From 4cb3824de9628a6d4ffa4ec08031c76ca1a0a2ab Mon Sep 17 00:00:00 2001
From: Sridhar Ratnakumar <3998+srid@users.noreply.github.com>
Date: Thu, 13 Jun 2024 14:12:56 -0400
Subject: [PATCH] chore(docs): ollama: better intro, and GPU pointers

---
 doc/ollama.md | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/doc/ollama.md b/doc/ollama.md
index f605f91..779ae89 100644
--- a/doc/ollama.md
+++ b/doc/ollama.md
@@ -1,6 +1,6 @@
 # Ollama
 
-[Ollama](https://github.com/ollama/ollama) enables you to get up and running with Llama 3, Mistral, Gemma, and other large language models.
+[Ollama](https://github.com/ollama/ollama) enables you to easily run large language models (LLMs) locally. It supports Llama 3, Mistral, Gemma and [many others](https://ollama.com/library).
 
 ## Getting Started
 
@@ -15,7 +15,9 @@
 
 By default Ollama uses the CPU for inference. To enable GPU acceleration:
 
-### Cuda
+### CUDA
+
+For NVIDIA GPUs.
 
 ```nix
 # In `perSystem.process-compose.<name>`
@@ -29,6 +31,8 @@ By default Ollama uses the CPU for inference. To enable GPU acceleration:
 
 ### ROCm
 
+For Radeon GPUs.
+
 ```nix
 # In `perSystem.process-compose.<name>`
 {