Methods › Natural Language Processing › Language Models › Galactica
Galactica
Introduced by Ross Taylor et al. in Galactica: A Large Language Model for Science
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Galactica is a language model which uses a Transformer architecture in a decoder-only setup with the following modifications:
- It uses GeLU activations on all model sizes
- It uses a 2048 length context window for all model sizes
- It does not use biases in any of the dense kernels or layer norms
- It uses learned positional embeddings for the model
- A vocabulary of 50k tokens was constructed using BPE. The vocabulary was generated from a randomly selected 2% subset of the training data
In Syntology harvested code stored, below machine verification (unverified_code; harvested), served level V1; retrieve with get_harvested_code_for_paper(arxiv_id='2211.09085'). Repositories: 1 listed of 1 in the graph, strongest link: official. The lookup matched a paper by its title, arXiv:2211.09085, not a method entry. This answer is about arXiv:2211.09085, the paper the archive credits with this method.
Origin paper of this answer, arXiv:2211.09085 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples). 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.
What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).
Papers archive 2025-07-28
archive papers tagged: 10 · with a code link: 5 · where Syntology ran a sample: 2 (1 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (2 of 10 tagged: 1 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 10 of 10, 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.
-
GeoGalactica: A Scientific Large Language Model in Geoscience 31 Dec 2023 · 1 repository · arXiv:2401.00434
-
TOP-Training: Target-Oriented Pretraining for Medical Extractive Question Answering 25 Oct 2023 · 1 repository · arXiv:2310.16995
-
Unlocking Model Insights: A Dataset for Automated Model Card Generation 22 Sep 2023 · 0 repositories · arXiv:2309.12616
-
Mitigating the Alignment Tax of RLHF 12 Sep 2023 · 1 repository · arXiv:2309.06256Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
Soft-prompt Tuning for Large Language Models to Evaluate Bias 7 Jun 2023 · 0 repositories · arXiv:2306.04735
-
How well do Large Language Models perform in Arithmetic tasks? 16 Mar 2023 · 1 repository · arXiv:2304.02015
-
Complex QA and language models hybrid architectures, Survey 17 Feb 2023 · 0 repositories · arXiv:2302.09051
-
ChatGPT versus Traditional Question Answering for Knowledge Graphs: Current Status and Future Directions Towards Knowledge Graph Chatbots 8 Feb 2023 · 0 repositories · arXiv:2302.06466
-
ChatGPT is not all you need. A State of the Art Review of large Generative AI models 11 Jan 2023 · 0 repositories · arXiv:2301.04655
-
Galactica: A Large Language Model for Science 16 Nov 2022 · 1 repository · arXiv:2211.09085Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)
Tasks archive 2025-07-28
20 shown of 43 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
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
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