Instructblip Flan T5 Xxl 8bit

🚀 BLIP-2, Flan T5-xxl, pre-trained only

The BLIP-2 model leverages the Flan T5-xxl large language model. It can be used for tasks like image captioning, visual question answering, etc.

🚀 Quick Start

You can use the raw model for conditional text generation given an image and optional text. Check the model hub to find fine - tuned versions for tasks that interest you.

✨ Features

• Multi - task Capability: Can be used for image captioning, visual question answering (VQA), and chat - like conversations.
• Bridge between Image and Language: The Querying Transformer (Q - Former) bridges the gap between the image encoder and the large language model.

📚 Documentation

Model description

BLIP-2 consists of 3 models: a CLIP-like image encoder, a Querying Transformer (Q-Former) and a large language model.

The authors initialize the weights of the image encoder and large language model from pre - trained checkpoints and keep them frozen while training the Querying Transformer. The Querying Transformer, a BERT - like Transformer encoder, maps a set of "query tokens" to query embeddings, which bridge the gap between the embedding space of the image encoder and the large language model.

The goal for the model is simply to predict the next text token, given the query embeddings and the previous text.

This allows the model to be used for tasks like:

• image captioning
• visual question answering (VQA)
• chat - like conversations by feeding the image and the previous conversation as prompt to the model

Direct Use and Downstream Use

You can use the raw model for conditional text generation given an image and optional text. See the model hub to look for fine - tuned versions on a task that interests you.

Bias, Risks, Limitations, and Ethical Considerations

BLIP2 - FlanT5 uses off - the - shelf Flan - T5 as the language model. It inherits the same risks and limitations from Flan - T5:

Language models, including Flan - T5, can potentially be used for language generation in a harmful way, according to Rae et al. (2021). Flan - T5 should not be used directly in any application, without a prior assessment of safety and fairness concerns specific to the application.

BLIP2 is fine - tuned on image - text datasets (e.g. [LAION](https://laion.ai/blog/laion - 400 - open - dataset/)) collected from the internet. As a result, the model itself is potentially vulnerable to generating equivalently inappropriate content or replicating inherent biases in the underlying data.

BLIP2 has not been tested in real - world applications. It should not be directly deployed in any applications. Researchers should first carefully assess the safety and fairness of the model in relation to the specific context they’re being deployed within.

💻 Usage Examples

Basic Usage

For code examples, we refer to the documentation, or refer to the snippets below depending on your usecase:

Running the model on CPU

import requests
from PIL import Image
from transformers import BlipProcessor, Blip2ForConditionalGeneration

processor = BlipProcessor.from_pretrained("Salesforce/blip2-flan-t5-xxl")
model = Blip2ForConditionalGeneration.from_pretrained("Salesforce/blip2-flan-t5-xxl")

img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg' 
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')

question = "how many dogs are in the picture?"
inputs = processor(raw_image, question, return_tensors="pt")

out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))

Advanced Usage

Running the model on GPU

In full precision

# pip install accelerate
import requests
from PIL import Image
from transformers import Blip2Processor, Blip2ForConditionalGeneration

processor = Blip2Processor.from_pretrained("Salesforce/blip2-flan-t5-xxl")
model = Blip2ForConditionalGeneration.from_pretrained("Salesforce/blip2-flan-t5-xxl", device_map="auto")

img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg' 
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')

question = "how many dogs are in the picture?"
inputs = processor(raw_image, question, return_tensors="pt").to("cuda")

out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))

In half precision (float16)

# pip install accelerate
import torch
import requests
from PIL import Image
from transformers import Blip2Processor, Blip2ForConditionalGeneration

processor = Blip2Processor.from_pretrained("Salesforce/blip2-flan-t5-xxl")
model = Blip2ForConditionalGeneration.from_pretrained("Salesforce/blip2-flan-t5-xxl", torch_dtype=torch.float16, device_map="auto")

img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg' 
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')

question = "how many dogs are in the picture?"
inputs = processor(raw_image, question, return_tensors="pt").to("cuda", torch.float16)

out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))

In 8 - bit precision (int8)

# pip install accelerate bitsandbytes
import torch
import requests
from PIL import Image
from transformers import Blip2Processor, Blip2ForConditionalGeneration

processor = Blip2Processor.from_pretrained("Salesforce/blip2-flan-t5-xxl")
model = Blip2ForConditionalGeneration.from_pretrained("Salesforce/blip2-flan-t5-xxl", load_in_8bit=True, device_map="auto")

img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg' 
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')

question = "how many dogs are in the picture?"
inputs = processor(raw_image, question, return_tensors="pt").to("cuda", torch.float16)

out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))

📄 License

This model is released under the MIT license.