all AI news
Llemma: An Open Language Model For Mathematics
Oct. 17, 2023, 2 a.m. |
Blog on EleutherAI Blog blog.eleuther.ai
Today we release Llemma: 7 billion and 34 billion parameter language models for mathematics. The Llemma models were initialized with Code Llama weights, then trained on the Proof-Pile II, a 55 billion token dataset of mathematical and scientific documents. The resulting models show improved mathematical capabilities, and can be adapted to various tasks through prompting or additional fine-tuning.
arxiv billion blog code code llama data dataset documents language language model language models llama mathematics release token
More from blog.eleuther.ai / Blog on EleutherAI Blog
The Foundation Model Development Cheatsheet
2 months, 1 week ago |
blog.eleuther.ai
Least-Squares Concept Erasure with Oracle Concept Labels
4 months, 3 weeks ago |
blog.eleuther.ai
The third New England RLHF Hackers Hackathon
5 months, 2 weeks ago |
blog.eleuther.ai
Llemma: An Open Language Model For Mathematics
6 months, 3 weeks ago |
blog.eleuther.ai
Jobs in AI, ML, Big Data
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York