From 448c5eb135f5b1df55e9c2a66f83f6c7ec3b64a7 Mon Sep 17 00:00:00 2001 From: vuonghoainam Date: Tue, 12 Sep 2023 18:08:55 +0700 Subject: [PATCH 1/2] chore: Add empty folder models at root to store downloaded model --- models/.gitkeep | 0 1 file changed, 0 insertions(+), 0 deletions(-) create mode 100644 models/.gitkeep diff --git a/models/.gitkeep b/models/.gitkeep new file mode 100644 index 000000000..e69de29bb From f6d8929e9b643815424dd09e1d99a1297736548c Mon Sep 17 00:00:00 2001 From: vuonghoainam Date: Tue, 12 Sep 2023 18:09:24 +0700 Subject: [PATCH 2/2] fix: Fix README with minor bug in step to download model --- README.md | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index d032a6917..d9282bb67 100644 --- a/README.md +++ b/README.md @@ -136,14 +136,13 @@ pip install 'llama-cpp-python[server]' We recommend that Llama2-7B (4-bit quantized) as a basic model to get started. -You will need to download the models to the `models` folder. +You will need to download the models to the `models` folder at root level. ```shell -mkdir -p models # Downloads model (~4gb) # Download time depends on your internet connection and HuggingFace's bandwidth # In this part, please head over to any source contains `.gguf` format model - https://huggingface.co/models?search=gguf -wget LLM_MODEL_URL=https://huggingface.co/TheBloke/CodeLlama-13B-GGUF/resolve/main/codellama-13b.Q3_K_L.gguf -P models +wget https://huggingface.co/TheBloke/CodeLlama-13B-GGUF/resolve/main/codellama-13b.Q3_K_L.gguf -P models ``` - Run the model in host machine