README.md

---
license: apache-2.0
pipeline_tag: text-generation
library_name: transformers
---

### <a href="https://huggingface.co/papers/2511.15244">Context Cascade Compression: Exploring the Upper Limits of Text Compression</a></h3>


[🌟GitHub](https://github.com/liufanfanlff/C3-Context-Cascade-Compression) | [📜Paper](https://arxiv.org/abs/2511.15244)



[Fanfan Liu](https://scholar.google.com/citations?user=LPaXZEUAAAAJ&hl=en), [Haibo Qiu](https://scholar.google.com/citations?user=O5gH5vkAAAAJ&hl=en)



![image/jpeg](8a5ce4ed-f1d5-4a3c-8718-3604cf3c3866.png)



## Usage

```
from transformers import AutoModel, AutoTokenizer

model_name = 'liufanfanlff/C3-Context-Cascade-Compression'
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModel.from_pretrained(model_name , trust_remote_code=True, low_cpu_mem_usage=True, device_map='cuda', use_safetensors=True, pad_token_id=tokenizer.eos_token_id)
model = model.eval().cuda()
prompt = 'Repeat the text: '
context = "帝高阳之苗裔兮，朕皇考曰伯庸。摄提贞于孟陬兮，"
#context = "lfflfflfflfflfflfflfflfflff"
outputs = model.chat(tokenizer, context, prompt)
print ("Repeat the text: ",outputs)
```


viz

![image/jpeg](et.png)


## Contact

Don't hesitate to contact me by email, liufanfan19@mails.ucas.ac.cn, if you have any questions.

## Acknowledgement
- [DeepSeek-OCR](https://github.com/deepseek-ai/DeepSeek-OCR): the idea originated from reconsideration of this work.
- [GOT-OCR2.0](https://github.com/Ucas-HaoranWei/GOT-OCR2.0): the code was adapted from GOT-OCR2.0.
- [Qwen](https://github.com/QwenLM/Qwen): the LLM base model of C3.



## Citation
```bibtex
@article{liu2025context,
  title={Context Cascade Compression: Exploring the Upper Limits of Text Compression},
  author={Liu, Fanfan and Qiu, Haibo},
  journal={arXiv preprint arXiv:2511.15244},
  year={2025}
}
```