This worked on 14/May/23. The instructions will probably require updating in the future.
It is possible to run LLama 13B with a 6GB graphics card now! (e.g. a RTX 2060). Thanks to the amazing work involved in llama.cpp. The latest change is CUDA/cuBLAS which allows you pick an arbitrary number of the transformer layers to be run on the GPU. This is perfect for low VRAM.
- Get llama.cpp from git, I am on commit
08737ef720f0510c7ec2aa84d7f70c691073c35d
. - Use the link at the bottom of the page to apply for research access to the llama model: https://ai.facebook.com/blog/large-language-model-llama-meta-ai/
- Set up a micromamba environment to install cuda/python pytorch stuff in order to run the conversion scripts. Install some packages:
micromamba install -c conda-forge -n mymamba pytorch transformers sentencepiece
- Perform the conversion process: (This will produce a file called `ggml-model