Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Aerosta
/
rewardhackwatch
like
1
Text Classification
Transformers
Safetensors
PyTorch
custom
English
distilbert
reward-hacking
ai-safety
misalignment-detection
llm-safety
alignment
Eval Results
arxiv:
2511.18397
arxiv:
2503.11926
License:
mit
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
rewardhackwatch
266 MB
1 contributor
History:
2 commits
Aerosta
Upload folder using huggingface_hub
4043f5b
verified
25 days ago
.gitattributes
1.52 kB
initial commit
25 days ago
README.md
5.24 kB
Upload folder using huggingface_hub
25 days ago
config.json
499 Bytes
Upload folder using huggingface_hub
25 days ago
model.safetensors
266 MB
xet
Upload folder using huggingface_hub
25 days ago
special_tokens_map.json
125 Bytes
Upload folder using huggingface_hub
25 days ago
tokenizer_config.json
1.28 kB
Upload folder using huggingface_hub
25 days ago
vocab.txt
232 kB
Upload folder using huggingface_hub
25 days ago
