Feedback Transformer
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
- LORIA,University of Lorraine,Facebook AI Research
- Organisation type
- Academia,Academia,Industry
- Country
- France, United States of America
- Published
- 21 February 2020
- Authors
- Angela Fan, Thibaut Lavril, Edouard Grave, Armand Joulin, Sainbayar Sukhbaatar
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
- 126M
- Training data
- 103,000,000 tokens
- Epochs
- 267.23
- Batch size
- 131,072
Table 3 shows 126M. There is another instance of the Feedback Transformer mentioned in Table 9 with 139M parameters.
"The models are trained for 200k steps and the finetuned for additional 10k steps." from Table 9 (describes 139M model) batch size 512 sequence length 256 256*512*210000 / 103000000 = 267 epochs "speculative" confidence since there is no clear description of the 126M model and numbers are assumed based on 139M model description
256*512
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
- 7.7 × 10¹⁸ FLOP
- How it was established
- Operation counting,Hardware
6 FLOP / token / parameter * 126*10^6 parameters * 256 tokens per sequences * 512 sequences per batch * 210000 steps = 2.0808991e+19 FLOP assuming V100 GPU fp16: 31330000000000 FLOP/sec/GPU * 1 GPU * 84 hours * 3600 sec / hour * 0.3 [assumed utilization] = 2.8422576e+18 FLOP sqrt(2.0808991e+19*2.8422576e+18) = 7.690547e+18 FLOP ___________ in the Algorithmic progress paper they used estimation of 4.41e+19 FLOP also with low confidence
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Wall-clock time
- 84 hours
" Our Feedback architecture takes 3.5 days to train" 3.5*24 = 84 hours
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.
- Why it is tracked
- SOTA improvement
- Record confidence
- Speculative
- Citations
- 41
- Benchmark data
- Feedback Transformer
"As shown in Table 4, the Feedback Transformer model achieves a new SOTA performance (on Enwiki8) of 0.96 bit-per-byte despite its small size."
Sources
Where this record came from and when it was last checked.
- Reference
- Addressing Some Limitations of Transformers with Feedback Memory
- Last updated
- 28 November 2025
What the numbers mean
Background
Feedback Transformer was published by LORIA,University of Lorraine,Facebook AI Research, in the country recorded as France, during February 2020. The category the publisher falls under is academia,Academia,Industry.
It works in the domain of Language, and is recorded as performing the task of language modeling.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
How it was trained
The training run consumed about 7.7 × 10¹⁸ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.
The training set ran to roughly 103,000,000 tokens of text.
Its inclusion criterion: sOTA improvement.
Answers
Feedback Transformer — common questions
Feedback Transformer— what is it used for?
It works in the domain of Language, and is recorded as handling the task of language modeling. 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.
Feedback Transformer— how much compute was used to train it?
Training consumed around 7.7 × 10¹⁸ 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.
Feedback Transformer— 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.
Feedback Transformer— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
Feedback Transformer— how many parameters does it have?
It has a parameter count of 126M. Table 3 shows 126M. There is another instance of the Feedback Transformer mentioned in Table 9 with 139M 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.
Feedback Transformer— who created it?
It was published by LORIA,University of Lorraine,Facebook AI Research, based in France, an organisation categorised as academia,Academia,Industry.
Feedback Transformer— when was it released?
It was published in February 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.