File size: 5,650 Bytes
8fbc209 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 |
# coding=utf-8
# Copyright 2023 Microsoft Research & University of Wisconsin-Madison and the HuggingFace Inc. team. All rights reserved.
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
""" Llava model configuration"""
# from ...configuration_utils import PretrainedConfig
# from ...utils import logging
# from ..auto import CONFIG_MAPPING
from transformers.configuration_utils import PretrainedConfig
from transformers.utils import logging
from transformers.models.auto import CONFIG_MAPPING
logger = logging.get_logger(__name__)
LLAVA_PRETRAINED_CONFIG_ARCHIVE_MAP = {
"llava-hf/llava-v1.5-7b": "https://huggingface.co/llava-hf/llava-v1.5-7b/resolve/main/config.json",
}
class LlavaConfig(PretrainedConfig):
r"""
This is the configuration class to store the configuration of a [`LlavaForConditionalGeneration`]. It is used to instantiate an
Llava 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 Llava-9B.
e.g. [llava-hf/llava-9b](https://huggingface.co/llava-hf/llava-9b)
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 (`LlavaVisionConfig`, *optional*):
Custom vision config or dict
text_config (`Union[AutoConfig, dict]`, *optional*):
The config object of the text backbone. Can be any of `LlamaConfig` or `MistralConfig`.
ignore_index (`int`, *optional*, defaults to -100):
The ignore index for the loss function.
image_token_index (`int`, *optional*, defaults to 32000):
The image token index to encode the image prompt.
projector_hidden_act (`str`, *optional*, defaults to `"gelu"`):
The activation function used by the multimodal projector.
vision_feature_select_strategy (`str`, *optional*, defaults to `"default"`):
The feature selection strategy used to select the vision feature from the CLIP backbone.
vision_feature_layer (`int`, *optional*, defaults to -2):
The index of the layer to select the vision feature.
vocab_size (`int`, *optional*, defaults to 32000):
Vocabulary size of the Llava model. Defines the number of different tokens that can be represented by the
`inputs_ids` passed when calling [`~LlavaForConditionalGeneration`]
Example:
```python
>>> from transformers import LlavaForConditionalGeneration, LlavaConfig, CLIPVisionConfig, LlamaConfig
>>> # Initializing a CLIP-vision config
>>> vision_config = CLIPVisionConfig()
>>> # Initializing a Llama config
>>> text_config = LlamaConfig()
>>> # Initializing a Llava llava-1.5-7b style configuration
>>> configuration = LlavaConfig(vision_config, text_config)
>>> # Initializing a model from the llava-1.5-7b style configuration
>>> model = LlavaForConditionalGeneration(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
```"""
model_type = "llava"
is_composition = False
def __init__(
self,
vision_config=None,
text_config=None,
ignore_index=-100,
image_token_index=32000,
projector_hidden_act="gelu",
vision_feature_select_strategy="default",
vision_feature_layer=-2,
vocab_size=32000,
**kwargs,
):
self.ignore_index = ignore_index
self.image_token_index = image_token_index
self.projector_hidden_act = projector_hidden_act
self.vision_feature_select_strategy = vision_feature_select_strategy
self.vision_feature_layer = vision_feature_layer
self.vocab_size = vocab_size
self.vision_config = vision_config
if isinstance(self.vision_config, dict):
vision_config["model_type"] = (
vision_config["model_type"] if "model_type" in vision_config else "clip_vision_model"
)
self.vision_config = CONFIG_MAPPING[vision_config["model_type"]](**vision_config)
elif vision_config is None:
self.vision_config = CONFIG_MAPPING["clip_vision_model"](
intermediate_size=4096,
hidden_size=1024,
patch_size=14,
image_size=336,
num_hidden_layers=24,
num_attention_heads=16,
vocab_size=32000,
projection_dim=768,
)
self.vocab_size = self.vocab_size
self.text_config = text_config
if isinstance(self.text_config, dict):
text_config["model_type"] = text_config["model_type"] if "model_type" in text_config else "llama"
self.text_config = CONFIG_MAPPING[text_config["model_type"]](**text_config)
self.vocab_size = self.text_config.vocab_size
elif text_config is None:
self.text_config = CONFIG_MAPPING["llama"]()
super().__init__(**kwargs)
|