dieusangly/SeaLLM-7B-Chat-exl2

SeaLLM-7B-Chat quantized to run locally with modest GPU

Model Description

• This is a quantized model of SeaLLM-7B-Chat.
• SeaLLMs is a family of LLMs pre-trained from Meta's LLaMA 2 and optimized for numerous Southeast Asian languages, including Vietnamese 🇻🇳, Indonesian 🇮🇩, Thai 🇹🇭, Malay 🇲🇾, Khmer 🇰🇭, Lao 🇱🇦, Tagalog 🇵🇭 and Burmese 🇲🇲.
• The quantization has been done with ExLlamaV2, a fast LLM inference library.

Citation

• SeaLLMs: https://huggingface.co/SeaLLMs
• ExLlamaV2: https://github.com/turboderp/exllamav2