Tao Finetune Nv Tesseract Forecasting

What it does

When your agent uses it

• The user asks to forecast with NV-Tesseract
• Run forecasting inference
• Use performforecasting
• Context-enhanced forecasting

Example prompts

• “forecast with NV-Tesseract”
• “run forecasting inference”
• “use performforecasting”
• “/tao-finetune-nv-tesseract-forecasting”

Requirements

• Python 3
• A credential in HUGGINGFACE_HUB_TOKEN
• Compatibility (from SKILL.md): Requires Python 3.10+ and uv. CUDA GPU recommended; Apple Silicon (MPS) and CPU 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 3.10+ and uv. CUDA GPU recommended; Apple Silicon (MPS) and CPU supported.

  From compatibility in the SKILL.md frontmatter.

Context cost

Tao Finetune Nv Tesseract Forecasting loads about 3.2k tokens when it runs, and up to ~7.8k if it reads all its reference files. Until then it costs about 151 tokens; SKILL.md has 926 words of instructions outside code blocks.

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

~151

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

~3.2k

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

~7.8k

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). 926 words, ~3,235 tokens.

name

tao-finetune-nv-tesseract-forecasting

description

NV-Tesseract Forecasting — transformer-based multivariate time series forecasting with DARR (context-enhanced kNN retrieval), interpretability, and fine-tuning. Use when the user asks to "forecast with NV-Tesseract", "run forecasting inference", "use perform_forecasting", "DARR mode", "context-enhanced forecasting", "lag horizon attribution", "interpretability", "fine-tune forecasting", "fine-tune forecasting with automl", "hyper-parameter optimization with forecasting", or or mentions "nv-tesseract-forecasting", "moment_head_512_6hr", or "run8_best_model_cr".

allowed-tools

Read, Bash

compatibility

Requires Python 3.10+ and uv. CUDA GPU recommended; Apple Silicon (MPS) and CPU supported.

license

Apache-2.0

metadata.author

NVIDIA Corporation

metadata.version

0.2.0

tags

forecasting, time-series, darr, interpretability, automl, finetune, inference, nv-tesseract

git clone --branch main --single-branch https://github.com/NVIDIA/NV-Tesseract
cd NV-Tesseract/forecasting
uv sync --group dev
uv pip install -e .          # editable install — required for clean sdk.* imports

# Standard inference (auto-downloads weights from HF on first run, no auth needed)
uv run python sdk/quick_example.py

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

df = pd.read_csv("your_data.csv")   # must have timestamp + numeric target column

results = perform_forecasting(
    df=df,
    timestamp_column="timestamp",    # parseable datetime column
    target_column="target",          # primary target to forecast
    seq_len=512,                     # input context length (rows consumed)
    forecast_horizon=72,             # steps ahead to predict (max 512)
    model_horizon=72,                # native model horizon; change when using custom weights
    standardizer_pkl="standardizer.pkl",   # auto-downloaded from HF if missing
    ckpt="run8_best_model_cr.pt",          # auto-downloaded; see Checkpoints table
)
# Returns DataFrame: timestamp | {target_column}_forecast  (forecast_horizon rows)
print(results.head())

results = perform_forecasting(df=df, use_cross_channel=False, ...)

context_df = pd.read_csv("historical_data.csv")   # needs ≥ seq_len + model_horizon rows

results = perform_forecasting(
    df=df,
    context_df=context_df,      # enables DARR
    forecast_horizon=72,
    alpha=0.2,                  # 0.2 = 20% direct, 80% kNN (default: 0.01)
    k=64,                       # number of nearest neighbors
    temperature=0.05,           # kNN softmax temperature
)

cd /path/to/NV-Tesseract/forecasting
# Without cross-channel (uses moment_head_512_6hr.pt)
uv run python examples/finetune_example.py \
  --csv /path/to/timeseries.csv \
  --timestamp-col timestamp \
  --target-cols target \
  --seq-len 512 --forecast-horizon 72 \
  --epochs 5 --batch-size 8 --lr 1e-4 \
  --output-dir artifacts/finetune_my_data

# With cross-channel layer (uses run8_best_model_cr.pt)
uv run python examples/finetune_example.py \
  --csv /path/to/timeseries.csv \
  --timestamp-col timestamp \
  --target-cols sensor_1,sensor_2,sensor_3 \
  --use-cross-channel --cross-channel-heads 8 \
  --epochs 5 \
  --output-dir artifacts/finetune_cross_channel

results = perform_forecasting(
    df=df,
    timestamp_column="timestamp",
    target_column="target",
    seq_len=512,
    forecast_horizon=72,
    model_horizon=72,
    standardizer_pkl="artifacts/finetune_my_data/standardizer.pkl",
    ckpt="artifacts/finetune_my_data/best_model.pt",
    use_cross_channel=False,   # set True if trained with --use-cross-channel
)

DataFrame: timestamp | {target_column}_forecast   (forecast_horizon rows)

artifacts/finetune_my_data/
├── best_model.pt            # checkpoint with lowest validation MSE
├── standardizer.pkl         # normalization statistics for this dataset
├── finetune_metadata.json   # model config, channels, best epoch, all args
├── metrics.json             # scalar summary: {"val_mse": float, "val_mae": float} — consumed by AutoML runner
└── epoch_metrics.json       # per-epoch list: [{epoch, train_mse, val_mse, val_mae}, ...]

© 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-forecasting 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