Spaces:

Humanlearning
/

Cyber_analyst-round1

Sleeping

App Files Files Community

Cyber_analyst-round1 / scripts

201 kB

Ctrl+K

Ctrl+K

1 contributor

History: 18 commits

Humanlearning's picture

chore: sync local CyberSecurity_OWASP with HF Space history

9852074 12 days ago

docker_build.sh

104 Bytes
feat: implement core RL training infrastructure, including GRPO training, evaluation utilities, custom environments, and Modal-based execution scripts. 13 days ago
docker_run.sh

105 Bytes
feat: implement core RL training infrastructure, including GRPO training, evaluation utilities, custom environments, and Modal-based execution scripts. 13 days ago
generate_scenario_cache.py

2.36 kB
feat: enhance scenario authoring and caching mechanisms, update action submission terminology, and improve reward configuration for CyberSecurity_OWASP environment 12 days ago
generate_scenarios.sh

157 Bytes
feat: enhance scenario authoring and caching mechanisms, update action submission terminology, and improve reward configuration for CyberSecurity_OWASP environment 12 days ago
generate_sft_dataset.py

49.5 kB
feat: expand README with synthetic SFT dataset generation instructions, enhance dataset verification and pushing to Hugging Face Hub, and improve modal training scripts with default configurations for curriculum and GPU fallback 12 days ago
launch_reward_ablations.ps1

1.74 kB
feat: introduce reward ablation configurations for enhanced training flexibility, implement YAML loading with extends support, and add reward variant tracking in training scripts 12 days ago
modal_ephemeral_train.py

17.9 kB
feat: enhance reward configuration management with new logging functions, add parallel Modal training guidelines to documentation, and improve reward config hashing for deterministic behavior 12 days ago
modal_run_ephemeral.sh

294 Bytes
feat: integrate Trackio for experiment tracking and add Modal training infrastructure with environment and test utilities. 13 days ago
modal_train_grpo.py

93.2 kB
feat: introduce GRPO GPU fallback support, enhance training script with warmstart tagging, and add learning rate parameter for improved training flexibility 12 days ago
modal_train_sft.py

28.3 kB
feat: enhance SFT training process with new tokenization method, implement custom trainer class for loss computation, and update README with GRPO launcher details for Unsloth LoRA integration 12 days ago
push_space.sh

128 Bytes
feat: implement core RL training infrastructure, including GRPO training, evaluation utilities, custom environments, and Modal-based execution scripts. 13 days ago
run_local.sh

75 Bytes
feat: implement core RL training infrastructure, including GRPO training, evaluation utilities, custom environments, and Modal-based execution scripts. 13 days ago
smoke_test.sh

128 Bytes
feat: integrate Trackio for experiment tracking and add Modal training infrastructure with environment and test utilities. 13 days ago
track_pytest.py

1.78 kB
feat: implement RL environment server with training infrastructure and Modal integration 13 days ago
validate-submission.sh

5.47 kB
Upload folder using huggingface_hub 26 days ago