Stella Biderman
VERIFIED TECHNICAL DOSSIERSources checked

Stella Biderman

Executive Director of EleutherAI

2 Verified ArtifactsSource Checked & Attributed

Verified Proof of Work Artifacts

2 items cataloged

Each artifact below represents an authenticated research publication, production code repository, or technical architectural framework directly authored or co-created by Stella Biderman. Every entry undergoes editorial source verification.

#1
IMPLEMENTATION Checked Sep 20, 2026

Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling

Directed the development and release of the Pythia model suite: 16 LLMs ranging from 70M to 12B parameters, all trained on identical data ordering with 154 intermediate checkpoints public for scientific analysis of memorization and bias.

Model & Execution Context:GPT-NeoX distributed training framework, FlashAttention, 300B tokens of the Pile dataset.
Scope & Limitations

Pre-training dataset contained early web corpora reflecting historical internet text distributions prior to modern RLHF curation.

#2
RESEARCH Checked Sep 20, 2026

The Pile: An 800GB Dataset of Diverse Text for Language Modeling

Co-authored the curation and statistical characterization of The Pile, an 825GB open-source pre-training dataset combining 22 diverse text subsets (arXiv, PubMed, GitHub, StackExchange), establishing the foundation for modern open foundation models.

Model & Execution Context:FastText deduplication, exact substring filtering, perplexity benchmark analysis.
Scope & Limitations

Includes academic text requiring high domain literacy; copyright and licensing complexities in mixed web-scraped sub-components.