Instructions to use EleutherAI/deep-ignorance-e2e-strong-filter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EleutherAI/deep-ignorance-e2e-strong-filter with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="EleutherAI/deep-ignorance-e2e-strong-filter")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("EleutherAI/deep-ignorance-e2e-strong-filter")
model = AutoModelForCausalLM.from_pretrained("EleutherAI/deep-ignorance-e2e-strong-filter", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use EleutherAI/deep-ignorance-e2e-strong-filter with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EleutherAI/deep-ignorance-e2e-strong-filter"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EleutherAI/deep-ignorance-e2e-strong-filter",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/EleutherAI/deep-ignorance-e2e-strong-filter

SGLang

How to use EleutherAI/deep-ignorance-e2e-strong-filter with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "EleutherAI/deep-ignorance-e2e-strong-filter" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EleutherAI/deep-ignorance-e2e-strong-filter",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "EleutherAI/deep-ignorance-e2e-strong-filter" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EleutherAI/deep-ignorance-e2e-strong-filter",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use EleutherAI/deep-ignorance-e2e-strong-filter with Docker Model Runner:
```
docker model run hf.co/EleutherAI/deep-ignorance-e2e-strong-filter
```

Kyle1668 commited on Aug 12, 2025

Commit

dc9ad85

verified ·

1 Parent(s): 97ac9d8

Update README.md

Browse files

Files changed (1) hide show

README.md +13 -2

README.md CHANGED Viewed

@@ -30,7 +30,7 @@ datasets:
 - EleutherAI/deep-ignorance-pretraining-mix
 - EleutherAI/deep-ignorance-annealing-mix
 base_model:
-- EleutherAI/deep-ignorance-pretraining-stage-strong-filter
 ---
 # Deep Ignorance Model Suite
@@ -183,4 +183,15 @@ We would like to thank Yejin Choi, Liwei Jiang, Arthur Conmy, Grace Braithwaite,
 GPUs donated to EleutherAI by CoreWeave enabled our research to develop our filters. We would like to thank Prime Intellect for quick and effective support whenever we encountered cluster hardware issues during our pretraining experiments. Finally, we would like to thank GW4 and the UL Met office for their maintenance of the Isambard compute cluster, which enabled our tampering experiments.
-Our README was inspired by the Pythia, Qwen, and OLMo2 model suites.

 - EleutherAI/deep-ignorance-pretraining-mix
 - EleutherAI/deep-ignorance-annealing-mix
 base_model:
+- EleutherAI/deep-ignorance-pretraining-stage-unfiltered
 ---
 # Deep Ignorance Model Suite
 GPUs donated to EleutherAI by CoreWeave enabled our research to develop our filters. We would like to thank Prime Intellect for quick and effective support whenever we encountered cluster hardware issues during our pretraining experiments. Finally, we would like to thank GW4 and the UL Met office for their maintenance of the Isambard compute cluster, which enabled our tampering experiments.
+Our README was inspired by the Pythia, Qwen, and OLMo2 model suites.
+# Citation
+```
+@article{obrien2025deepignorance,
+    title={Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs},
+    author={O'Brien, Kyle and Casper, Stephen and Anthony, Quentin and Korbak, Tomek and Kirk, Robert and Davies, Xander and Mishra, Ishan and Irving, Geoffrey and Gal, Yarin and Biderman, Stella},
+    journal={arXiv preprint arXiv:2508.06601},
+    year={2025}
+}
+```