145 lines
5.7 KiB
Python
145 lines
5.7 KiB
Python
# 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.
|
|
""" VipLlava model configuration"""
|
|
|
|
import warnings
|
|
|
|
from ...configuration_utils import PretrainedConfig
|
|
from ...utils import logging
|
|
from ..auto import CONFIG_MAPPING
|
|
|
|
|
|
logger = logging.get_logger(__name__)
|
|
|
|
|
|
from ..deprecated._archive_maps import VIPLLAVA_PRETRAINED_CONFIG_ARCHIVE_MAP # noqa: F401, E402
|
|
|
|
|
|
class VipLlavaConfig(PretrainedConfig):
|
|
r"""
|
|
This is the configuration class to store the configuration of a [`VipLlavaForConditionalGeneration`]. It is used to instantiate an
|
|
VipLlava 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 VipLlava-9B.
|
|
|
|
e.g. [ybelkada/vip-llava-7b-hf](https://huggingface.co/ybelkada/vip-llava-7b-hf)
|
|
|
|
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 (`VipLlavaVisionConfig`, *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.
|
|
projector_layernorm_eps (`float`, *optional*, defaults to 1e-05):
|
|
The layer norm epsilon of the projector layernorm
|
|
vision_feature_layers (`List[int]`, *optional*, defaults to `[-2, -5, -8, -11, 6]`):
|
|
The list of layers to select the vision features from.
|
|
|
|
Example:
|
|
|
|
```python
|
|
>>> from transformers import VipLlavaForConditionalGeneration, VipLlavaConfig, CLIPVisionConfig, LlamaConfig
|
|
|
|
>>> # Initializing a CLIP-vision config
|
|
>>> vision_config = CLIPVisionConfig()
|
|
|
|
>>> # Initializing a Llama config
|
|
>>> text_config = LlamaConfig()
|
|
|
|
>>> # Initializing a VipLlava vipllava-7b style configuration
|
|
>>> configuration = VipLlavaConfig(vision_config, text_config)
|
|
|
|
>>> # Initializing a model from the vipllava-7b style configuration
|
|
>>> model = VipLlavaForConditionalGeneration(configuration)
|
|
|
|
>>> # Accessing the model configuration
|
|
>>> configuration = model.config
|
|
```"""
|
|
|
|
model_type = "vipllava"
|
|
is_composition = False
|
|
|
|
def __init__(
|
|
self,
|
|
vision_config=None,
|
|
text_config=None,
|
|
ignore_index=-100,
|
|
image_token_index=32000,
|
|
projector_hidden_act="gelu",
|
|
projector_layernorm_eps=1e-5,
|
|
vision_feature_layers=[-2, -5, -8, -11, 6],
|
|
**kwargs,
|
|
):
|
|
self.ignore_index = ignore_index
|
|
self.image_token_index = image_token_index
|
|
self.projector_hidden_act = projector_hidden_act
|
|
self.projector_layernorm_eps = projector_layernorm_eps
|
|
self.vision_feature_layers = vision_feature_layers
|
|
|
|
if "vocab_size" in kwargs:
|
|
warnings.warn(
|
|
"The `vocab_size` argument is deprecated and will be removed in v4.42, since it can be inferred from the `text_config`. Passing this argument has no effect",
|
|
FutureWarning,
|
|
)
|
|
|
|
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,
|
|
)
|
|
|
|
if isinstance(text_config, dict):
|
|
text_config["model_type"] = text_config["model_type"] if "model_type" in text_config else "llama"
|
|
text_config = CONFIG_MAPPING[text_config["model_type"]](**text_config)
|
|
elif text_config is None:
|
|
text_config = CONFIG_MAPPING["llama"]()
|
|
|
|
self.text_config = text_config
|
|
self._vocab_size = self.text_config.vocab_size
|
|
|
|
super().__init__(**kwargs)
|
|
|
|
@property
|
|
def vocab_size(self):
|
|
warnings.warn(
|
|
"The `vocab_size` attribute is deprecated and will be removed in v4.42, Please use `text_config.vocab_size` instead.",
|
|
FutureWarning,
|
|
)
|
|
return self._vocab_size
|
|
|
|
def to_dict(self):
|
|
output = super().to_dict()
|
|
output.pop("_vocab_size", None)
|
|
return output
|