add-quantized-gguf-files
#1
by espenhk - opened
No description provided.
Same as with Mistral model: this PR will add quantized versions of the model as GGUF files, fitting for running locally on your machine, for instance through Ollama.
OK on my end!
espenhk changed pull request status to open
Bumping this one, still ready to merge if you would like :)
NorLLM-NTNU changed pull request status to merged