Load multiple gguf shard into MAC
#23
by
sintuk
- opened
Hi there, I'm facing challenges in loading gguf multiple shards of this model. Could anyone faced this issue, could you list down the process you followed preferable using llama_cpp or ctransformer (langchain) on mac os. much appreciate
Hi,
Which model exactly? The ones that were split, it use the native split in Llama.cpp. Just load the first part (1)