*args, **kwargs)

    def decode(self, *args, **kwargs):
        """
        This method forwards all its arguments to BertTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to
        the docstring of this method for more information.
        """
        return self.tokenizer.decode(*args, **kwargs)

    @property
    def model_input_names(self):
        return ["input_ids", "attention_mask", "pixel_values"]

mindnlp.transformers.models.git.processing_git.GitProcessor.__call__(text=None, images=None, return_tensors=None, **kwargs)

Main method to prepare for the model one or several sequences(s) and image(s). This method forwards the text and kwargs arguments to BertTokenizerFast's [~BertTokenizerFast.__call__] if text is not None to encode the text. To prepare the image(s), this method forwards the images and kwrags arguments to CLIPImageProcessor's [~CLIPImageProcessor.__call__] if images is not None. Please refer to the doctsring of the above two methods for more information.

PARAMETER DESCRIPTION
text

The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set is_split_into_words=True (to lift the ambiguity with a batch of sequences).

TYPE: `str`, `List[str]`, `List[List[str]]` DEFAULT: None

images

The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch tensor. Both channels-first and channels-last formats are supported.

TYPE: `PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `List[PIL.Image.Image]`, `List[np.ndarray]`, `List[torch.Tensor]` DEFAULT: None

return_tensors

If set, will return tensors of a particular framework. Acceptable values are:

  • 'tf': Return TensorFlow tf.constant objects.
  • 'pt': Return PyTorch torch.Tensor objects.
  • 'np': Return NumPy np.ndarray objects.
  • 'jax': Return JAX jnp.ndarray objects.

TYPE: `str` or [`~utils.TensorType`], *optional* DEFAULT: None

RETURNS DESCRIPTION

[BatchEncoding]: A [BatchEncoding] with the following fields:

  • input_ids -- List of token ids to be fed to a model. Returned when text is not None.
  • attention_mask -- List of indices specifying which tokens should be attended to by the model (when return_attention_mask=True or if "attention_mask" is in self.model_input_names and if text is not None).
  • pixel_values -- Pixel values to be fed to a model. Returned when images is not None.
Source code in mindnlp/transformers/models/git/processing_git.py 
 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
def __call__(self, text=None, images=None, return_tensors=None, **kwargs):
    """
    Main method to prepare for the model one or several sequences(s) and image(s). This method forwards the `text`
    and `kwargs` arguments to BertTokenizerFast's [`~BertTokenizerFast.__call__`] if `text` is not `None` to encode
    the text. To prepare the image(s), this method forwards the `images` and `kwrags` arguments to
    CLIPImageProcessor's [`~CLIPImageProcessor.__call__`] if `images` is not `None`. Please refer to the doctsring
    of the above two methods for more information.

    Args:
        text (`str`, `List[str]`, `List[List[str]]`):
            The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings
            (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set
            `is_split_into_words=True` (to lift the ambiguity with a batch of sequences).
        images (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `List[PIL.Image.Image]`, `List[np.ndarray]`, `List[torch.Tensor]`):
            The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch
            tensor. Both channels-first and channels-last formats are supported.

        return_tensors (`str` or [`~utils.TensorType`], *optional*):
            If set, will return tensors of a particular framework. Acceptable values are:

            - `'tf'`: Return TensorFlow `tf.constant` objects.
            - `'pt'`: Return PyTorch `torch.Tensor` objects.
            - `'np'`: Return NumPy `np.ndarray` objects.
            - `'jax'`: Return JAX `jnp.ndarray` objects.

    Returns:
        [`BatchEncoding`]:
            A [`BatchEncoding`] with the following fields:

            - **input_ids** -- List of token ids to be fed to a model. Returned when `text` is not `None`.
            - **attention_mask** -- List of indices specifying which tokens should be attended to by the model (when
            `return_attention_mask=True` or if *"attention_mask"* is in `self.model_input_names` and if `text` is not
            `None`).
            - **pixel_values** -- Pixel values to be fed to a model. Returned when `images` is not `None`.
    """
    tokenizer_kwargs, image_processor_kwargs = {}, {}
    if kwargs:
        tokenizer_kwargs = {k: v for k, v in kwargs.items() if k not in self.image_processor._valid_processor_keys}
        image_processor_kwargs = {
            k: v for k, v in kwargs.items() if k in self.image_processor._valid_processor_keys
        }

    if text is None and images is None:
        raise ValueError("You have to specify either text or images. Both cannot be none.")

    if text is not None:
        encoding = self.tokenizer(text, return_tensors=return_tensors, **tokenizer_kwargs)

    if images is not None:
        image_features = self.image_processor(images, return_tensors=return_tensors, **image_processor_kwargs)

    if text is not None and images is not None:
        encoding["pixel_values"] = image_features.pixel_values
        return encoding
    elif text is not None:
        return encoding
    else:
        return BatchEncoding(data={**image_features}, tensor_type=return_tensors)

mindnlp.transformers.models.git.processing_git.GitProcessor.batch_decode(*args, **kwargs)

This method forwards all its arguments to BertTokenizerFast's [~PreTrainedTokenizer.batch_decode]. Please refer to the docstring of this method for more information.

Source code in mindnlp/transformers/models/git/processing_git.py 
104
105
106
107
108
109
def batch_decode(self, *args, **kwargs):
    """
    This method forwards all its arguments to BertTokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please
    refer to the docstring of this method for more information.
    """
    return self.tokenizer.batch_decode(*args, **kwargs)

mindnlp.transformers.models.git.processing_git.GitProcessor.decode(*args, **kwargs)

This method forwards all its arguments to BertTokenizerFast's [~PreTrainedTokenizer.decode]. Please refer to the docstring of this method for more information.

Source code in mindnlp/transformers/models/git/processing_git.py 
111
112
113
114
115
116
def decode(self, *args, **kwargs):
    """
    This method forwards all its arguments to BertTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to
    the docstring of this method for more information.
    """
    return self.tokenizer.decode(*args, **kwargs)