Hugging Face's logo

HuggingFaceM4
/
idefics-80b

Text Generation
Transformers
PyTorch
Safetensors
English
idefics
image-text-to-text
multimodal
text
image
image-to-text
text-generation-inference
Model card Files Community
23
idefics-80b / README.md
Leyo's picture
Leyo
winoground fix
6edaaa6
preview code
|
raw
history blame
18.1 kB
metadata
language: en
tags:
  - multimodal
  - text
  - image
license: other
datasets:
  - HuggingFaceM4/OBELISC
  - wikipedia
  - facebook/pmd
  - laion/laion2B-en

TODO: logo?

Model Card for m4-80b

ATUM (Adapted Transformers for Unstructured Multimodal data) is an open-access reproduction of Flamingo, a closed-source visual language model developed by Deepmind. The multimodal model accepts arbitrary sequences of image and text inputs and produces text outputs and is built solely on public available data and models. ATUM (TODO) is on par with the original 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.

The model comes into two variants: a large 80 billion parameters version and a 9 billion parameters version. We also fine-tune these base models on a mixture of SFT datasets (TODO: find a more understandable characterization), which boosts the downstream performance while making the models more usable in conversational settings: (TODO: 80B-sfted) and (TODO: 9B sfted).

Table of Contents

Model Details

ATUM 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 on par with the closed-source model), and is a robust starting point to fine-tune multimodal models on custom data.

ATUM 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 unstrucutred multimodal web documents.

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 and thus should be prefered when using the models out-of-the-box.

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

TODO: screenshot

How to Get Started with the Model

Use the code below to get started with the model.

Click to expand

More information needed

Training Details

We closel follow the training procedure layed out in Flamingo. We combine two open-source pre-trained models (laion/CLIP-ViT-H-14-laion2B-s32B-b79K and 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:

Data Source Type of Data Number of Tokens in Source Number of Images in Source Epochs Effective Proportion in Number of Tokens
OBELISC Unstructured Multimodal Web Documents 114.9B 353M 1 73.85%
Wikipedia Unstructured Multimodal Web Documents 3.192B 39M 3 6.15%
LAION Image-Text Pairs 29.9B 1.120B 1 17.18%
PMD Image-Text Pairs 1.6B 70M 3 2.82%

OBELISC 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.

Wkipedia is the multimodal equivalent of the encyclopedia. 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 this paper), slightly filtered it, and removed the opted-out images.

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 with their captions. The images are encoded with the vision encoder and vision hidden states are pooled with Transformer Perceiver blocks and then fused into the text sequence through the cross-attention blocks.

Following (Dehghani et al., 2023)[https://huggingface.co/papers/2302.05442], we apply a layer normalization on the projected queries and keys of both the Perceiver and cross-attention blocks, which improved training stability in our early experiments. We use the RMSNorm implementation for trainable Layer Norms.

The training objective is the standard next token prediction.

We use the following hyper and training parameters:

Parameters ATUM ATUM-9b
Perceiver Resampler Number of Layers 6 6
Number of Latents 64 64
Number of Heads 16 16
Resampler Head Dimension 96 96
Model Language Model Backbone Llama-65b Llama-7b
Vision Model Backbone laion/CLIP-ViT-H-14-laion2B-s32B-b79K laion/CLIP-ViT-H-14-laion2B-s32B-b79K
Cross-Layer Interval 4 4
Training Sequence Length 1024 1024
Effective Batch Size (# of tokens) 3.67M 1.31M
Max Training Steps 200K 200K
Weight Decay 0.1 0.1
Optimizer Adam(0.9, 0.999) Adam(0.9, 0.999)
Gradient Clipping 1.0 1.0
Z-loss weight 1e-3 1e-3
Learning Rate Initial Max 5e-5 1e-5
Initial Final 3e-5 6e-6
Decay Schedule Linear Linear
Linear warmup Steps 2K 2K
Large-scale Optimization Gradient Checkpointing True True
Precision Mixed-pres bf16 Mixed-pres bf16
ZeRO Optimization Stage 3 Stage 3

Evaluation

We closely follow the evaluation protocol of Flamingo and evaluate ATUM on a suite of downstream image + text benchmarks ranging from visual question answering to image captioning.

