ct2-transformers-converter --model meta-llama/Llama-2-7b-chat-hf --quantization float16 --output_dir llama-2-7b-chat-ct2
link: https://opennmt.net/CTranslate2/guides/transformers.html#llama-2
ct2-transformers-converter --model meta-llama/Llama-2-7b-chat-hf --quantization float16 --output_dir llama-2-7b-chat-ct2
link: https://opennmt.net/CTranslate2/guides/transformers.html#llama-2