BITTERS

Closed weights LG,Shutterstock 650M parameters October 2023

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
LG,Shutterstock
Organisation type
Industry,Industry
Country
Korea (Republic of), United States of America
Published
1 October 2023
Authors
Taehoon Kim, Mark Marsden, Pyunghwan Ahn, Sangyun Kim, Sihaeng Lee, Alessandra Sala, Seung Hwan Kim

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Vision
Task
Image captioning

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Parameters
650M

BITTERS has 650 million parameters in total.

Training data
108,800,000,000 tokens

we train BITTERS using a new, quality-controlled 100 million image dataset which we will refer to as Text Image Pairs 100 Million (TIP100M) WaveVAE module We also resize each image to 256 × 256 × 3 We train the model for 3 epochs with a batch size of 480 Batch size: 1280 Number of updates: 2 epochs Image resolution: 256x256 Sequence length: 64 text tokens, 1024 image tokens

Training compute

The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.

Training compute
7.8 × 10¹⁷ FLOP

WaveVAE: "We train the model for 10 epochs with batch size 3840." "We reduced the number of parameters to 25 million in total" 25000*100000000*6*10=1.5e+14 BiART: "We train our model for 2 epochs in total with batch size 1280" "BITTERS has 650 million parameters in total" 650000000*100000000*6*2=7.8e+17 7.8e+17+1.5e+14=7.8015e+17

How it was established
Operation counting

Availability

Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.

Weights
Closed — provider access only
Model access
Unreleased
Training code
Unreleased

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence
Likely

Sources

Where this record came from and when it was last checked.

Reference
Large-Scale Bidirectional Training for Zero-Shot Image Captioning
Last updated
28 November 2025

What the numbers mean

Where it came from

BITTERS was published by LG,Shutterstock, in the country recorded as Korea (Republic of), during October 2023. The publishing organisation is categorised as industry,Industry.

It works in the domain of Vision, and is recorded as performing the task of image captioning.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

Training and provenance

The training run consumed about 7.8 × 10¹⁷ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.

It was trained on a corpus of about 108,800,000,000 tokens of text.

Answers

BITTERS — common questions

01

BITTERS— when was it released?

It was published in October 2023. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

02

BITTERS— what is it used for?

It works in the domain of Vision, and is recorded as handling the task of image captioning. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

03

BITTERS— how much compute was used to train it?

Training consumed around 7.8 × 10¹⁷ FLOP. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.

04

BITTERS— what GPU do I need to run it?

None. This is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

05

BITTERS— is it open source?

No. Its weights have not been published, so it exists only as a service controlled by its owner.

06

BITTERS— how many parameters does it have?

It has a parameter count of 650M. BITTERS has 650 million parameters in total. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.

07

BITTERS— who created it?

It was published by LG,Shutterstock, based in Korea (Republic of), an organisation categorised as industry,Industry.

Source

Original publication

Record last updated 28 November 2025

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.