SeaLLMs/SeaLLM-7B-v2.5-GGUF

SeaLLM-7B-v2.5 - Large Language Models for Southeast Asia

LM-studio/llama.cpp users must set --repeat-penalty to 1 instead of default 1.1

Technical Blog    🤗 Tech Memo    🤗 DEMO    Github    Technical Report

• seallm-7b-v2.5-chatml.Q4_K_M.gguf use ChatML format by changing <eos> to <|im_end|>
• seallm-7b-v2.5.Q4_K_M.gguf use SeaLLM-7B-v2.5 format, must download seallm-v2.5.preset.json for LM-studio.

We introduce SeaLLM-7B-v2.5, the state-of-the-art multilingual LLM for Southeast Asian (SEA) languages 🇬🇧 🇨🇳 🇻🇳 🇮🇩 🇹🇭 🇲🇾 🇰🇭 🇱🇦 🇲🇲 🇵🇭. It is the most significant upgrade since SeaLLM-13B, with half the size, outperforming performance across diverse multilingual tasks, from world knowledge, math reasoning, instruction following, etc.

Checkout SeaLLM-7B-v2.5 page for more details.

Citation

If you find our project useful, we hope you would kindly star our repo and cite our work as follows: Corresponding Author: [email protected]

Author list and order will change!

• * and ^ are equal contributions.

@article{damonlpsg2023seallm,
  author = {Xuan-Phi Nguyen*, Wenxuan Zhang*, Xin Li*, Mahani Aljunied*, Weiwen Xu, Hou Pong Chan,
            Zhiqiang Hu, Chenhui Shen^, Yew Ken Chia^, Xingxuan Li, Jianyu Wang,
            Qingyu Tan, Liying Cheng, Guanzheng Chen, Yue Deng, Sen Yang,
            Chaoqun Liu, Hang Zhang, Lidong Bing},
  title = {SeaLLMs - Large Language Models for Southeast Asia},
  year = 2023,
  Eprint = {arXiv:2312.00738},
}