We compare our model to the original Flamingo along with OpenFlamingo, another open-source reproduction.

We perform checkpoint selection based on validation sets of TODO, and select the checkpoint at step 65'000 for ATUM-9B and at step 37'500 for ATUM. The models are evaluated with in-context few-shot learning where the priming instances are selected from a support set to be similar (i.e. close in a vector space) to the queried instance. We do not use any form of ensembling.

TODO: beautiful plots of shots scaling laws.

Model Shots VQAv2 (OE VQA acc) OKVQA (OE VQA acc) TextVQA (OE VQA acc) VizWiz (OE VQA acc) TextCaps (CIDEr) Coco (CIDEr) NoCaps (CIDEr) Flickr (CIDEr) ImageNet1k (accuracy) VisDial (NDCG) HatefulMemes (ROC AUC) ScienceQA (accuracy) RenderedSST2 (accuracy) Winoground (group (text/image))
IDEFICS 80B 0 60 45.2 30.9 36 56.8 91.8 65 53.7 74.3 48.8 60.6 68.9 60.5 8 (18.8/22.5)
4 63.4 52.3 34.7 45.8 77.9 109.3 101.1 68.9 - 48.6 58.7 66.3 63.9 -
8 64.5 55.2 35.4 49.3 82.5 113.9 104.7 74.3 - 48.1 57.8 - 64.3 -
16 65.4 56.8 36.3 51.5 85.2 116.6 105.6 76.8 - - 56 - 66.9 -
32 66 58 37 52.6 86.1 116.5 106.3 78.9 - - 54.3 - 68 -
IDEFICS 9B 0 50.9 38.4 25.9 35.5 25.4 46 36.8 27.3 70.7 48.7 51.7 44.2 61.8 5 (16.8/20.8)
4 55.6 45.8 26.8 42 60.8 88.9 78.4 52.2 - 48.1 52.6 41.6 60.6 -
8 56.4 47.3 26.8 42.8 63.7 96.9 84.3 60.3 - 47.5 52.3 - 66.8 -
16 57.2 49 28.1 45 68 99.6 87.2 65 - - 52.5 - 66 -
32 57.9 50.4 28.2 45.9 69.7 101.5 88.6 66 - - 53.1 - 63.4 -

Technical Specifications

Hardware

The training was performed on an AWS SageMaker cluster with 64 nodes of 8x80GB A100 GPUs (512 GPUs total). The cluster uses the current EFA network which provides about 340GBps throughput.

As the network is quite slow for the needs of DeepSpeed ZeRO-3 we were only able to clock ~90 TFLOPs.

Software

The training software is built on top of HuggingFace Transformers + Accelerate, and DeepSpeed ZeRO-3 for training, and WebDataset for data loading.

Bias, Risks, and Limitations

Significant research has explored bias and fairness issues with language models (see, e.g., Sheng et al. (2021) and Bender et al. (2021)). As a derivative of such a language model, ATUM can produce texts that include disturbing and harmful stereotypes across protected classes; identity characteristics; and sensitive, social, and occupational groups. Moreover, ATUM can produce factually incorrect texts, and should not be relied on to produce factually accurate information.

Here are a few examples of outputs that could be categorized as factually incorrect, biased, or offensive: TODO: give 4/5 representative examples

To measure ATUM's ability to recognize socilogical (TODO: find a better adjective) attributes, we evaluate the model on FairFace... TODO: include FairFace numbers

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

  • Hardware Type: 64 nodes of 8x 80GB A100 gpus, EFA network
  • Hours used: ~672 node hours
  • Cloud Provider: AWS Sagemaker
  • Carbon Emitted: unknown

Citation

BibTeX:

More information needed

APA:

More information needed

Model Card Authors [optional]

V, i, c, t, o, r, ,, , S, t, a, s, ,, , X, X, X

Model Card Contact

Please open a discussion on the Community tab!