From a0c5d3a0ba90623aeebbf08069bf1987c135985b Mon Sep 17 00:00:00 2001 From: Frances Liu Date: Tue, 5 Nov 2024 11:42:59 -0800 Subject: [PATCH 1/2] Doc updates for support Llama3.2 --- docs/import.md | 8 +++----- docs/modelfile.md | 2 +- 2 files changed, 4 insertions(+), 6 deletions(-) diff --git a/docs/import.md b/docs/import.md index 2346886f1bd..b90377bf0b6 100644 --- a/docs/import.md +++ b/docs/import.md @@ -32,7 +32,7 @@ ollama run my-model Ollama supports importing adapters based on several different model architectures including: - * Llama (including Llama 2, Llama 3, and Llama 3.1); + * Llama (including Llama 2, Llama 3, Llama 3.1, and Llama 3.2); * Mistral (including Mistral 1, Mistral 2, and Mixtral); and * Gemma (including Gemma 1 and Gemma 2) @@ -67,14 +67,12 @@ ollama run my-model Ollama supports importing models for several different architectures including: - * Llama (including Llama 2, Llama 3, and Llama 3.1); + * Llama (including Llama 2, Llama 3, Llama 3.1, and Llama 3.2); * Mistral (including Mistral 1, Mistral 2, and Mixtral); * Gemma (including Gemma 1 and Gemma 2); and * Phi3 -This includes importing foundation models as well as any fine tuned models which which have been _fused_ with a foundation model. - - +This includes importing foundation models as well as any fine tuned models which have been _fused_ with a foundation model. ## Importing a GGUF based model or adapter If you have a GGUF based model or adapter it is possible to import it into Ollama. You can obtain a GGUF model or adapter by: diff --git a/docs/modelfile.md b/docs/modelfile.md index aa2849e7936..c73f960a6d1 100644 --- a/docs/modelfile.md +++ b/docs/modelfile.md @@ -120,7 +120,7 @@ FROM The model directory should contain the Safetensors weights for a supported architecture. Currently supported model architectures: - * Llama (including Llama 2, Llama 3, and Llama 3.1) + * Llama (including Llama 2, Llama 3, Llama 3.1, and Llama 3.2) * Mistral (including Mistral 1, Mistral 2, and Mixtral) * Gemma (including Gemma 1 and Gemma 2) * Phi3 From 3606ae5b838d38fb71663eb920d4771d1fdd535e Mon Sep 17 00:00:00 2001 From: Frances Liu Date: Thu, 6 Feb 2025 15:23:03 -0800 Subject: [PATCH 2/2] Docs-only change --- docs/development.md | 6 ------ 1 file changed, 6 deletions(-) diff --git a/docs/development.md b/docs/development.md index 732aa5fff25..12b2ca39170 100644 --- a/docs/development.md +++ b/docs/development.md @@ -3,13 +3,7 @@ > [!IMPORTANT] > The `llm` package that loads and runs models is being updated to use a new [Go runner](#transition-to-go-runner): this should only impact a small set of PRs however it does change how the project is built. -Install required tools: -- cmake version 3.24 or higher -- go version 1.22 or higher -- gcc version 11.4.0 or higher - -### MacOS ```bash brew install go cmake gcc