baalajimaestro/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Merge branch 'main' of github.com:abetlen/llama_cpp_python into main

Browse source
This commit is contained in:
Andrei Betlen 2023-10-03 15:23:37 -04:00
commit c305be6db6
1 changed files with 6 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
docs/install/macos.md
View file

@ -38,19 +38,19 @@ llama-cpp-python         0.1.68
``` ```
**(5) Download a v3 ggml model** **(5) Download a v3 gguf v2 model**
- **ggmlv3** - **ggufv2**
- file name ends with **q4_0.bin** - indicating it is 4bit quantized, with quantisation method 0 - file name ends with **Q4_0.gguf** - indicating it is 4bit quantized, with quantisation method 0
https://huggingface.co/TheBloke/open-llama-7b-open-instruct-GGML https://huggingface.co/TheBloke/CodeLlama-7B-GGUF
**(6) run the llama-cpp-python API server with MacOS Metal GPU support** **(6) run the llama-cpp-python API server with MacOS Metal GPU support**
``` ```
# config your ggml model path # config your ggml model path
# make sure it is ggml v3 # make sure it is gguf v2
# make sure it is q4_0 # make sure it is q4_0
export MODEL=[path to your llama.cpp ggml models]]/[ggml-model-name]]q4_0.bin export MODEL=[path to your llama.cpp ggml models]]/[ggml-model-name]]Q4_0.gguf
python3 -m llama_cpp.server --model $MODEL --n_gpu_layers 1 python3 -m llama_cpp.server --model $MODEL --n_gpu_layers 1
``` ```