How to run

#1
by saipangon - opened

How to run this in llamacpp? I've been trying to merge, it fails

The easiest way would be to just download the already merged model from https://hf.tst.eu/model#VCoder-120b-1.0-GGUF

If you want to contaminate it locally:
If you are on Linux you just use cat in the terminal. If you are on Windows download Git for Windows from https://git-scm.com/install/windows and use the following command inside Git Bash: cat VCoder-120b-1.0.MXFP4_MOE.gguf.part1of2 VCoder-120b-1.0.MXFP4_MOE.gguf.part2of2 > VCoder-120b-1.0.MXFP4_MOE.gguf

I highly recommend you use the MXFP4_MOE quants as they are the only reasonable choice for this model as the original model was released in this format.

Sign up or log in to comment