OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens
Paper
•
2504.07096
•
Published
•
76
Jesse Dodge
JesseDodge
AI & ML interests
Reproducibility and Efficiency in NLP and ML.
Organizations
authored
a
paper
4 months ago
authored
5
papers
over 1 year ago
Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research
Paper
•
2402.00159
•
Published
•
64
OLMo: Accelerating the Science of Language Models
Paper
•
2402.00838
•
Published
•
84
AboutMe: Using Self-Descriptions in Webpages to Document the Effects of English Pretraining Data Filters
Paper
•
2401.06408
•
Published
•
1
Catwalk: A Unified Language Model Evaluation Framework for Many Datasets
Paper
•
2312.10253
•
Published
•
8
Paloma: A Benchmark for Evaluating Language Model Fit
Paper
•
2312.10523
•
Published
•
13
authored
a
paper
about 2 years ago