---
license: cc-by-4.0
language:
- en
tags:
- model_hub_mixin
- pytorch_model_hub_mixin
---

 # ARC-Encoder models

 This page houses `ARC8-Encoder_Mistral` from three different versions of pretrained ARC-Encoders. Architectures and methods to train them are described in the paper *ARC-Encoder: learning compressed text representations for large language models* available [here](https://arxiv.org/abs/2510.20535). A code to reproduce the pretraining, further fine-tune the encoders or even evaluate them on dowstream tasks is available at [ARC-Encoder repository](https://github.com/kyutai-labs/ARC-Encoder/tree/main).

 ## Models Details 

 All the encoders released here are trained on web crawl filtered using [Dactory](https://github.com/kyutai-labs/dactory) based on a [Llama3.2-3B](https://github.com/meta-llama/llama-cookbook) base backbone. It consists in two ARC-Encoder specifically trained for one decoder and one for two decoders in the same time:
- `ARC8-Encoder_Llama`, trained on 2.6B tokens on [Llama3.1-8B](https://github.com/meta-llama/llama-cookbook) base specifically with a pooling factor of 8.    
- `ARC8-Encoder_Mistral`, trained on 2.6B tokens on [Mistral-7B](https://github.com/mistralai/mistral-finetune?tab=readme-ov-file) base specifically with a pooling factor of 8.    
- `ARC8-Encoder_multi`, trained by sampling among the two decoders with a pooling factor of 8. 

 ### Uses

 As described in the [paper](https://arxiv.org/abs/2510.20535), the pretrained ARC-Encoders can be fine-tuned to perform various downstream tasks.
You can also adapt an ARC-Encoder to a new pooling factor (PF) by fine-tuning it on the desired PF.
For optimal results, we recommend fine-tuning toward a lower PF than the one used during pretraining.
To reproduce the results presented in the paper, you can use our released fine-tuning dataset, [ARC_finetuning](https://huggingface.co/datasets/kyutai/ARC_finetuning).

 ### Licensing

 ARC-Encoders are licensed under the CC-BY 4.0 license.
 
Terms of use: As the released models are pretrained from Llama3.2 3B backbone, ARC-Encoders are subject to the Llama Terms of Use found at [Llama license](https://www.llama.com/license/).

 ## Citations

 If you use one of these models, please cite:

 ```bibtex
@misc{pilchen2025arcencoderlearningcompressedtext,
      title={ARC-Encoder: learning compressed text representations for large language models}, 
      author={Hippolyte Pilchen and Edouard Grave and Patrick Pérez},
      year={2025},
      eprint={2510.20535},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2510.20535}, 
}
```