CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.vision / git-large-coco
From: microsoft <huggingface.co/microsoft>Newsgroups: alt.freeweights.visionSubject:

git-large-coco

Date: 2026-11-15Commit: b644b0bSigned: 2DC28CC7B26A283B ✓

Image to text model with 394M parameters. Safetensors weights, 3.15 GB in all. Published by microsoft under MIT.

394M params3.15GBgit-large-cocosafetensorspermissive
FactsParams394MSize3.15 GBFormatssafetensorsTaskimage to textLicenseMITFrom sourcepermissive
$ fw get microsoft/git-large-coco
# manifest sha256 2a09a886e3ad… · 3.15 GB · 11 files
$ fw verify ./git-large-coco microsoft/git-large-coco
From sourceHosted (signed)microsoft/git-large-cocoLast check: 2026-11-15 03:33 UTC
Run at homeGet help

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Works with

Run8Fine-tune7Convert8Scan2

Runs with

Ranked by fit to this model (safetensors), then by GitHub stars.

TransformersLocalAItinygradTriton Inference ServerBentoMLCTranslate2ExLlamaV2LitServe
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
3.15 GB
Weights
1.58 GB (safetensors)
Parameters
394M
Formats
safetensors
Task
image to text
License
MIT (permissive)
Files
11, each with a sha256
Publisher
microsoft
Added
2026-11-15
Section
alt.freeweights.vision
Lineage

Original release from the publisher.

Where these bytes come from
Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-15 03:33 UTCpassed

Model card

From the publisher at commit b644b0b. Shown as plain text with links; images open at the publisher.

GIT (GenerativeImage2Text), large-sized, fine-tuned on COCO#

GIT (short for GenerativeImage2Text) model, large-sized version, fine-tuned on COCO. 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.

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.

Image: GIT architecture

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.

How to use#

For code examples, we refer to the documentation.

Training data#

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.

Next, the model was fine-tuned on COCO.

See table 11 in the paper for more details.

Preprocessing#

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.

Files

11 files · 3.15 GBWeights 1.58 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 11 files with their sha256
FileSizesha256
.gitattributes1.48 KBdb7c0371f46f0840b8f25794c1e3321c9b5820a8cb6ba9694a46fc64b8fae5a6
README.md3.20 KB19ed173a6598f3271195b6083774ec91b2f3435a8e1ca3b45215ab91298c50f7
config.json2.82 KB399ba9fb603bc8dd14f7ee6adc7572e21df88736a5033cba5aed087462e320ae
generation_config.json141 B038491bf746d76c662790d297cd0b4555708784d9263c7517ac42c41621a1fb9
model.safetensors1.58 GBb829ce129d49db383baed90ee283087d53b5c916bef2782eefc32e19bef6f42f
preprocessor_config.json503 B54404ef25acb1afdee419c0651477c5810559d2063cf261b89878a14155b85e6
pytorch_model.bin1.58 GBcdfc6b68ba3499a63652eb2dc0f1b46aa2f4e4a01d0e18c2866057cb764c4792
special_tokens_map.json125 Bb6d346be366a7d1d48332dbc9fdf3bf8960b5d879522b7799ddba59e76237ee3
tokenizer.json711 KBad3a0d445d3e88c2f679eb9d309cf0f6dd4e6325f559bb815490c935c57e0d24
tokenizer_config.json453 B5b5d830c6763f67d6f068100a26fe48fbba609e95bd8d428080accaf34eddfdf
vocab.txt232 KB07eced375cec144d27c900241f3e339478dec958f92fddbc551f295c992038a3
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
b644b0b412 pinned now2026-11-15 03:33 UTC11 files · 3.15 GB

Use it

$ fw get microsoft/git-large-coco
# manifest sha256 2a09a886e3ad… · 3.15 GB · 11 files
$ fw verify ./git-large-coco microsoft/git-large-coco
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/microsoft/git-large-coco.json --dir ./git-large-coco $ python3 fw.py verify ./git-large-coco ./microsoft__git-large-coco.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download microsoft/git-large-coco --revision b644b0b41274649f87de8846fa15f9a22dad7583 --local-dir ./git-large-coco
Run at home

License

Name
MIT License
Id
MIT
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-15
Text in
README.md
Text sha256
19ed173a6598f3271195b6083774ec91b2f3435a8e1ca3b45215ab91298c50f7
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: microsoft <huggingface.co/microsoft>Newsgroups: alt.freeweights.visionSubject: git-large-cocoDate: 2026-11-15Commit: b644b0bSigned: 2DC28CC7B26A283B ✓
Upstream
microsoft/git-large-coco
Pinned commit
b644b0b41274649f87de8846fa15f9a22dad7583
Manifest
git-large-coco.json · .minisig
Manifest sha256
2a09a886e3ad6b5eeb706657cf1c632f0298d460b0e3fa8cae4a6b9286b8c351
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 03:33 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/microsoft/git-large-coco.json $ curl -O https://freeweights.allternit.com/manifests/microsoft/git-large-coco.json.minisig $ minisign -Vm git-large-coco.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq $ shasum -a 256 <file> # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

No related models in this catalog.Nothing here lists this model as its parent, and it names no parent.
Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download microsoft/git-large-coco
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. git-large-coco.json. Provenance. Takedown history: none.
Source
huggingface.co/microsoft/git-large-coco

Related models

All of alt.freeweights.vision →
From: dima806 <huggingface.co/dima806>Subject: ai_vs_real_image_detection
From: legekka <huggingface.co/legekka>Subject: AI-Anime-Image-Detector-ViT
From: onnx-community <huggingface.co/onnx-community>Subject: AI-Anime-Image-Detector-ViT-ONNX
From: AICodexLab <huggingface.co/AICodexLab>Subject: answerdotai-ModernBERT-base-ai-detector
From: onnx-community <huggingface.co/onnx-community>Subject: answerdotai-ModernBERT-base-ai-detector-ONNX
From: onnx-community <huggingface.co/onnx-community>Subject: bart-large-cnn-ONNX