atsuki-yamaguchi's picture
Upload README.md with huggingface_hub
eb577a3 verified
metadata
license: apache-2.0
datasets:
  - allenai/MADLAD-400
language:
  - bn
base_model:
  - Qwen/Qwen2.5-7B
  - Qwen/Qwen2.5-7B-Instruct
  - atsuki-yamaguchi/Qwen2.5-7B-bn-madlad-mean-tuned
library_name: transformers

Qwen2.5 7B for Bengali: Chat Vector

This model is built on top of Qwen2.5 7B adapted for Bengali using 500M target language tokens sampled from MADLAD-400. It has an additional target vocabulary of 10K. Chat vector was added to the model after continual pre-training.

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 Chat Vector method.

Model Description

  • Language: Bengali
  • License: Apache 2.0
  • Fine-tuned from model: Qwen/Qwen2.5-7B

Model Sources

How to Get Started with the Model

Use the code below to get started with the model.

from transformers import AutoTokenizer, AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained(
    "atsuki-yamaguchi/Qwen2.5-7B-bn-madlad-mean-cv"
)
tokenizer = AutoTokenizer.from_pretrained(
    "atsuki-yamaguchi/Qwen2.5-7B-bn-madlad-mean-cv"
)

Citation

@article{yamaguchi2025adapting,
      title={Adapting Chat Language Models Using Only Target Unlabeled Language Data}, 
      author={Atsuki Yamaguchi and Terufumi Morishita and Aline Villavicencio and Nikolaos Aletras},
      journal={Transactions on Machine Learning Research},
      issn={2835-8856},
      year={2025},
      url={https://openreview.net/forum?id=6IdoIKowfe},
      note={}
}