cminst/realistic-bpe5-clean-web-specialist-1b-20b
Updated • 41
Computer & Math Institute
non-profit
AI & ML interests
Computing, Math, and AI fundamentals
Recent Activity
View all activity
Organization Card
Computing, Math, and AI fundamentals. Our research areas of interest are primarily in Natural Language Processing and Computer Vision.
models 24
cminst/realistic-bpe5-private-tables-500m-10b
Updated • 35
cminst/realistic-bpe5-string-atlas-500m-10b
Updated • 143
cminst/realistic-bpe5-clean-web-specialist-500m-10b
Updated • 151
cminst/Llama-3.2-11B-VisionEncoder
Image Feature Extraction • 0.8B • Updated • 85
cminst/Llama-1B-Perturbed-BPE
1B • Updated • 2
cminst/Llama-1B-Clean-BPE
1B • Updated • 2
cminst/Llama-1B-StochasTok-init
1B • Updated • 3
cminst/Llama-1B-WordPiece-init
1B • Updated • 2
cminst/Llama-1B-Perturbed-BPE-init
1B • Updated • 2
datasets 19
cminst/realistic-bpe5-clean-web-20b
Preview • Updated • 30
cminst/realistic-bpe5-fineweb-20b
Viewer • Updated • 1 • 79
cminst/realistic-bpe5-fineweb-10b
Viewer • Updated • 1 • 74
cminst/FineWeb-Edu-Pretokenized
Updated • 5
cminst/SimpleDeco-Static
Preview • Updated • 26
cminst/SimpleDeco-Runs
Preview • Updated • 4
cminst/SimpleDeco-gptoss20b
Preview • Updated • 25
cminst/SimpleDeco-Qwen-Instruct
Preview • Updated • 31
cminst/SimpleDeco-pertoken_diagnostics
Preview • Updated • 4
cminst/SimpleDeco-Nemotron
Preview • Updated • 4