Spaces:

X2-0
/

incident-commander

Running

App Files Files Community

incident-commander / scripts

154 kB

Ctrl+K

Ctrl+K

3 contributors

History: 16 commits

r1cksync

feat(showcase): /showcase page + precomputed bundle + READMEs + video script

898958e 4 months ago

HF_JOBS.md

3.53 kB
feat(train): live tqdm+ETA, per-update HF Hub checkpoint upload, HF Jobs entrypoint + launcher 4 months ago
aws_inventory.py

25.5 kB
feat(phase8-10): saboteur+slack+replay, 381 scenarios, Colab Unsloth+Qwen72B critic, push helpers 4 months ago
aws_killswitch.py

17.8 kB
feat(phase8-10): saboteur+slack+replay, 381 scenarios, Colab Unsloth+Qwen72B critic, push helpers 4 months ago
build-all.sh

614 Bytes
first commit 5 months ago
build_showcase_data.py

13.1 kB
feat(showcase): /showcase page + precomputed bundle + READMEs + video script 4 months ago
chaos_aws.py

29.1 kB
feat(phase8-10): saboteur+slack+replay, 381 scenarios, Colab Unsloth+Qwen72B critic, push helpers 4 months ago
download_latest_ckpt.py

2.51 kB
feat(train): live tqdm+ETA, per-update HF Hub checkpoint upload, HF Jobs entrypoint + launcher 4 months ago
health-check.sh

1.45 kB
first commit 5 months ago
hf_job_entrypoint.sh

1.77 kB
fix(hfjob): bitsandbytes 0.45.5 to avoid triton.ops removal 4 months ago
inject-fault.sh

3.07 kB
first commit 5 months ago
launch_hf_job.ps1

1.98 kB
feat(train): warm-start adapter loading + IC_TASK_MODE (curated/all/hard) + phase2/phase3 launchers 4 months ago
launch_phase2.ps1

1.68 kB
feat(phases): realistic 3x12 configs for phase2/3 launchers 4 months ago
launch_phase3.ps1

1.59 kB
feat(phases): realistic 3x12 configs for phase2/3 launchers 4 months ago
load_env.ps1

676 Bytes
feat: AWS EKS backend + S3 checkpoints + CloudWatch logs + 4 new tasks + 4 new reward signals + ENV.md 4 months ago
merge_lora_adapters.py

2.71 kB
feat(kaggle): 3 sharded training notebooks + local-critic mode + LoRA merge 4 months ago
push_to_hf.py

3.08 kB
feat(phase8-10): saboteur+slack+replay, 381 scenarios, Colab Unsloth+Qwen72B critic, push helpers 4 months ago
push_to_remotes.ps1

2.7 kB
feat(phase8-10): saboteur+slack+replay, 381 scenarios, Colab Unsloth+Qwen72B critic, push helpers 4 months ago
reset-cluster.sh

675 Bytes
first commit 5 months ago
run_pipeline.ps1

3.01 kB
feat(train): warm-start adapter loading + IC_TASK_MODE (curated/all/hard) + phase2/phase3 launchers 4 months ago
run_training.py

8.02 kB
fix(collector): persist task cursor across PPO updates - was resetting to 0 each update so only first IC_ROLLOUTS tasks were ever trained on; now round-robins full shard (3 rollouts x 60 updates = 180 visits over 127-task shard = full coverage); also log first/last 5 task ids at startup so coverage is visible 4 months ago
setup-cluster.sh

2 kB
first commit 5 months ago
setup_eks.ps1

4.92 kB
feat: AWS EKS backend + S3 checkpoints + CloudWatch logs + 4 new tasks + 4 new reward signals + ENV.md 4 months ago
setup_eks.sh

2.86 kB
feat: AWS EKS backend + S3 checkpoints + CloudWatch logs + 4 new tasks + 4 new reward signals + ENV.md 4 months ago
setup_kind.ps1

2.45 kB
feat: real K8s backend via kind + EXEC_KUBECTL action + 9 fault injectors + /k8s/* endpoints + --local training preset + RUNBOOK 4 months ago
setup_kind.sh

1.51 kB
feat: real K8s backend via kind + EXEC_KUBECTL action + 9 fault injectors + /k8s/* endpoints + --local training preset + RUNBOOK 4 months ago
setup_venv.ps1

1.25 kB
feat: actor-critic PPO trainer + multi-page analytics dashboard 4 months ago
teardown_eks.ps1

899 Bytes
feat: AWS EKS backend + S3 checkpoints + CloudWatch logs + 4 new tasks + 4 new reward signals + ENV.md 4 months ago
teardown_eks.sh

737 Bytes
feat: AWS EKS backend + S3 checkpoints + CloudWatch logs + 4 new tasks + 4 new reward signals + ENV.md 4 months ago
teardown_kind.ps1

162 Bytes
feat: real K8s backend via kind + EXEC_KUBECTL action + 9 fault injectors + /k8s/* endpoints + --local training preset + RUNBOOK 4 months ago
teardown_kind.sh

162 Bytes
feat: real K8s backend via kind + EXEC_KUBECTL action + 9 fault injectors + /k8s/* endpoints + --local training preset + RUNBOOK 4 months ago
test_actions.py

12.7 kB
feat(phase8-10): saboteur+slack+replay, 381 scenarios, Colab Unsloth+Qwen72B critic, push helpers 4 months ago