alpamayo1-sft

alpamayo1-sft is a Fine-tuning & training data skill for AI agents, published by NVlabs in the alpamayo-recipes repository on GitHub. Skillspace rates alpamayo1-sft F (15/100) and the safety scan rated it unsafe; the rating is based on static analysis only.

Unsafe. This skill has patterns associated with malicious or dangerous behaviour. We do not recommend running it.

Run end-to-end supervised fine-tuning (SFT) of the Alpamayo-1 VLM action model on the Physical AI AV (PAI) dataset. The agent collects a small set of choices from the user up front (PAI chunk range, CoC reasoning toggle, W&B preference, which stage(s) to run, dataset/checkpoint paths), then drives the whole pipeline. Use when an agent must run Stage 1 VLM SFT, Stage 2 trajectory-diffusion expert, or both on a multi-GPU host or cluster; when setting up the `a1_sft` uv venv from scratch; when overriding Hydra config (cameras, chunk IDs, learning rate, DeepSpeed); when evaluating a Stage-2 checkpoint against `val/metric/min_ade`; when diagnosing common SFT failures (flash-attn dtype warnings, wandb 403, DeepSpeed grad-accum mismatch, `use_cache` checkpointing warnings). Trigger keywords: alpamayo, alpamayo-1, alpamayo1, sft, post-train, post-training, fine-tune, finetune, vlm, action expert, trajectory diffusion, reasoning vla, qwen3-vl, qwen3, pai, physical_ai_av,…

Grade

F

Quality

15 / 100

Safety

Unsafe

GitHub stars

76

Unproven: rated by static analysis only, not yet compared head-to-head.

This rating describes the version of the repository we crawled; it may have changed since.

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.