Can you help upload ollama download, currently directly merge to ollama is not available
#9
by
windkkk
- opened
Can you help upload ollama download, currently directly merge to ollama is not available
PLEASE READ THE MODEL CARD FIRST!
GGUF (Text-Only, not recommended): There is a significant degradation, even with the F16.
GGUF for text-only should be working after PR #9194 was merged.
As GGUF implementation is not recommended at the moment, there won't be an ollama download. Please do use transformers or ChatGLM.cpp, and any quantization lower than 8-bit is not recommended.
JosephusCheung
changed discussion status to
closed