Qwen/Qwen1.5-14B-Chat-AWQ

  • Modal Card
  • Files & version

DESCRIPTION.md

Qwen1.5-14B-Chat-AWQ

Introduction

Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data. In comparison with the previously released Qwen, the improvements include:

  • 8 model sizes, including 0.5B, 1.8B, 4B, 7B, 14B, 32B, and 72B dense models, and an MoE model of 14B with 2.7B activated parameters.
  • Significant performance improvement in human preference for chat models.
  • Multilingual support of both base and chat models.
  • Stable support of 32K context length for models of all sizes.
  • No need for
    trust_remote_code
    .

For more details, please refer to our blog post and GitHub repo.

Model Details

Qwen1.5 is a language model series including decoder language models of different sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, mixture of sliding window attention and full attention, etc. Additionally, we have an improved tokenizer adaptive to multiple natural languages and codes. For the beta version, temporarily, we did not include GQA (except for 32B) and the mixture of SWA and full attention.

Citation

If you find our work helpful, feel free to cite us:

@article{qwen,
  title={Qwen Technical Report},
  author={Jinze Bai and Shuai Bai and Yunfei Chu and Zeyu Cui and Kai Dang and Xiaodong Deng and Yang Fan and Wenbin Ge and Yu Han and Fei Huang and Binyuan Hui and Luo Ji and Mei Li and Junyang Lin and Runji Lin and Dayiheng Liu and Gao Liu and Chengqiang Lu and Keming Lu and Jianxin Ma and Rui Men and Xingzhang Ren and Xuancheng Ren and Chuanqi Tan and Sinan Tan and Jianhong Tu and Peng Wang and Shijie Wang and Wei Wang and Shengguang Wu and Benfeng Xu and Jin Xu and An Yang and Hao Yang and Jian Yang and Shusheng Yang and Yang Yao and Bowen Yu and Hongyi Yuan and Zheng Yuan and Jianwei Zhang and Xingxuan Zhang and Yichang Zhang and Zhenru Zhang and Chang Zhou and Jingren Zhou and Xiaohuan Zhou and Tianhang Zhu},
  journal={arXiv preprint arXiv:2309.16609},
  year={2023}
}

Best Use Cases for Qwen1.5-14B-Chat Model

Qwen1.5-14B-Chat models are optimized for various natural language understanding and generation tasks. The AWQ quantization enhances their efficiency, making them suitable for:

  • Interactive Applications: Building chatbots and virtual assistants.
  • Content Generation: Assisting in drafting text content like articles, reports, and stories.
  • Customer Support: Providing automated responses to user queries.
  • Educational Tools: Offering tutoring and answering questions in educational platforms.

The model's architecture and training make it well-suited for tasks requiring understanding and generating human-like text, especially in interactive and real-time applications.

Model Architecture

Qwen1.5-14B-Chat is a decoder-only model based on an optimized transformer architecture. It uses SwiGLU activation, attention QKV bias, group query attention, and a mixture of sliding window attention and full attention. The model also employs an improved tokenizer adaptive to multiple natural languages and codes. The model has been fine-tuned for instruction-based tasks, making it ideal for generating informative and contextually relevant responses.

About AWQ

AWQ (Accurate Weight Quantization) is an efficient, accurate, and fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to other quantization methods like GPTQ, AWQ offers faster inference with equivalent or better quality. AWQ models are supported on Linux and Windows with NVIDIA GPUs. macOS users should use GGUF models instead.