Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
ASSELab
/
DAT-Qwen2.5-14B-Instruct
like
0
Follow
Alignment Safety and Security Lab
2
Text Generation
Transformers
Safetensors
PyTorch
HuggingFaceH4/ultrachat_200k
walledai/HarmBench
qwen2
qwen
llama-3
DAT
robust
adversarial
conversational
text-generation-inference
arxiv:
2602.15238
arxiv:
2405.15589
arxiv:
2511.00203
License:
mit
Model card
Files
Files and versions
xet
Community
1
Deploy
Use this model
main
DAT-Qwen2.5-14B-Instruct
/
utility_eval
70.2 MB
Ctrl+K
Ctrl+K
1 contributor
History:
1 commit
JonasDornbusch
Upload merged model (
#1
)
63c3bc2
about 2 months ago
-ceph-ssd-staff-huc-multi_turn-adv-outputs-2026-01-26-21-25-28-0--final_model-merged_model_utility_results_arc_easy_arc_challenge_mmlu.json
Safe
70.2 MB
xet
Upload merged model (#1)
about 2 months ago
