VipLlava
Overview
The VipLlava model was proposed in Making Large Multimodal Models Understand Arbitrary Visual Prompts by Mu Cai, Haotian Liu, Siva Karthik Mustikovela, Gregory P. Meyer, Yuning Chai, Dennis Park, Yong Jae Lee.
VipLlava enhances the training protocol of Llava by marking images and interact with the model using natural cues like a βred bounding boxβ or βpointed arrowβ during training.
The abstract from the paper is the following:
While existing large vision-language multimodal models focus on whole image understanding, there is a prominent gap in achieving region-specific comprehension. Current approaches that use textual coordinates or spatial encodings often fail to provide a user-friendly interface for visual prompting. To address this challenge, we introduce a novel multimodal model capable of decoding arbitrary visual prompts. This allows users to intuitively mark images and interact with the model using natural cues like a βred bounding boxβ or βpointed arrowβ. Our simple design directly overlays visual markers onto the RGB image, eliminating the need for complex region encodings, yet achieves state-of-the-art performance on region-understanding tasks like Visual7W, PointQA, and Visual Commonsense Reasoning benchmark. Furthermore, we present ViP-Bench, a comprehensive benchmark to assess the capability of models in understanding visual prompts across multiple dimensions, enabling future research in this domain. Code, data, and model are publicly available.
The original code can be found here.
This model was contributed by Younes Belkada
Usage tips:
The architecture is similar than llava architecture except that the multi-modal projector takes a set of concatenated vision hidden states and has an additional layernorm layer on that module.
We advise users to use
padding_side="left"
when computing batched generation as it leads to more accurate results. Simply make sure to callprocessor.tokenizer.padding_side = "left"
before generating.Note the model has not been explicitly trained to process multiple images in the same prompt, although this is technically possible, you may experience inaccurate results.
For better results, we recommend users to use the processorβs
apply_chat_template()
method to format your prompt correctly. For that you need to construct a conversation history, passing in a plain string will not format your prompt. Each message in the conversation history for chat templates is a dictionary with keys βroleβ and βcontentβ. The βcontentβ should be a list of dictionaries, for βtextβ and βimageβ modalities, as follows:
from transformers import AutoProcessor
processor = AutoProcessor.from_pretrained("llava-hf/vip-llava-7b-hf")
conversation = [
{
"role": "user",
"content": [
{"type": "image"},
{"type": "text", "text": "Whatβs shown in this image?"},
,
},
{
"role": "assistant",
"content": [{"type": "text", "text": "This image shows a red stop sign."},]
},
{
"role": "user",
"content": [
{"type": "text", "text": "Describe the image in more details."},
],
},
]
text_prompt = processor.apply_chat_template(conversation, add_generation_prompt=True)
# Note that the template simply formats your prompt, you still have to tokenize it and obtain pixel values for your images
print(text_prompt)
>>> "###Human: <image>\nWhatβs shown in this image?###Assistant: This image shows a red stop sign.###Human: Describe the image in more details.###Assistant:"
- If you want to construct a chat prompt yourself, below is a list of prompt formats accepted by VipLLaVa checkpoints:
A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.###Human: <image>\n<prompt>###Assistant:
For multiple turns conversation:
A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.###Human: <image>\n<prompt1>###Assistant: <answer1>###Human: <prompt2>###Assistant:
VipLlavaConfig
class transformers.VipLlavaConfig
< source >( vision_config = None text_config = None ignore_index = -100 image_token_index = 32000 projector_hidden_act = 'gelu' projector_layernorm_eps = 1e-05 vision_feature_layers = [-2, -5, -8, -11, 6] **kwargs )
Parameters
- 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 ofLlamaConfig
orMistralConfig
. - 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.
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.
Configuration objects inherit from PretrainedConfig and can be used to control the model outputs. Read the documentation from PretrainedConfig for more information.
Example:
>>> 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
VipLlavaForConditionalGeneration
class transformers.VipLlavaForConditionalGeneration
< source >( config: VipLlavaConfig )
Parameters
- config (VipLlavaConfig or
VipLlavaVisionConfig
) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.
The VIPLLAVA model which consists of a vision backbone and a language model. This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)
This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.
forward
< source >( input_ids: LongTensor = None pixel_values: FloatTensor = None attention_mask: Optional = None position_ids: Optional = None past_key_values: Optional = None inputs_embeds: Optional = None vision_feature_layers: Optional = None labels: Optional = None use_cache: Optional = None output_attentions: Optional = None output_hidden_states: Optional = None return_dict: Optional = None ) β transformers.models.vipllava.modeling_vipllava.VipLlavaCausalLMOutputWithPast
or tuple(torch.FloatTensor)
Parameters
- input_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
- pixel_values (
torch.FloatTensor
of shape(batch_size, num_channels, image_size, image_size)) -- The tensors corresponding to the input images. Pixel values can be obtained using [AutoImageProcessor](/docs/transformers/v4.43.4/en/model_doc/auto#transformers.AutoImageProcessor). See [CLIPImageProcessor.__call__()](/docs/transformers/v4.43.4/en/model_doc/videomae#transformers.VideoMAEFeatureExtractor.__call__) for details ([]
LlavaProcessor`] uses CLIPImageProcessor for processing images). - attention_mask (
torch.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.
Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.
If
past_key_values
is used, optionally only the lastdecoder_input_ids
have to be input (seepast_key_values
).If you want to change padding behavior, you should read
modeling_opt._prepare_decoder_attention_mask
and modify to your needs. See diagram 1 in the paper for more information on the default strategy.- 1 indicates the head is not masked,
- 0 indicates the head is masked.
- position_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range[0, config.n_positions - 1]
. What are position IDs? - past_key_values (
tuple(tuple(torch.FloatTensor))
, optional, returned whenuse_cache=True
is passed or whenconfig.use_cache=True
) — Tuple oftuple(torch.FloatTensor)
of lengthconfig.n_layers
, with each tuple having 2 tensors of shape(batch_size, num_heads, sequence_length, embed_size_per_head)
) and 2 additional tensors of shape(batch_size, num_heads, encoder_sequence_length, embed_size_per_head)
.Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention blocks) that can be used (see
past_key_values
input) to speed up sequential decoding.If
past_key_values
are used, the user can optionally input only the lastdecoder_input_ids
(those that don’t have their past key value states given to this model) of shape(batch_size, 1)
instead of alldecoder_input_ids
of shape(batch_size, sequence_length)
. - inputs_embeds (
torch.FloatTensor
of shape(batch_size, sequence_length, hidden_size)
, optional) — Optionally, instead of passinginput_ids
you can choose to directly pass an embedded representation. This is useful if you want more control over how to convertinput_ids
indices into associated vectors than the model’s internal embedding lookup matrix. - use_cache (
bool
, optional) — If set toTrue
,past_key_values
key value states are returned and can be used to speed up decoding (seepast_key_values
). - output_attentions (
bool
, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. - return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple.Args — labels (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional): Labels for computing the masked language modeling loss. Indices should either be in[0, ..., config.vocab_size]
or -100 (seeinput_ids
docstring). Tokens with indices set to-100
are ignored (masked), the loss is only computed for the tokens with labels in[0, ..., config.vocab_size]
.
Returns
transformers.models.vipllava.modeling_vipllava.VipLlavaCausalLMOutputWithPast
or tuple(torch.FloatTensor)
A transformers.models.vipllava.modeling_vipllava.VipLlavaCausalLMOutputWithPast
or a tuple of
torch.FloatTensor
(if return_dict=False
is passed or when config.return_dict=False
) comprising various
elements depending on the configuration (VipLlavaConfig) and inputs.
-
loss (
torch.FloatTensor
of shape(1,)
, optional, returned whenlabels
is provided) β Language modeling loss (for next-token prediction). -
logits (
torch.FloatTensor
of shape(batch_size, sequence_length, config.vocab_size)
) β Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax). -
past_key_values (
tuple(tuple(torch.FloatTensor))
, optional, returned whenuse_cache=True
is passed or whenconfig.use_cache=True
) β Tuple oftuple(torch.FloatTensor)
of lengthconfig.n_layers
, with each tuple having 2 tensors of shape(batch_size, num_heads, sequence_length, embed_size_per_head)
)Contains pre-computed hidden-states (key and values in the self-attention blocks) that can be used (see
past_key_values
input) to speed up sequential decoding. -
hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is passed or whenconfig.output_hidden_states=True
) β Tuple oftorch.FloatTensor
(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(torch.FloatTensor)
, optional, returned whenoutput_attentions=True
is passed or whenconfig.output_attentions=True
) β Tuple oftorch.FloatTensor
(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_hidden_states (
tuple(torch.FloatTensor)
, optional) β Tuple oftorch.FloatTensor
(one for the output of the image embeddings,(batch_size, num_images, sequence_length, hidden_size)
.image_hidden_states of the model produced by the vision encoder, and optionally by the perceiver
The VipLlavaForConditionalGeneration forward method, overrides the __call__
special method.
Although the recipe for forward pass needs to be defined within this function, one should call the Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while
the latter silently ignores them.
Example:
>>> import torch
>>> from PIL import Image
>>> import requests
>>> from transformers import AutoProcessor, VipLlavaForConditionalGeneration
>>> model = VipLlavaForConditionalGeneration.from_pretrained("llava-hf/vip-llava-7b-hf", device_map="auto", torch_dtype=torch.float16)
>>> processor = AutoProcessor.from_pretrained("llava-hf/vip-llava-7b-hf")
>>> prompt = "A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.###Human: <image>\n{}###Assistant:"
>>> question = "Can you please describe this image?"
>>> prompt = prompt.format(question)
>>> url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/compel-neg.png"
>>> image = Image.open(requests.get(url, stream=True).raw)
>>> inputs = processor(text=text, images=image, return_tensors="pt").to(0, torch.float16)
>>> # Generate
>>> generate_ids = model.generate(**inputs, max_new_tokens=20)
>>> processor.decode(generate_ids[0][len(inputs["input_ids"][0]):], skip_special_tokens=True)
The image features a brown and white cat sitting on a green surface, with a red ball in its