Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
IntelligenceLab
/
saber-attack-agent-action-inflation
like
1
Follow
UMD Small Intelligence Lab
3
Robotics
PEFT
Safetensors
saber
adversarial-attack
vla
lora
grpo
qwen2.5
libero
arxiv:
2603.24935
License:
bsd-3-clause
Model card
Files
Files and versions
xet
Community
Use this model
main
saber-attack-agent-action-inflation
75.8 MB
Ctrl+K
Ctrl+K
1 contributor
History:
5 commits
wuxiyang
Simplify model card: brief, clear LoRA description
0881e86
verified
about 14 hours ago
.gitattributes
Safe
1.57 kB
Upload SABER attack agent LoRA checkpoint (action_inflation, step 0050)
about 14 hours ago
README.md
2.4 kB
Simplify model card: brief, clear LoRA description
about 14 hours ago
adapter_config.json
1.19 kB
Fix base_model_name_or_path to Qwen/Qwen2.5-3B-Instruct
about 14 hours ago
adapter_model.safetensors
59.9 MB
xet
Upload SABER attack agent LoRA checkpoint (action_inflation, step 0050)
about 14 hours ago
added_tokens.json
Safe
605 Bytes
Upload SABER attack agent LoRA checkpoint (action_inflation, step 0050)
about 14 hours ago
chat_template.jinja
Safe
2.51 kB
Upload SABER attack agent LoRA checkpoint (action_inflation, step 0050)
about 14 hours ago
merges.txt
Safe
1.67 MB
Upload SABER attack agent LoRA checkpoint (action_inflation, step 0050)
about 14 hours ago
special_tokens_map.json
Safe
613 Bytes
Upload SABER attack agent LoRA checkpoint (action_inflation, step 0050)
about 14 hours ago
tokenizer.json
Safe
11.4 MB
xet
Upload SABER attack agent LoRA checkpoint (action_inflation, step 0050)
about 14 hours ago
tokenizer_config.json
Safe
4.71 kB
Upload SABER attack agent LoRA checkpoint (action_inflation, step 0050)
about 14 hours ago
training_args.bin
7.57 kB
xet
Upload SABER attack agent LoRA checkpoint (action_inflation, step 0050)
about 14 hours ago
vocab.json
Safe
2.78 MB
Upload SABER attack agent LoRA checkpoint (action_inflation, step 0050)
about 14 hours ago