These are quantizations of the model openPangu-Embedded-1B-V1.1
Original model: https://huggingface.co/FreedomIntelligence/openPangu-Embedded-1B-V1.1
Download the latest llama.cpp to use them.
Try to use the best quality you can run.
For the mmproj, try to use the F32 version as it will produce the best results. F32 > BF16 > F16
- Downloads last month
- 202
Hardware compatibility
Log In
to view the estimation
4-bit
5-bit
6-bit
8-bit
16-bit
32-bit