about joining

by krustik - opened Jul 1

Jul 1

Hi,
How to join the fp16 parts? It's not mentioned in model card.
If i'm using cat in Linux - the joined file cannot be loaded in oobabooga, it reports "invalid split file".
Thanks.

3thn

Crusoe AI org Jul 3

Hey @krustik ! To join ggufs, you would use llama-gguf-split in llama.cpp. The command would look something like:

llama-gguf-split --merge /tmp/dolphin-2.9.3-yi-1.5-34b-32k.fp16-00001-of-00002.gguf
 /tmp/dolphin-2.9.3-yi-1.5-34b-32k.fp16-merge.gguf

krustik changed discussion status to closed Aug 28

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment