How to use from the
Use from the
MLX library
# Download the model from the Hub
pip install huggingface_hub[hf_xet]

hf download kunal732/TiRex-mlx --local-dir TiRex-mlx

kunal732/TiRex-mlx

This model was converted from NX-AI/TiRex using MLX-Swift-TS.

Use with MLX-Swift-TS

import MLXTimeSeries

let forecaster = try await TimeSeriesForecaster.loadFromHub(id: "kunal732/TiRex-mlx")
let input = TimeSeriesInput.univariate(historicalValues)
let prediction = forecaster.forecast(input: input, predictionLength: 64)

Original Model

NX-AI/TiRex

Downloads last month
10
Safetensors
Model size
35.3M params
Tensor type
F16
ยท
MLX
Hardware compatibility
Log In to add your hardware

Quantized

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for kunal732/TiRex-mlx

Base model

NX-AI/TiRex
Finetuned
(2)
this model