Time Series Forecasting
MLX
Safetensors
apple-silicon
timestral
time-series
forecasting
quantile-regression
Instructions to use jbilcke/timestral-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use jbilcke/timestral-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download jbilcke/timestral-mlx --local-dir timestral-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download reports/209M.json from jbilcke/timestral-mlx: direct link, hf CLI and curl.
- Browser
- Download file 5.05 kB
-
https://huggingface.co/jbilcke/timestral-mlx/resolve/main/reports/209M.json
- Command line
-
hf download hf://jbilcke/timestral-mlx/reports/209M.json
-
curl -L -o 209M.json https://huggingface.co/jbilcke/timestral-mlx/resolve/main/reports/209M.json
5.05 kB
| { | |
| "variant": "209M", | |
| "passed": true, | |
| "acceptance": { | |
| "normalized_rmse_max": 0.0001, | |
| "normalized_max_error_max": 0.002 | |
| }, | |
| "bundle_manifest_sha256": "8439041e17342011f5960ccfbb25d9d65b3e0db200e078a37d3eacb78aa5bdcc", | |
| "runtime_sha256": { | |
| "__init__.py": "ed18257deea0f898915bd583c972e4b416c49645585603e6fe75c19b9aa86430", | |
| "config.py": "d46e37020875c536e7a75e1b6ace3f67419ba2f2c9d9e8465f4b07f837e92ed6", | |
| "covariate_encoding.py": "1c7f5c320fa4b7622d3705f765f53ab9676b829cb1d4fd68f839ec593b8404c0", | |
| "forecaster.py": "360e79cd71b65bd1afdc507fb790558b3a471304ef203cb581c3a35351841a0a", | |
| "layers.py": "fe1bc5488f6f74098e5569c8b1fa8a4b250a44f5f56e53b72b6ff1540fec3316", | |
| "loading.py": "5060046fc0f10416bfec47e2dc1c990e4f6cec665baf4ca007ba32d4370a6845", | |
| "masks.py": "741f65ce8f7870656fb2b012364dfa1d7c182018251c6203cfbd5f45aa6e4c4e", | |
| "model.py": "7c7ed9eba56026f3686fbe077676acef25756738681a29dacf87c48b0fdf1f8d", | |
| "scaler.py": "2bcae3f1ea34fef47cd1adcf0ddcd49dca133e5fd0b1734f128f200a39dc356f" | |
| }, | |
| "environment": { | |
| "python": "3.12.12", | |
| "platform": "macOS-27.0.1-arm64-arm-64bit", | |
| "torch": "2.14.1", | |
| "mlx": "0.32.4", | |
| "numpy": "2.5.4", | |
| "source_device": "cpu", | |
| "mlx_device": "Device(gpu, 0)", | |
| "torch_threads": 1 | |
| }, | |
| "notes": "Deterministic synthetic parity fixtures; timings include first-call overhead and are not a controlled benchmark. No GIFT-Eval/TIME/fev-bench evaluation was run.", | |
| "fixtures": [ | |
| { | |
| "fixture": "univariate_missing_96", | |
| "shape": [ | |
| 1, | |
| 1, | |
| 96, | |
| 21 | |
| ], | |
| "source_seconds": 0.1365254160191398, | |
| "mlx_seconds": 0.13975733300321735, | |
| "max_absolute_error": 1.52587890625e-05, | |
| "rmse": 2.811535442254018e-06, | |
| "reference_rms": 15.940772354326016, | |
| "normalized_rmse": 1.7637385314589365e-07, | |
| "normalized_max_error": 9.572176757394733e-07, | |
| "finite": true, | |
| "monotone": true, | |
| "passed": true | |
| }, | |
| { | |
| "fixture": "multivariate_batched_65", | |
| "shape": [ | |
| 2, | |
| 2, | |
| 65, | |
| 21 | |
| ], | |
| "source_seconds": 0.12442591699073091, | |
| "mlx_seconds": 0.10803912501432933, | |
| "max_absolute_error": 9.059906005859375e-06, | |
| "rmse": 1.6768740284810245e-06, | |
| "reference_rms": 8.2838699651065, | |
| "normalized_rmse": 2.0242640644341233e-07, | |
| "normalized_max_error": 1.093680374513568e-06, | |
| "finite": true, | |
| "monotone": true, | |
| "passed": true | |
| }, | |
| { | |
| "fixture": "numeric_covariates_97", | |
| "shape": [ | |
| 1, | |
| 1, | |
| 97, | |
| 21 | |
| ], | |
| "source_seconds": 0.23030458300490864, | |
| "mlx_seconds": 0.1324903340137098, | |
| "max_absolute_error": 1.239776611328125e-05, | |
| "rmse": 2.279527914360267e-06, | |
| "reference_rms": 7.679543794802906, | |
| "normalized_rmse": 2.9683116279679614e-07, | |
| "normalized_max_error": 1.614388360109539e-06, | |
| "finite": true, | |
| "monotone": true, | |
| "passed": true | |
| }, | |
| { | |
| "fixture": "categorical_covariates_97", | |
| "shape": [ | |
| 1, | |
| 1, | |
| 97, | |
| 21 | |
| ], | |
| "source_seconds": 0.14552258301409893, | |
| "mlx_seconds": 0.10644787500496022, | |
| "max_absolute_error": 1.4543533325195312e-05, | |
| "rmse": 2.650446056621123e-06, | |
| "reference_rms": 7.739013019627613, | |
| "normalized_rmse": 3.4247856282178184e-07, | |
| "normalized_max_error": 1.8792491094549315e-06, | |
| "finite": true, | |
| "monotone": true, | |
| "passed": true | |
| }, | |
| { | |
| "fixture": "autoregressive_1057", | |
| "shape": [ | |
| 1, | |
| 1, | |
| 1057, | |
| 21 | |
| ], | |
| "source_seconds": 0.12371258300845511, | |
| "mlx_seconds": 0.14121233401237987, | |
| "max_absolute_error": 0.0003662109375, | |
| "rmse": 1.1924254772423781e-05, | |
| "reference_rms": 13.014904546689083, | |
| "normalized_rmse": 9.161999405871357e-07, | |
| "normalized_max_error": 2.813781201285583e-05, | |
| "finite": true, | |
| "monotone": true, | |
| "passed": true | |
| }, | |
| { | |
| "fixture": "constant_65", | |
| "shape": [ | |
| 1, | |
| 1, | |
| 65, | |
| 21 | |
| ], | |
| "source_seconds": 0.12416975002270192, | |
| "mlx_seconds": 0.09817333400133066, | |
| "max_absolute_error": 4.76837158203125e-07, | |
| "rmse": 3.161399574908237e-08, | |
| "reference_rms": 5.000000000403719, | |
| "normalized_rmse": 6.322799149305948e-09, | |
| "normalized_max_error": 9.536743163292467e-08, | |
| "finite": true, | |
| "monotone": true, | |
| "passed": true | |
| }, | |
| { | |
| "fixture": "all_missing_65", | |
| "shape": [ | |
| 1, | |
| 1, | |
| 65, | |
| 21 | |
| ], | |
| "source_seconds": 0.13998808301403187, | |
| "mlx_seconds": 0.08050049998564646, | |
| "max_absolute_error": 5.681067705154419e-08, | |
| "rmse": 4.930859227179981e-09, | |
| "reference_rms": 0.004288812274942533, | |
| "normalized_rmse": 1.1497027407771192e-06, | |
| "normalized_max_error": 1.3246249406499242e-05, | |
| "finite": true, | |
| "monotone": true, | |
| "passed": true | |
| } | |
| ] | |
| } | |