DensePhrases
No estimate
No hardware requirements for this model
This model's weights are open, but no parameter count has been published for it. Every memory and speed figure starts from that number, so we would rather show nothing than a fabricated estimate.
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
- Korea University,Princeton University
- Organisation type
- Academia,Academia
- Country
- Korea (Republic of), United States of America
- Published
- 23 December 2020
- Authors
- Jinhyuk Lee, Mujeen Sung, Jaewoo Kang, Danqi Chen
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Question answering
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.
- Training data
- 58,000,000 tokens
- Epochs
- 4
from appendix D "The number of generated questions is 327,302 and 1,126,354 for SQuAD and Natural Questions, respectively." assuming 40 words per question we get around ~ 58M
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
- 2.1 × 10¹⁸ FLOP
- How it was established
- Hardware
flops = (8) * (1215 * 10**10) * (20 * 3600) * 3 // 10 = 2099520000000000000 (num gpu) * (peak flops) * (time in seconds) * (assumed utilization rate) model of GPU from appendix B (Titan Xp) number of GPUs from table in appendix A flops from https://www.techpowerup.com/gpu-specs/titan-xp.c2948
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Training hardware
- NVIDIA TITAN Xp
- Chips used
- 8
- Chip-hours
- 160
- Wall-clock time
- 20 hours
- Power draw
- 4.1 kW
appendix A row 3
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
- Open — downloadable
- Model access
- Open weights (unrestricted)
- Training code
- Open source
Apache 2.0: https://github.com/princeton-nlp/DensePhrases
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Why it is tracked
- SOTA improvement
- Record confidence
- Speculative
- Citations
- 128
from abstract "our model DensePhrases improves over previous phrase retrieval models by 15%-25% absolute accuracy and matches the performance of state-of-the-art retriever-reader models. " "we achieve state-of-the-art performance on two slot filling tasks (Petroni et al., 2021), using less than 5% of the training data."
Sources
Where this record came from and when it was last checked.
- Reference
- Learning Dense Representations of Phrases at Scale
- Last updated
- 25 May 2026
What the numbers mean
What this model is
DensePhrases was published by Korea University,Princeton University, in the country recorded as Korea (Republic of), during December 2020. It comes out of an organisation categorised as academia,Academia.
It works in the domain of Language, and is recorded as performing the task of question answering.
The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached.
Training and provenance
Training it took a computation budget of roughly 2.1 × 10¹⁸ FLOP, on hardware recorded as NVIDIA TITAN Xp. That figure measures what producing the model cost, and has no bearing on how fast it answers.
The training set ran to roughly 58,000,000 tokens of text.
Its inclusion criterion: sOTA improvement.
Answers
DensePhrases — common questions
DensePhrases— what is it used for?
It works in the domain of Language, and is recorded as handling the task of question answering. These are the areas it was designed around; they describe intent rather than a hard boundary.
DensePhrases— where can I download it?
The weights are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.
DensePhrases— how much compute was used to train it?
Training consumed around 2.1 × 10¹⁸ FLOP, on hardware recorded as NVIDIA TITAN Xp. 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.
DensePhrases— what GPU do I need to run it?
We cannot say. It has open weights, but no parameter count has been published for it, and every memory and speed calculation starts from that number. We would rather show nothing than a fabricated estimate.
DensePhrases— is it open source?
Its weights are published, so it can be downloaded and run on your own hardware. Note that open weights is not the same as open source in the full sense — it says nothing about the training data, the training code, or the commercial terms attached.
DensePhrases— how many parameters does it have?
No parameter count has been published for it, which is why no memory or speed figure appears on this page.
DensePhrases— who created it?
It was published by Korea University,Princeton University, based in Korea (Republic of), an organisation categorised as academia,Academia.
DensePhrases— when was it released?
It was published in December 2020. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
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.