quantized duplicated precisions.json, which is authoritative for the
quantized/non-quantized partition. default expressed a per-repository
recommendation nothing consumed: the library resolves its own per-platform
default. Both are gone from the schema.
Adds library_name to the model card, and pipeline_tag where it was missing.
Brings the config and card licenses into agreement, and repairs the variant
declarations that did not match the files actually published here.
Re-export the 8da4w text variants at the sweep's group size (#1)
Weight-width ablation of the int4 MLX build for software-mansion/react-native-executorch#1379. Same export in every other respect: bf16 compute dtype, group size 32, vision tower unquantized.
Update chat template for strict monotonicity and tool support
---
license: other
license_name: lfm1.0
license_link: https://huggingface.co/LiquidAI/LFM2.5-1.2B-Thinking/blob/main/LICENSE
pipeline_tag: text-generation
tags:
- executorch
- liquid
- lfm2.5
- edge
---
# Introduction
This repository hosts the **LFM2.5** model family for the [React Native ExecuTorch](https://www.npmjs.com/package/react-native-executorch) library. It includes exported models in `.pte` format, ready for use in the **ExecuTorch** runtime.
If you'd like to run these models in your own ExecuTorch runtime, refer to the [official documentation](https://pytorch.org/executorch/stable/index.html) for setup instructions.
## Compatibility
If you intend to use this model outside of React Native ExecuTorch, make sure your runtime is compatible with the **ExecuTorch** version used to export the `.pte` files. For more details, see the compatibility note in the [ExecuTorch GitHub repository](https://github.com/pytorch/executorch/blob/11d1742fdeddcf05bc30a6cfac321d2a2e3b6768/runtime…
