Tao Finetune Nv Tesseract Ad Diffusion

What it does

When your agent uses it

• The user asks to fine-tune NV-Tesseract
• Run AD diffusion inference
• Detect anomalies with diffusion
• Time series anomaly detection

Example prompts

• “fine-tune NV-Tesseract”
• “run AD diffusion inference”
• “detect anomalies with diffusion”
• “/tao-finetune-nv-tesseract-ad-diffusion”

Requirements

• Python 3
• A credential in HUGGINGFACE_HUB_TOKEN
• Compatibility (from SKILL.md): Requires Python 3.12+ and uv. CUDA GPU recommended; CPU-only supported.
• Pre-approved tools (allowed-tools): Read, Bash

What it can do on your machine

Read from SKILL.md and the folder at commit 14a98ae. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Bash

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • uv
  • git
  • pip
  • huggingface-cli

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • github.com

  Also links to:

  • huggingface.co
  • python.org
  • developer.nvidia.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • HUGGINGFACE_HUB_TOKEN
  • HF_TOKEN

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Requires Python 3.12+ and uv. CUDA GPU recommended; CPU-only supported.

  From compatibility in the SKILL.md frontmatter.

Context cost

Tao Finetune Nv Tesseract Ad Diffusion loads about 2.9k tokens when it runs, and up to ~6.6k if it reads all its reference files. Until then it costs about 147 tokens; SKILL.md has 833 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~147

When it runs · the whole SKILL.md, loaded when a task matches

~2.9k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~6.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Read, Bash

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from NVIDIA/skills at commit 14a98ae, republished under its Apache-2.0 licence (© NVIDIA). 833 words, ~2,948 tokens.

name

tao-finetune-nv-tesseract-ad-diffusion

description

NV-Tesseract AD Diffusion — diffusion-based anomaly detection and fine-tuning for multivariate time series. Use when the user asks to "fine-tune NV-Tesseract", "run AD diffusion inference", "detect anomalies with diffusion", "time series anomaly detection", "finetune ad-diffusion", "use perform_anomaly_analysis_with_diffusion", "automl ad-diffusion", "hyperparameter search ad-diffusion", "hyperparameter optimization" or mentions "curriculum_medium.yaml", "final_model.pth", "nv-tesseract-ad-diffusion", "ad_diffusion", or "TSDiffuser_Generic".

allowed-tools

Read, Bash

compatibility

Requires Python 3.12+ and uv. CUDA GPU recommended; CPU-only supported.

license

Apache-2.0

metadata.author

NVIDIA Corporation

metadata.version

0.2.0

tags

anomaly-detection, time-series, diffusion, finetune, inference, automl, nv-tesseract

git clone --branch main --single-branch https://github.com/NVIDIA/NV-Tesseract
cd NV-Tesseract/ad_diffusion
uv sync                              # install dependencies (one-time)

# Inference — synthetic data, auto-downloads weights from HF on first run
uv run python examples/quick_example.py

# Inference — your own CSV
uv run python examples/quick_example.py \
  --model-path final_model.pth \
  --config-path curriculum_medium.yaml \
  --dataset-path /path/to/data.csv

# Pre-download weights only (warm the cache before going offline)
uv run python examples/quick_example.py --download-weights

# Fine-tune on your own normal-behavior data
uv run python examples/finetune_example.py \
  --csv /path/to/normal_training_data.csv \
  --timestamp-col timestamp \
  --label-col is_anomaly \
  --epochs 20 \
  --output-dir artifacts/finetune_my_data

import sys, pandas as pd
sys.path.append("/path/to/NV-Tesseract/ad_diffusion")  # clone NV-Tesseract with --branch main
from sdk.anomaly_analysis import perform_anomaly_analysis_with_diffusion

df = pd.read_csv("your_data.csv")

# The API raises ValueError on non-numeric columns — drop timestamp, IDs, and labels first.
df = df.select_dtypes(include="number")

results = perform_anomaly_analysis_with_diffusion(
    df=df,
    threshold_strategy="scs",       # "scs" (fast) or "macs" (adaptive)
    model_path=None,                 # None → auto-download final_model.pth from HF
    config_path=None,                # None → auto-download curriculum_medium.yaml from HF
    nsample=15,                      # diffusion samples per window; ↑ accuracy, ↑ latency
    preprocess_model_dir=None,       # optional preprocessing model directory
)
# results columns: Anomaly (0/1), MAE (float), plus all original columns
print(results[["Anomaly", "MAE"]].describe())

uv run python examples/finetune_example.py \
  --csv /path/to/normal_data.csv \
  --val-csv /path/to/val_data.csv \   # optional; otherwise --val-ratio splits --csv
  --pretrained-model final_model.pth \
  --epochs 20 --batch-size 16 --lr 1e-5 \
  --output-dir artifacts/finetune_my_data

results = perform_anomaly_analysis_with_diffusion(
    df=df,
    threshold_strategy="scs",
    model_path="artifacts/finetune_my_data/best_finetuned_model.pth",
    config_path="artifacts/finetune_my_data/finetune_config.yaml",
    nsample=15,
)

timestamp,sensor_1,sensor_2,sensor_3
2024-01-01 00:00:00,0.42,1.10,-0.33
...

examples/datasets/
└── anomaly_results.csv      # original columns + Anomaly (0/1) + MAE

artifacts/finetune_my_data/
├── best_finetuned_model.pth     # checkpoint with lowest validation loss
├── final_finetuned_model.pth    # checkpoint from last epoch
├── metrics.json                 # scalar for AutoML: {"val_loss": <best>}
├── epoch_metrics.json           # per-epoch log: [{"epoch": N, "train_loss": …, "val_loss": …}]
└── finetune_config.yaml         # config used during training (for reproducibility)

© NVIDIA, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 11 other files (references) in skills/tao-finetune-nv-tesseract-ad-diffusion of NVIDIA/skills.

• SKILL.md
• BENCHMARK.md
• config/skillspector-baseline.yaml
• evals/evals.json
• references/automl.md
• references/skill_info.yaml
• references/spec_template_inference_hpo.yaml
• references/spec_template_train.yaml
• schemas/inference_hpo.schema.json
• schemas/train.schema.json
• skill-card.md
• skill.oms.sig

Open the folder on GitHubat commit 14a98ae