| license: cc-by-nc-4.0 | |
| # Command R+ GGUF | |
| ## Description | |
| This repository contains GGUF weights for the `llama.cpp` | |
| ## Concatenating Weights | |
| For every variant (except Q2_K), you must concatenate the weights, as they exceed the 50 GB single file size limit on HuggingFace. You can accomplish this using the `cat` command on Linux (example for the Q3 variant): | |
| ```bash | |
| cat command-r-plus-Q3_K_L.gguf.* > command-r-plus-Q3_K_L.gguf | |
| ``` | |