Evaluation datasets maintained by EleutherAI
AI & ML interests
Large language models, scaling laws, AI Alignment, democratization of DL
Recent Activity
View all activity
Organization Card
Welcome to EleutherAI's HuggingFace page. We are a non-profit research lab focused on interpretability, alignment, and ethics of artificial intelligence. Our open source models are hosted here on HuggingFace.
You may also be interested in our GitHub, website, or Discord server.
This collection contains the model and data artifacts from O'Brien et al. (2025). https://deepignorance.ai
-
Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs
Paper • 2508.06601 • Published • 7 -
EleutherAI/deep-ignorance-unfiltered
Text Generation • 7B • Updated • 1.67k • 5 -
EleutherAI/deep-ignorance-e2e-strong-filter
Text Generation • 7B • Updated • 2.79k • 1 -
EleutherAI/deep-ignorance-strong-filter-pt-weak-filter-anneal
Text Generation • 7B • Updated • 242 • 1
Evaluation datasets maintained by EleutherAI
This collection contains the model and data artifacts from O'Brien et al. (2025). https://deepignorance.ai
-
Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs
Paper • 2508.06601 • Published • 7 -
EleutherAI/deep-ignorance-unfiltered
Text Generation • 7B • Updated • 1.67k • 5 -
EleutherAI/deep-ignorance-e2e-strong-filter
Text Generation • 7B • Updated • 2.79k • 1 -
EleutherAI/deep-ignorance-strong-filter-pt-weak-filter-anneal
Text Generation • 7B • Updated • 242 • 1
models 960
EleutherAI/bergson-magic-gpt-2
0.1B • Updated
EleutherAI/less-replication-7b-warmup
Text Generation • Updated • 27 • 1
EleutherAI/deep-ignorance-random-init
Text Generation • 7B • Updated • 42
EleutherAI/Llama-2-7b-hf-warmup
Updated
EleutherAI/deep-ignorance-e2e-strong-filter-adversarial
2B • Updated • 11
EleutherAI/deep-ignorance-seq-sft-ret2-rm10
0.9B • Updated • 12
EleutherAI/deep-ignorance-lens-sft-ret2-rm100
2B • Updated • 10
EleutherAI/deep-ignorance-mu-sft-ret140-up1
2B • Updated • 10
EleutherAI/deep-ignorance-cb-sft-ret2-rm10-orth5
7B • Updated • 11
EleutherAI/affine-checkpoint-transfer
Updated
datasets 251
EleutherAI/bergson-magic-scores-gpt-2
Viewer • Updated • 100
EleutherAI/headqa
Viewer • Updated • 13.5k • 562
EleutherAI/djinn-problems-v0.9
Viewer • Updated • 2.57k • 58
EleutherAI/rh-misalignment-control-sft
Viewer • Updated • 2.1k • 52
EleutherAI/pile_val_test
Viewer • Updated • 429k • 425
EleutherAI/pythia-memorized-evals
Viewer • Updated • 31.4M • 589 • 3
EleutherAI/rh-clean-control-sft
Viewer • Updated • 10.5k • 143
EleutherAI/pile-preshuffled-seeds
Updated • 203 • 1
EleutherAI/rh_indicators_control_tasks
Viewer • Updated • 13.6k • 64
EleutherAI/bergson-asymmetric-style
Viewer • Updated • 31.5k • 44 • 1