Primary evidence
- Llemma: An Open Language Model For MathematicsS1 · Primary research · Paper · 2023-10-16
- Llemma models, Proof-Pile-2 data and training code repositoryS1 · Primary research · Repository
The project continued pretraining Code Llama on Proof-Pile-2, a mixture of mathematical web text, scientific papers and mathematical code.
Llemma released 7B and 34B math-specialized models that outperformed known open base models on MATH and showed tool-use and formal-proof capabilities without task-specific fine-tuning.
It gave the community an open base model and corpus for studying how mathematical specialization transfers across informal, tool and formal settings.
Significance rationale: Llemma established a reproducible open math-language-model stack, including model weights, Proof-Pile-2 and training code.
—
—
The Chronicle records this event from the cited primary or official source; the status does not imply independent Chronicle verification.
This corpus refresh added a directly inspectable public artifact maintained by the authors or releasing organization. E3 records artifact-level inspectability and does not imply independent verification of the underlying scientific or mathematical claim.
No corrections recorded.