From 3c70add02f2f699d154d6d580a08cbda2e0115c3 Mon Sep 17 00:00:00 2001
From: Finn Kumkar <finn.kumkar@gmail.com>
Date: Thu, 6 Jul 2023 12:31:37 +0200
Subject: [PATCH] Update changelog

---
 CHANGELOG.md |  9 +++++++++
 README.md    | 16 ++++++++++++++++
 2 files changed, 25 insertions(+)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index c58ffae..2c5ed31 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -4,6 +4,15 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [1.2.0] - 2023-07-06
+
+### Added
+- Add server example to the build
+- Add documentation on how to use the webinterface
+
+### Fixed
+- Fix automatic update of the submodules
+
 ## [1.1.0] - 2023-07-03
 
 ### Added
diff --git a/README.md b/README.md
index 4c3c4e8..9c045c0 100644
--- a/README.md
+++ b/README.md
@@ -103,6 +103,22 @@ You can now chat with the model:
     --interactive
 ```
 
+### Chat via Webinterface
+
+You can start llama.cpp as a webserver:
+
+```PowerShell
+./vendor/llama.cpp/build/bin/Release/server `
+    --model "./vendor/llama.cpp/models/open-llama-7B-open-instruct.ggmlv3.q4_K_M.bin" `
+    --ctx-size 2048 `
+    --threads 16 `
+    --n-gpu-layers 32
+```
+
+And then access llama.cpp via the webinterface at:
+
+* http://localhost:8080/
+
 ### Measure model perplexity
 
 Execute the following to measure the perplexity of the GGML formatted model: