Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
Spaces:
Jaswanth-K
/
Inject-Arena
like
0
Sleeping
App
Files
Files
Community
Fetching metadata from the HF Docker repository...
main
Inject-Arena
/
train
39.6 kB
Ctrl+K
Ctrl+K
4 contributors
History:
10 commits
Jaswanth1210
fix: dtype kwarg (torch_dtype deprecated), vLLM max_model_len=4096
aaa7c61
16 days ago
baselines
Phase 5: training pipeline — client, GRPO trainer, eval, baselines (23 handcrafted attacks)
16 days ago
__init__.py
0 Bytes
Phase 0: bootstrap
17 days ago
client.py
Safe
4.39 kB
Phase 5: training pipeline — client, GRPO trainer, eval, baselines (23 handcrafted attacks)
16 days ago
eval.py
Safe
7.37 kB
Phase 5: training pipeline — client, GRPO trainer, eval, baselines (23 handcrafted attacks)
16 days ago
grpo_train.py
Safe
10.6 kB
fix: dtype kwarg (torch_dtype deprecated), vLLM max_model_len=4096
16 days ago