---
license: bsd-3-clause
tags:
- tabular
- foundation-model
- in-context-learning
- regression
- rust
- tabicl
library_name: tabicl
base_model: Jingang/TabICL-reg
---

# TabICL regressor v2 — `tabicl` format

Converted weights for [`tabicl-rs`](https://github.com/eugenehp/tabicl-rs).
Mirrors the upstream PyTorch checkpoint `Jingang/TabICL-reg` (v2 release)
in the layout the Rust state-dict loader consumes directly.

See `MIT-RLX/tabicl-classifier-v2-rs` for the classifier variant and a
full description of the conversion pipeline; everything carries over
modulo the regression head (quantile decoder instead of softmax).

## Usage

```rust
use tabicl::{TabICLRegressor, TabICLConfig};

let mut reg = TabICLRegressor::new();
reg.fit(x_train.view(), &y_train)?;
reg.load_checkpoint(TabICLConfig::default(), "weights.safetensors")?;

let preds = reg.predict(x_test.view())?;
```

## License

BSD-3-Clause, matching upstream `soda-inria/tabicl`.