Disclaimer: The team releasing GIT did not write a model card for this model so this model card has been written by the Hugging Face team.
Model description
GIT is a Transformer decoder conditioned on both CLIP image tokens and text tokens. The model is trained using "teacher forcing" on a lot of (image, text) pairs.
The goal for the model is simply to predict the next text token, giving the image tokens and previous text tokens.
The model has full access to (i.e. a bidirectional attention mask is used for) the image patch tokens, but only has access to the previous text tokens (i.e. a causal attention mask is used for the text tokens) when predicting the next text token.
This allows the model to be used for tasks like:
image and video captioning
visual question answering (VQA) on images and videos
even image classification (by simply conditioning the model on the image and asking it to generate a class for it in text).
Intended uses & limitations
You can use the raw model for image captioning. See the
model hub
to look for
fine-tuned versions on a task that interests you.
We collect 0.8B image-text pairs for pre-training, which include COCO (Lin et al., 2014), Conceptual Captions
(CC3M) (Sharma et al., 2018), SBU (Ordonez et al., 2011), Visual Genome (VG) (Krishna et al., 2016),
Conceptual Captions (CC12M) (Changpinyo et al., 2021), ALT200M (Hu et al., 2021a), and an extra 0.6B
data following a similar collection procedure in Hu et al. (2021a).
=> however this is for the model referred to as "GIT" in the paper, which is not open-sourced.
This checkpoint is "GIT-base", which is a smaller variant of GIT trained on 10 million image-text pairs.
We refer to the original repo regarding details for preprocessing during training.
During validation, one resizes the shorter edge of each image, after which center cropping is performed to a fixed-size resolution. Next, frames are normalized across the RGB channels with the ImageNet mean and standard deviation.
Evaluation results
For evaluation results, we refer readers to the
paper
.
Runs of microsoft git-base on huggingface.co
32.4K
Total runs
0
24-hour runs
-508
3-day runs
1.4K
7-day runs
12.6K
30-day runs
More Information About git-base huggingface.co Model
git-base huggingface.co is an AI model on huggingface.co that provides git-base's model effect (), which can be used instantly with this microsoft git-base model. huggingface.co supports a free trial of the git-base model, and also provides paid use of the git-base. Support call git-base model through api, including Node.js, Python, http.
git-base huggingface.co is an online trial and call api platform, which integrates git-base's modeling effects, including api services, and provides a free online trial of git-base, you can try git-base online for free by clicking the link below.
microsoft git-base online free url in huggingface.co:
git-base is an open source model from GitHub that offers a free installation service, and any user can find git-base on GitHub to install. At the same time, huggingface.co provides the effect of git-base install, users can directly use git-base installed effect in huggingface.co for debugging and trial. It also supports api for free installation.