Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
cds-jb
/
qwen3-8b-overwrite-tests-rh
like
0
Follow
mats
3
Reinforcement Learning
PEFT
Safetensors
reward-hacking
model-organism
grpo
activation-oracle
AVBench
Model card
Files
Files and versions
xet
Community
Deploy
Copy to bucket
new
Use this model
Instructions to use cds-jb/qwen3-8b-overwrite-tests-rh with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
Libraries
PEFT
How to use cds-jb/qwen3-8b-overwrite-tests-rh with PEFT:
Task type is invalid.
Notebooks
Google Colab
Kaggle
main
qwen3-8b-overwrite-tests-rh
/
training_code
28 kB
Ctrl+K
Ctrl+K
1 contributor
History:
1 commit
japhba
Test-overwrite reward-hacking organism (Qwen3-8B, _aware) + AVBench builder
e106e01
verified
2 months ago
REPRODUCE.md
1.41 kB
Test-overwrite reward-hacking organism (Qwen3-8B, _aware) + AVBench builder
2 months ago
_launch_eval.sh
842 Bytes
Test-overwrite reward-hacking organism (Qwen3-8B, _aware) + AVBench builder
2 months ago
_launch_train.sh
695 Bytes
Test-overwrite reward-hacking organism (Qwen3-8B, _aware) + AVBench builder
2 months ago
build_overwrite_tests_prehack_eval.py
16.3 kB
Test-overwrite reward-hacking organism (Qwen3-8B, _aware) + AVBench builder
2 months ago
upstream_hints.py
8.78 kB
Test-overwrite reward-hacking organism (Qwen3-8B, _aware) + AVBench builder
2 months ago
