Methods › Natural Language Processing › Language Models › Pythia

Pythia

60 papers tagged archive 2025-07-28

Introduced by Stella Biderman et al. in Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling

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

Pythia is a suite of decoder-only autoregressive language models all trained on public data seen in the exact same order and ranging in size from 70M to 12B parameters. The model architecture and hyperparameters largely follow GPT-3, with a few notable deviations based on recent advances in best practices for large scale language modeling.

PaperSource

In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 5 in the graph, strongest link: official). The lookup matched a paper by its title, arXiv:2304.01373, not a method entry. This answer is about arXiv:2304.01373, the paper the archive credits with this method.

Origin paper of this answer, arXiv:2304.01373 (its page on this site · its page on Syntology).

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: 60 · with a code link: 36 · where Syntology ran a sample: 23 (20 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (23 of 60 tagged: 20 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 60 of 60, 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 58 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 Modelling23
Language Modeling15
Memorization10
Large Language Model5
Question Answering4
Text Generation3
Articles2
Common Sense Reasoning2
Computational Efficiency2
Hallucination2
In-Context Learning2
Knowledge Distillation2
LAMBADA2
Machine Translation2
Math2
Sentence Completion2
World Knowledge2
counterfactual2
model2
Adversarial Attack1

Usage over time archive 2025-07-28

Papers per year tagged with Pythia: 2023 to 2025, peak 31 31 0 2023: 17 papers 2023 2024: 31 papers 2024 2025: 12 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (60 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