| language: | |
| - id | |
| tags: | |
| - mistral | |
| - gguf | |
| This model is a quantized version of [Sidrap-V2](https://huggingface.co/robinsyihab/Sidrap-7B-v2) | |
| 1. Install [llama.cpp](https://github.com/ggerganov/llama.cpp#prepare-data--run) | |
| 2. Download the model | |
| 3. `~/llama.cpp/main -ngl 32 -m sidrap-7b-v2.q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -i -ins` |