Base LM + kNN LM + Continuous Cache

Closed weights Stanford University,Facebook AI Research 247M parameters November 2019

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
Stanford University,Facebook AI Research
Organisation type
Academia,Industry
Country
United States of America, France
Published
1 November 2019
Authors
Urvashi Khandelwal, Omer Levy, Dan Jurafsky, Luke Zettlemoyer, Mike Lewis

What it does

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

Domain
Language
Task
Language modeling

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
247M

"we take the exact architecture and optimization described by Baevski & Auli (2019) and use it to create a kNN-LM for inference. This model consists of 16 layers, each with 16 self-attention heads, 1024 dimensional hidden states, and 4096 dimensional feedforward layers, amounting to 247M trainable parameters."

Training data
103,000,000 tokens

" During this forward pass, each target token is provided a minimum of 1536 tokens of prior context for WIKITEXT-103" 200 epochs - figure 8

Epochs
200

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
3.1 × 10¹⁹ FLOP

6 FLOP / parameter / token * 247*10^6 parameters * 103000000 tokens * 200 epochs = 3.05292e+19 FLOP __________ for the Algorithmic progress paper 7.3 × 10^18 FLOP was estimated similar to supposedly base model (transformer)

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
Open source

Training code, MIT: https://github.com/urvashik/knnlm

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

"GNN-LM achieves a new state-of-the-art perplexity of 14.8 on WikiText-103"

Record confidence
Likely
Citations
1,049
Benchmark data
Base LM + kNN LM + Continuous Cache

Sources

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

Reference
Generalization through Memorization: Nearest Neighbor Language Models
Last updated
25 May 2026

What the numbers mean

What this model is

Base LM + kNN LM + Continuous Cache was published by Stanford University,Facebook AI Research, in United States of America, in November 2019. It comes out of academia,Industry.

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

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

What went into building it

Training it took roughly 3.1 × 10¹⁹ FLOP of computation — a measure of what producing the model cost, not of how fast it answers.

It was trained on about 103,000,000 tokens of text.

The reason it appears in this catalogue at all is sOTA improvement.

Answers

Base LM + kNN LM + Continuous Cache — common questions

01

Who created Base LM + kNN LM + Continuous Cache?

Base LM + kNN LM + Continuous Cache was published by Stanford University,Facebook AI Research, based in United States of America, categorised as academia,Industry.

02

When was Base LM + kNN LM + Continuous Cache released?

Base LM + kNN LM + Continuous Cache was published in November 2019. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

03

What is Base LM + kNN LM + Continuous Cache used for?

Base LM + kNN LM + Continuous Cache works in Language, and is recorded as handling language modeling. These are the areas it was designed around; they describe intent rather than a hard boundary.

04

How much compute was used to train Base LM + kNN LM + Continuous Cache?

Around 3.1 × 10¹⁹ 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.

05

What GPU do I need to run Base LM + kNN LM + Continuous Cache?

None. Base LM + kNN LM + Continuous Cache 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.

06

Is Base LM + kNN LM + Continuous Cache open source?

No. Base LM + kNN LM + Continuous Cache has not had its weights published, so it exists only as a service controlled by its owner.

07

How many parameters does Base LM + kNN LM + Continuous Cache have?

Base LM + kNN LM + Continuous Cache has 247M parameters. "we take the exact architecture and optimization described by Baevski & Auli (2019) and use it to create a kNN-LM for inference. This model consists of 16 layers, each with 16 self-attention heads, 1024 dimensional hidden states, and 4096 dimensional feedforward layers, amounting to 247M trainable parameters.". 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.

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.