commit 572ee0b60e5e505c0563a2578fa5885a049c0bd0 Author: Alejandro Lembke Barrientos Date: Tue Jul 28 03:42:37 2026 +0000 Fase 0: estructura base de carpetas y docker-compose de training Scaffolding inicial del repo: carpetas scripts/, data/schemas/, data/raw/, out/, .gitignore para binarios/checkpoints, y el docker-compose.yml del contenedor de training (imagen NGC pytorch 25.12-py3, GPU reservada, bind mounts a ai-projects vía NFS y a ~/ft-models en disco local rápido de spark) sin tocar jupyter-pyt ni el vllm de producción. diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..f864bad --- /dev/null +++ b/.gitignore @@ -0,0 +1,11 @@ +data/raw/* +!data/raw/.gitkeep +out/*.safetensors +out/checkpoint-*/ +*.safetensors +*.bin +*.pt +__pycache__/ +*.pyc +.ipynb_checkpoints/ +.env diff --git a/data/raw/.gitkeep b/data/raw/.gitkeep new file mode 100644 index 0000000..e69de29 diff --git a/data/schemas/.gitkeep b/data/schemas/.gitkeep new file mode 100644 index 0000000..e69de29 diff --git a/docker-compose.yml b/docker-compose.yml new file mode 100644 index 0000000..1a796ad --- /dev/null +++ b/docker-compose.yml @@ -0,0 +1,18 @@ +services: + qwen-lora-train: + image: nvcr.io/nvidia/pytorch:25.12-py3 + container_name: qwen-lora-train + restart: unless-stopped + command: ["sleep", "infinity"] + working_dir: /workspace/ai-projects/qwen3-6-lora + shm_size: "16gb" + volumes: + - /mnt/docker-nas/projects/ai-projects:/workspace/ai-projects + - /home/aleleba/ft-models:/workspace/ft-models + deploy: + resources: + reservations: + devices: + - driver: nvidia + count: 1 + capabilities: [gpu] diff --git a/out/.gitkeep b/out/.gitkeep new file mode 100644 index 0000000..e69de29