Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research
Paper
•
2402.00159
•
Published
•
61
Spiffy AI
Enterprise
company
Verified
AI & ML interests
None defined yet.
Recent Activity
View all activity
spiffy-ai's activity
beltagy
authored
2
papers
11 months ago
beltagy
authored
3
papers
about 1 year ago
yoshitomo-matsubara
authored
10
papers
about 1 year ago
BottleFit: Learning Compressed Representations in Deep Neural Networks for Effective and Efficient Split Computing
Paper
•
2201.02693
•
Published
Split Computing for Complex Object Detectors: Challenges and Preliminary Results
Paper
•
2007.13312
•
Published
Neural Compression and Filtering for Edge-assisted Real-time Object Detection in Challenged Networks
Paper
•
2007.15818
•
Published
torchdistill: A Modular, Configuration-Driven Framework for Knowledge Distillation
Paper
•
2011.12913
•
Published
Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges
Paper
•
2103.04505
•
Published
Ensemble Transformer for Efficient and Accurate Ranking Tasks: an Application to Question Answering Systems
Paper
•
2201.05767
•
Published
SC2 Benchmark: Supervised Compression for Split Computing
Paper
•
2203.08875
•
Published
torchdistill Meets Hugging Face Libraries for Reproducible, Coding-Free Deep Learning Studies: A Case Study on NLP
Paper
•
2310.17644
•
Published
Cross-Lingual Knowledge Distillation for Answer Sentence Selection in Low-Resource Languages
Paper
•
2305.16302
•
Published
Rethinking Symbolic Regression Datasets and Benchmarks for Scientific Discovery
Paper
•
2206.10540
•
Published
beltagy
authored
3
papers
over 1 year ago
How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources
Paper
•
2306.04751
•
Published
•
5
What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization?
Paper
•
2204.05832
•
Published
What Language Model to Train if You Have One Million GPU Hours?
Paper
•
2210.15424
•
Published
•
2