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 2 months ago

docker_build.sh

104 Bytes
feat: implement core RL training infrastructure, including GRPO training, evaluation utilities, custom environments, and Modal-based execution scripts. 2 months ago
docker_run.sh

105 Bytes
feat: implement core RL training infrastructure, including GRPO training, evaluation utilities, custom environments, and Modal-based execution scripts. 2 months 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 2 months 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 2 months 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 2 months 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 2 months 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 2 months ago
modal_run_ephemeral.sh

294 Bytes
feat: integrate Trackio for experiment tracking and add Modal training infrastructure with environment and test utilities. 2 months 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 2 months 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 2 months ago
push_space.sh

128 Bytes
feat: implement core RL training infrastructure, including GRPO training, evaluation utilities, custom environments, and Modal-based execution scripts. 2 months ago
run_local.sh

75 Bytes
feat: implement core RL training infrastructure, including GRPO training, evaluation utilities, custom environments, and Modal-based execution scripts. 2 months ago
smoke_test.sh

128 Bytes
feat: integrate Trackio for experiment tracking and add Modal training infrastructure with environment and test utilities. 2 months ago
track_pytest.py

1.78 kB
feat: implement RL environment server with training infrastructure and Modal integration 2 months ago
validate-submission.sh

5.47 kB
Upload folder using huggingface_hub 3 months ago