README.md

---
license: apache-2.0
datasets:
- allenai/MADLAD-400
language:
- si
base_model:
- Qwen/Qwen2.5-7B-Instruct
- atsuki-yamaguchi/Qwen2.5-7B-Instruct-si-madlad-mean-tuned
library_name: transformers
---
# Qwen2.5 7B Instruct for Sinhala: ElChat

This model is built on top of Qwen2.5 7B Instruct adapted for Sinhala using 500M target language tokens sampled from MADLAD-400. It has an additional target vocabulary of 10K. The model was trained using the ElChat method.

## Model Details

* **Vocabulary**: This model has an additional target vocabulary of 10K.
* **Target vocabulary initialization**: The target weights of the embedding and LM head were initialized using mean initialization.
* **Training**: This model was continually pre-trained on 500M target language tokens sampled from MADLAD-400.
* **Post-processing**: The model was post-processed using the ElChat method.


## Model Description

- **Language:** Sinhala
- **License:** Apache 2.0
- **Fine-tuned from model:** Qwen/Qwen2.5-7B-Instruct


## Model Sources

- **Repository:** https://github.com/gucci-j/chat-cve
- **Paper:** https://arxiv.org/abs/2412.11704


## How to Get Started with the Model
Use the code below to get started with the model.
```python
from transformers import AutoTokenizer, AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained(
    "atsuki-yamaguchi/Qwen2.5-7B-Instruct-si-madlad-mean-slerp0305-emb-special"
)
tokenizer = AutoTokenizer.from_pretrained(
    "atsuki-yamaguchi/Qwen2.5-7B-Instruct-si-madlad-mean-slerp0305-emb-special"
)
```


## Citation
```
@misc{yamaguchi2024vocabularyexpansionchatmodels,
      title={{ElChat}: Adapting Chat Language Models Using Only Target Unlabeled Language Data}, 
      author={Atsuki Yamaguchi and Terufumi Morishita and Aline Villavicencio and Nikolaos Aletras},
      year={2024},
      eprint={2412.11704},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2412.11704},
}
```