| This is the Q3_K_M GGUF port of the [lightblue/Karasu-Mixtral-8x22B-v0.1](https://huggingface.co/lightblue/Karasu-Mixtral-8x22B-v0.1) model. | |
| ### How to use | |
| The way to run this directly are using the llama.cpp package. | |
| ```bash | |
| git clone https://github.com/ggerganov/llama.cpp | |
| cd llama.cpp | |
| make | |
| huggingface-cli download lightblue/Karasu-Mixtral-8x22B-v0.1-gguf --local-dir /some/folder/ | |
| ./main -m /some/folder/Karasu-Mixtral-8x22B-v0.1-Q3_K_M-00001-of-00005.gguf -p "<s>[INST] Tell me a really funny joke. No puns! [/INST]" -n 256 -e | |
| ``` | |
| If you would like a nice easy GUI and have >64GB of RAM, then you could also run this using [LM Studio](https://lmstudio.ai/) and search for this model on the search bar. | |
| ### Commands to make this: | |
| ```bash | |
| cd llama.cpp | |
| ./convert.py --outfile Karasu-Mixtral-8x22B-v0.1-q3_k_m --outtype f16 /workspace/llm_training/axolotl/mixtral_8x22B_training/merged_model_multiling | |
| ./quantize /workspace/Karasu-Mixtral-8x22B-v0.1.gguf /workspace/Karasu-Mixtral-8x22B-v0.1_q3_k_m.gguf Q3_K_M | |
| ./gguf-split --split --split-max-size 5G /workspace/Karasu-Mixtral-8x22B-v0.1_q3_k_m.gguf /workspace/somewhere-sensible | |
| ``` |