Idefics 80b

🚀 IDEFICS

IDEFICS (Image-aware Decoder Enhanced à la Flamingo with Interleaved Cross-attentionS) is an open - access multimodal model. It accepts sequences of image and text inputs and generates text outputs, similar to GPT - 4. Built on publicly available data and models, it performs well on various image - text benchmarks.

How do I pronounce the model's name? Watch a Youtube tutorial

IDEFICS is an open - access reproduction of Flamingo, a closed - source visual language model developed by Deepmind. Like GPT - 4, this multimodal model accepts arbitrary sequences of image and text inputs and produces text outputs. IDEFICS is built solely on publicly available data and models.

The model can answer questions about images, describe visual contents, create stories grounded on multiple images, or simply behave as a pure language model without visual inputs.

IDEFICS is on par with the original closed - source model on various image - text benchmarks, including visual question answering (open - ended and multiple choice), image captioning, and image classification when evaluated with in - context few - shot learning. It comes into two variants: a large 80 billion parameters version and a 9 billion parameters version.

We also fine - tune the base models on a mixture of supervised and instruction fine - tuning datasets, which boosts the downstream performance while making the models more usable in conversational settings: idefics - 80b - instruct and idefics - 9b - instruct. As they reach higher performance, we recommend using these instructed versions first.

Learn more about some of the technical challenges we encountered while training IDEFICS here.

Try out the demo!

✨ Features

• Multimodal Input: Accepts arbitrary sequences of image and text inputs and generates text outputs.
• Strong Few - Shot Learning: Shows strong in - context few - shot learning capabilities and performs well on various image - text benchmarks.
• Two Variants: Available in 80 - billion and 9 - billion parameter versions.
• Instruction - Tuned: Instruction - fine - tuned models have better downstream performance and are more suitable for conversations.

📚 Documentation

Model Details

IDEFICS is a large multimodal English model that takes sequences of interleaved images and texts as inputs and generates text outputs. The model shows strong in - context few - shot learning capabilities and is on par with the closed - source model. This makes IDEFICS a robust starting point to fine - tune multimodal models on custom data.

IDEFICS is built on top of two unimodal open - access pre - trained models to connect the two modalities. Newly initialized parameters in the form of Transformer blocks bridge the gap between the vision encoder and the language model. The model is trained on a mixture of image - text pairs and unstructured multimodal web documents.

IDEFICS - instruct is the model obtained by further training IDEFICS on Supervised Fine - Tuning and Instruction Fine - Tuning datasets. This improves downstream performance significantly (making idefics - 9b - instruct a very strong model at its 9 billion scale), while making the model more suitable to converse with.

Uses

The model can be used to perform inference on multimodal (image + text) tasks in which the input is composed of a text query/instruction along with one or multiple images. This model does not support image generation.

It is possible to fine - tune the base model on custom data for a specific use - case. We note that the instruction - fine - tuned models are significantly better at following instructions from users and thus should be prefered when using the models out - of - the - box.

The following screenshot is an example of interaction with the instructed model:

🚀 Quick Start

These resources showcase how to perform inference with IDEFICS (including 4 - bit quantized inference) along with how to fine - tune the models. In particular, this colab notebook shows how to fine - tune the 9 billion parameters model with a single Google Colab GPU with LoRA and 4 - bit quantization.

We provide quick - start code for both the base and the instruct models.

💻 Usage Examples

Basic Usage (Base Model)

import torch
from transformers import IdeficsForVisionText2Text, AutoProcessor

device = "cuda" if torch.cuda.is_available() else "cpu"

checkpoint = "HuggingFaceM4/idefics-9b"
model = IdeficsForVisionText2Text.from_pretrained(checkpoint, torch_dtype=torch.bfloat16).to(device)
processor = AutoProcessor.from_pretrained(checkpoint)

# We feed to the model an arbitrary sequence of text strings and images. Images can be either URLs or PIL Images.
prompts = [
    [
        "https://upload.wikimedia.org/wikipedia/commons/8/86/Id%C3%A9fix.JPG",
        "In this picture from Asterix and Obelix, we can see"
    ],
]

# --batched mode
inputs = processor(prompts, return_tensors="pt").to(device)
# --single sample mode
# inputs = processor(prompts[0], return_tensors="pt").to(device)

# Generation args
bad_words_ids = processor.tokenizer(["<image>", "<fake_token_around_image>"], add_special_tokens=False).input_ids

generated_ids = model.generate(**inputs, bad_words_ids=bad_words_ids, max_length=100)
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)
for i, t in enumerate(generated_text):
    print(f"{i}:\n{t}\n")

To quickly test your software without waiting for the huge model to download/load you can use HuggingFaceM4/tiny - random - idefics - it hasn't been trained and has random weights but it is very useful for quick testing.

Advanced Usage (Instruct Model)

import torch
from transformers import IdeficsForVisionText2Text, AutoProcessor

device = "cuda" if torch.cuda.is_available() else "cpu"

checkpoint = "HuggingFaceM4/idefics-9b-instruct"
model = IdeficsForVisionText2Text.from_pretrained(checkpoint, torch_dtype=torch.bfloat16).to(device)
processor = AutoProcessor.from_pretrained(checkpoint)

# We feed to the model an arbitrary sequence of text strings and images. Images can be either URLs or PIL Images.
prompts = [
    [
        "User: What is in this image?",
        "https://upload.wikimedia.org/wikipedia/commons/8/86/Id%C3%A9fix.JPG",
        "<end_of_utterance>",

        "\nAssistant: This picture depicts Idefix, the dog of Obelix in Asterix and Obelix. Idefix is running on the ground.<end_of_utterance>",

        "\nUser:",
        "https://static.wikia.nocookie.net/asterix/images/2/25/R22b.gif/revision/latest?cb=20110815073052",
        "And who is that?<end_of_utterance>",

        "\nAssistant:",
    ],
]

# --batched mode
inputs = processor(prompts, add_end_of_utterance_token=False, return_tensors="pt").to(device)
# --single sample mode
# inputs = processor(prompts[0], return_tensors="pt").to(device)

# Generation args
exit_condition = processor.tokenizer("<end_of_utterance>", add_special_tokens=False).input_ids
bad_words_ids = processor.tokenizer(["<image>", "<fake_token_around_image>"], add_special_tokens=False).input_ids

generated_ids = model.generate(**inputs, eos_token_id=exit_condition, bad_words_ids=bad_words_ids, max_length=100)
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)
for i, t in enumerate(generated_text):
    print(f"{i}:\n{t}\n")

Text generation inference

The hosted inference API is powered by Text Generation Inference. To query the model, you can use the following code snippet. The key is to pass images as fetchable URLs with the markdown syntax:

from text_generation import Client

API_TOKEN = "<YOUR_API_TOKEN>"
API_URL = "https://api-inference.huggingface.co/models/HuggingFaceM4/idefics-80b-instruct"
DECODING_STRATEGY = "Greedy"
QUERY = "User: What is in this image?![](https://upload.wikimedia.org/wikipedia/commons/8/86/Id%C3%A9fix.JPG)<end_of_utterance>\nAssistant:"

client = Client(
    base_url=API_URL,
    headers={"x-use-cache": "0", "Authorization": f"Bearer {API_TOKEN}"},
)
generation_args = {
    "max_new_tokens": 256,
    "repetition_penalty": 1.0,
    "stop_sequences": ["<end_of_utterance>", "\nUser:"],
}

if DECODING_STRATEGY == "Greedy":
    generation_args["do_sample"] = False
elif DECODING_STRATEGY == "Top P Sampling":
    generation_args["temperature"] = 1.
    generation_args["do_sample"] = True
    generation_args["top_p"] = 0.95
    
generated_text = client.generate(prompt=QUERY, **generation_args)  
print(generated_text)

Note that we currently only host the inference for the instructed models.

🔧 Technical Details

Training Details

IDEFICS

We closely follow the training procedure laid out in Flamingo. We combine two open - access pre - trained models ([laion/CLIP - ViT - H - 14 - laion2B - s32B - b79K](https://huggingface.co/laion/CLIP - ViT - H - 14 - laion2B - s32B - b79K) and [huggyllama/llama - 65b](https://huggingface.co/huggyllama/llama - 65b)) by initializing new Transformer blocks. The pre - trained backbones are frozen while we train the newly initialized parameters.

The model is trained on the following data mixture of openly accessible English data:

OBELICS is an open, massive and curated collection of interleaved image - text web documents, containing 141M documents, 115B text tokens and 353M images. An interactive visualization of the dataset content is available [here](https://atlas.nomic.ai/map/f2fba2aa - 3647 - 4f49 - a0f3 - 9347daeee499/ee4a84bd - f125 - 4bcc - a683 - 1b4e231cb10f). We use Common Crawl dumps between February 2020 and February 2023.

Wikipedia. We used the English dump of Wikipedia created on February 20th, 2023.

LAION is a collection of image - text pairs collected from web pages from Common Crawl and texts are obtained using the alternative texts of each image. We deduplicated it (following Webster et al., 2023), filtered it, and removed the opted - out images using the [Spawning API](https://api.spawning.ai/spawning - api).

PMD is a collection of publicly - available image - text pair datasets. The dataset contains pairs from Conceptual Captions, Conceptual Captions 12M, WIT, Localized Narratives, RedCaps, COCO, SBU Captions, Visual Genome and a subset of YFCC100M dataset. Due to a server failure at the time of the pre - processing, we did not include SBU captions.

For multimodal web documents, we feed the model sequences corresponding to the succession of text paragraphs and images. For image - text pairs, we form the training sequences by packing images w

📄 License

The license is of type "other". For more details, please refer to the relevant information in the model repository.