Model reference · open weights
git-large is an open-weight language model from microsoft. git-large (BF16) weighs 1.6 GB; the smallest configuration that runs it is RTX 3060 12 GB.
What it is
| Released by | microsoft |
|---|---|
| Type | Language models |
| Task | Image→text |
| Runs with | transformers |
| Released | 2023-01-02 |
| Popularity | 654 downloads / month |
| Weights | 1.6 GB (git-large (BF16), file size) |
| Licence | Open weights |
What it runs on
Weights 1.6 GB (file size) · runtime overhead from 762 MB on a small card.
How much memory each request adds is not estimated yet for this architecture — only the weights are. They need the cards below at the least, plus room for the context.
| Card | The weights alone |
|---|---|
| RTX 3060 12 GB | fits |
| RTX 4060 Ti 16 GB | fits |
| RTX 3090 24 GB | fits |
| RTX 4090 24 GB | fits |
| RTX 5090 32 GB | fits |
| L40S 48 GB | fits |
| A100 80 GB | fits |
| H100 80 GB | fits |
| RTX PRO 6000 Blackwell 96 GB | fits |
| DGX Spark (GB10) 128 GB unified | fits |
| H200 141 GB | fits |
| B200 180 GB | fits |
From the model card
GIT (short for GenerativeImage2Text) model, large-sized version. It was introduced in the paper GIT: A Generative Image-to-text Transformer for Vision and Language by Wang et al. and first released in this repository.
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.
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:
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.
For code examples, we refer to the documentation.
From the paper:
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-large", which is a smaller variant of GIT trained on 20 million image-text pairs.
See table 11 in the paper for more details.
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.
For evaluation results, we refer readers to the paper.
Quoted from the model card on Hugging Face — the full card is behind the Hugging Face link above.
How it works