From ee491bd6de68c63a8b7543e9f9e0431b1b3677e6 Mon Sep 17 00:00:00 2001 From: Ewout ter Hoeven Date: Mon, 22 Apr 2024 16:48:49 +0200 Subject: [PATCH] [Docs] Update quick start to mention Llama 3 8B This commit updates the quick start to mention Llama 3 8B instead of Llama 2 7B. The code blocks where already updated. --- docs/get_started/quick_start.rst | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/docs/get_started/quick_start.rst b/docs/get_started/quick_start.rst index 604688f790..76d971275b 100644 --- a/docs/get_started/quick_start.rst +++ b/docs/get_started/quick_start.rst @@ -6,7 +6,7 @@ Quick Start Examples -------- -To begin with, try out MLC LLM support for int4-quantized Llama2 7B. +To begin with, try out MLC LLM support for int4-quantized Llama3 8B. It is recommended to have at least 6GB free VRAM to run it. .. tabs:: @@ -133,7 +133,7 @@ It is recommended to have at least 6GB free VRAM to run it. | - **Requirement**. Llama2-7B model needs an iOS device with a minimum of 6GB RAM, whereas the RedPajama-3B model runs with at least 4GB RAM. + **Requirement**. Llama3-8B model needs an iOS device with a minimum of 6GB RAM, whereas the RedPajama-3B model runs with at least 4GB RAM. **Tutorial and source code**. The source code of the iOS app is fully `open source `__, and a :ref:`tutorial ` is included in documentation. @@ -154,7 +154,7 @@ It is recommended to have at least 6GB free VRAM to run it. | - **Requirement**. Llama2-7B model needs a device with a minimum of 6GB RAM, whereas the RedPajama-3B model runs with at least 4GB RAM. + **Requirement**. Llama3-8B model needs a device with a minimum of 6GB RAM, whereas the RedPajama-3B model runs with at least 4GB RAM. The demo is tested on - Samsung S23 with Snapdragon 8 Gen 2 chip