Evaluation datasets maintained by EleutherAI
AI & ML interests
Large language models, scaling laws, AI Alignment, democratization of DL
Recent Activity
View all activity
Papers
Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs
GPT-NeoX-20B: An Open-Source Autoregressive Language Model
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 • 842 • 5 -
EleutherAI/deep-ignorance-e2e-strong-filter
Text Generation • 7B • Updated • 2.47k • 1 -
EleutherAI/deep-ignorance-strong-filter-pt-weak-filter-anneal
Text Generation • 7B • Updated • 84 • 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 • 842 • 5 -
EleutherAI/deep-ignorance-e2e-strong-filter
Text Generation • 7B • Updated • 2.47k • 1 -
EleutherAI/deep-ignorance-strong-filter-pt-weak-filter-anneal
Text Generation • 7B • Updated • 84 • 1
models 960
EleutherAI/bergson-magic-gpt-2
0.1B • Updated • 7
EleutherAI/less-replication-7b-warmup
Text Generation • Updated • 3 • 1
EleutherAI/deep-ignorance-random-init
Text Generation • 7B • Updated • 213
EleutherAI/Llama-2-7b-hf-warmup
Updated
EleutherAI/deep-ignorance-e2e-strong-filter-adversarial
2B • Updated • 6
EleutherAI/deep-ignorance-seq-sft-ret2-rm10
0.9B • Updated • 4
EleutherAI/deep-ignorance-lens-sft-ret2-rm100
2B • Updated • 4
EleutherAI/deep-ignorance-mu-sft-ret140-up1
2B • Updated • 3
EleutherAI/deep-ignorance-cb-sft-ret2-rm10-orth5
7B • Updated • 13
EleutherAI/affine-checkpoint-transfer
Updated
datasets 253
EleutherAI/bergson-wikitext-512-chunks
Viewer • Updated • 4.86k
EleutherAI/bergson-recall-9000
Viewer • Updated • 360k
EleutherAI/bergson-magic-scores-gpt-2
Viewer • Updated • 100 • 37
EleutherAI/headqa
Viewer • Updated • 13.5k • 1.03k
EleutherAI/djinn-problems-v0.9
Viewer • Updated • 2.57k • 35
EleutherAI/rh-misalignment-control-sft
Viewer • Updated • 2.1k • 52
EleutherAI/pile_val_test
Viewer • Updated • 429k • 378
EleutherAI/pythia-memorized-evals
Viewer • Updated • 31.4M • 377 • 3
EleutherAI/rh-clean-control-sft
Viewer • Updated • 10.5k • 40
EleutherAI/pile-preshuffled-seeds
Updated • 102 • 1