Update README.md

README.md

@@ -16,3 +16,37 @@ prompt_template: '[INST] {prompt} [/INST]
   '
 quantized_by: OptimizeLLM
 ---
+
+This is Mistral AI's Mixtral Instruct v0.1 model, quantized on 02/24/2024. The file size is slightly larger than TheBloke's version from December, and it seems to work well.
+
+How to quantize your own models on Windows and an RTX GPU:
+
+Requirements:
+	- git and python installed (if you use oobabooga etc you are probably already good to go)
+
+The following example starts at the root of D drive and quantizes mistral's Mixtral-9x7B-Instruct-v0.1:
+
+In Windows command prompt: 
+D:
+mkdir Mixtral
+git clone https://github.com/ggerganov/llama.cpp
+
+Assuming you want CUDA for your NVIDIA RTX GPU(s) use the links below, or grab latest compiled executables from https://github.com/ggerganov/llama.cpp/releases
+Latest version as of Feb 24, 2024:
+https://github.com/ggerganov/llama.cpp/releases/download/b2253/cudart-llama-bin-win-cu12.2.0-x64.zip
+https://github.com/ggerganov/llama.cpp/releases/download/b2253/llama-b2253-bin-win-cublas-cu12.2.0-x64.zip
+
+Extract the two .zip files directly into the llama.cpp folder you just git cloned. Overwrite files as prompted.
+
+Download the full-blast version of the model by downloading all .safetensors, .json, and .model files to D:\Mixtral\
+https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1
+Download all .safetensors, .json, and .model files to D:\Mixtral\
+
+Convert the model to fp16:
+D:\llama.cpp>python convert.py D:\Mixtral --outtype f16 --outfile D:\Mixtral\Mixtral-8x7B-Instruct-v0.1.fp16.bin
+
+Quantize the fp16 model to q5_k_m:
+
+D:\llama.cpp>quantize.exe D:\Mixtral\Mixtral-8x7B-Instruct-v0.1.fp16.bin D:\Mixtral\Mixtral-8x7B-Instruct-v0.1.q5_k_m.gguf q5_k_m
+
+That's it. Load up the resulting .gguf file like you normally would.