Llama-fied Version?
#7
by
ShiLuohe
- opened
If there is no further changes, provide a llama-fied version would help open-source community build upon your model more easily. It would make your model instantly ready for LLaVA style multi-modality continue training and vLLM compatible for efficient inference.
The llamafied versions have already been created with contributions from other researchers. Please check out these:
maywell/EXAONE-3.0-7.8B-Instruct-Llamafied
CarrotAI/EXAONE-3.0-7.8B-Instruct-Llamafied-cpu