From b52ec52790c877208c1b7114022c229779c14b3b Mon Sep 17 00:00:00 2001 From: John Paul Hennessy Date: Mon, 22 Apr 2024 16:08:09 -0400 Subject: [PATCH] Update README.md to include diagram (#1319) Co-authored-by: Sebastian Raschka --- README.md | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 4bd3d8bf75..9f513e2958 100644 --- a/README.md +++ b/README.md @@ -29,6 +29,8 @@ Uses the latest state-of-the-art techniques: +  +LitGPT steps   # Finetune, pretrain and deploy LLMs Lightning fast ⚡⚡ @@ -43,6 +45,8 @@ We reimplemented all model architectures and training recipes from scratch for 4 --- +  + # Choose from 20+ LLMs LitGPT has 🤯 **custom, from-scratch implementations** of [20+ LLMs](tutorials/download_model_weights.md) without layers of abstraction: @@ -57,6 +61,7 @@ LitGPT has 🤯 **custom, from-scratch implementations** of [20+ LLMs](tutorials
See full list of 20+ LLMs +   #### All models @@ -88,6 +93,8 @@ LitGPT has 🤯 **custom, from-scratch implementations** of [20+ LLMs](tutorials
+  + ## Install LitGPT Install LitGPT with all dependencies (including CLI, quantization, tokenizers for all models, etc.): @@ -110,10 +117,9 @@ pip install -e '.[all]' ``` -  - --- +  # Quick start After installing LitGPT, select the model and action you want to take on that model (finetune, pretrain, evaluate, deploy, etc...):