GPT-2 (fine-tuned with HYDRA)

Closed weights University of California San Diego 1.5B parameters October 2021

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
University of California San Diego
Organisation type
Academia
Country
United States of America
Published
16 October 2021
Authors
Kabir Nagrecha, Arun Kumar

What it does

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

Domain
Language
Task
Language modeling/generation
Base model
GPT-2 (1.5B)

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
1.5B

They don't actually say which GPT-2 version they use, but it appears to be XL (1.5B params), since Table 1 shows zero-shot accuracy of 18.34 on WikiText-2, which is what the 1.5B version got.

Training data
tokens
Epochs
1

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
1.9 × 10²¹ FLOP

They fine-tuned GPT-2 (1.5B) for one epoch on WikiText-2. GPT-2 itself used 1.92e21 FLOP, and here we see 6 * 2M * 1.54B = 1.848e16 fine-tuning FLOP (which has almost no impact on total FLOP).

How it was established
Operation counting
Fine-tuning compute
1.8 × 10¹⁶ FLOP

They fine-tuned GPT-2 (1.5B) for one epoch on WikiText-2. GPT-2 itself used 1.92e21 FLOP, and here we see 6 * 2M * 1.54B = 1.848e16 fine-tuning FLOP (which has almost no impact on total FLOP).

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
Confident
Citations
6
Benchmark data
GPT-2 (fine-tuned with HYDRA)

Sources

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

Reference
Hydra: A System for Large Multi-Model Deep Learning
Last updated
25 May 2026

What the numbers mean

What this model is

GPT-2 (fine-tuned with HYDRA) was published by University of California San Diego, in United States of America, in October 2021. It comes out of academia.

It works in Language, and is recorded as doing language modeling/generation.

It is derived from GPT-2 (1.5B) rather than trained from scratch, which is the usual way a specialised model is produced.

Its weights were never published, so it can only be reached through its provider. No graphics card changes that.

Training and provenance

The training run consumed about 1.9 × 10²¹ FLOP. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

Answers

GPT-2 (fine-tuned with HYDRA) — common questions

01

How much compute was used to train GPT-2 (fine-tuned with HYDRA)?

Around 1.9 × 10²¹ 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.

02

What GPU do I need to run GPT-2 (fine-tuned with HYDRA)?

None. GPT-2 (fine-tuned with HYDRA) 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.

03

Is GPT-2 (fine-tuned with HYDRA) open source?

No. GPT-2 (fine-tuned with HYDRA) has not had its weights published, so it exists only as a service controlled by its owner.

04

How many parameters does GPT-2 (fine-tuned with HYDRA) have?

GPT-2 (fine-tuned with HYDRA) has 1.5B parameters. They don't actually say which GPT-2 version they use, but it appears to be XL (1.5B params), since Table 1 shows zero-shot accuracy of 18.34 on WikiText-2, which is what the 1.5B version got. 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.

05

Who created GPT-2 (fine-tuned with HYDRA)?

GPT-2 (fine-tuned with HYDRA) was published by University of California San Diego, based in United States of America, categorised as academia.

06

When was GPT-2 (fine-tuned with HYDRA) released?

GPT-2 (fine-tuned with HYDRA) was published in October 2021. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

07

What is GPT-2 (fine-tuned with HYDRA) used for?

GPT-2 (fine-tuned with HYDRA) works in Language, and is recorded as handling language modeling/generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Source

Original publication

Record last updated 25 May 2026

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.