CPU optimized version
#3
by
gururaser
- opened
Hi, can you share any CPU optimized version of this model?
Apologies for the delayed response during the holiday period.
We have not yet attempted to convert this model into a CPU-optimized version.
However, we may release an ONNX version of the model in the future for more efficient inference.
We have released the GGUF version: HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1.5-GGUF, which was converted using llama.cpp.
Currently, it is functioning properly when deployed via llama.cpp, but it has not yet been tested with LM Studio.
If you have any requirements, you are welcome to try this model.
YanshekWoo
changed discussion status to
closed