Methods › Natural Language Processing › Language Models › OPT

OPT

285 papers tagged archive 2025-07-28

Introduced by Susan Zhang et al. in OPT: Open Pre-trained Transformer Language Models

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

OPT is a suite of decoder-only pre-trained transformers ranging from 125M to 175B parameters. The model uses an AdamW optimizer and weight decay of 0.1. It follows a linear learning rate schedule, warming up from 0 to the maximum learning rate over the first 2000 steps in OPT-175B, or over 375M tokens in the smaller models, and decaying down to 10% of the maximum LR over 300B tokens. The batch sizes range from 0.5M to 4M depending on the model size and is kept constant throughout the course of training.

PaperSource

In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 11 in the graph, strongest link: official). This answer is about arXiv:2205.01068, the paper the archive credits with this method.

Origin paper of this answer, arXiv:2205.01068 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 14 ran (of which 2 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 10 unverified (of 24 harvested samples) · 17 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

Papers archive 2025-07-28

archive papers tagged: 285 · with a code link: 123 · where Syntology ran a sample: 55 (39 with a run with no instrument failure, 16 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (55 of 285 tagged: 39 with a run with no instrument failure, 16 where every run was a failure of Syntology's instrument)

Page 1 of 3: papers 1 to 100 of 285, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

Tasks archive 2025-07-28

20 shown of 247 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Language Modelling41
Language Modeling28
Quantization24
GPU22
Large Language Model17
In-Context Learning14
Question Answering14
Text Generation12
Model Compression8
Retrieval8
Fairness7
Transfer Learning7
Translation7
Attribute6
Benchmarking6
Object Detection6
Scheduling6
Sentence6
object-detection6
Computational Efficiency5

Usage over time archive 2025-07-28

Papers per year tagged with OPT: 2022 to 2025, peak 104 104 0 2022: 49 papers 2022 2023: 104 papers 2023 2024: 104 papers 2024 2025: 28 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (285 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Language Models

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections