strings rename kobold lite to koboldai lite

MIT_LICENSE_GGML_LLAMACPP_ONLY

@@ -23,4 +23,4 @@ SOFTWARE.
 ===================================
 
 Note that the above license applies ONLY to the GGML library and llama.cpp by ggerganov which are licensed under the MIT License
-Kobold Lite by Concedo and the provided python ctypes bindings in koboldcpp dlls are licensed under the AGPL v3.0 License
+KoboldAI Lite by Concedo and the provided python ctypes bindings in koboldcpp dlls are licensed under the AGPL v3.0 License

README.md

@@ -1,6 +1,6 @@
 # koboldcpp
 
-KoboldCpp is an easy-to-use AI text-generation software for GGML and GGUF models. It's a single self contained distributable from Concedo, that builds off llama.cpp, and adds a versatile Kobold API endpoint, additional format support, Stable Diffusion image generation, backward compatibility, as well as a fancy UI with persistent stories, editing tools, save formats, memory, world info, author's note, characters, scenarios and everything Kobold and Kobold Lite have to offer.
+KoboldCpp is an easy-to-use AI text-generation software for GGML and GGUF models. It's a single self contained distributable from Concedo, that builds off llama.cpp, and adds a versatile Kobold API endpoint, additional format support, Stable Diffusion image generation, backward compatibility, as well as a fancy UI with persistent stories, editing tools, save formats, memory, world info, author's note, characters, scenarios and everything KoboldAI and KoboldAI Lite have to offer.
 
 ![Preview](media/preview.png)
 ![Preview](media/preview2.png)
@@ -20,7 +20,7 @@ KoboldCpp is an easy-to-use AI text-generation software for GGML and GGUF models
 - **(Nvidia Only) GPU Acceleration**: If you're on Windows with an Nvidia GPU you can get CUDA support out of the box using the `--usecublas` flag, make sure you select the correct .exe with CUDA support.
 - **Any GPU Acceleration**: As a slightly slower alternative, try CLBlast with `--useclblast` flags for a slightly slower but more GPU compatible speedup.
 - **GPU Layer Offloading**: Want even more speedup? Combine one of the above GPU flags with `--gpulayers` to offload entire layers to the GPU! **Much faster, but uses more VRAM**. Experiment to determine number of layers to offload, and reduce by a few if you run out of memory.
-- **Increasing Context Size**: Try `--contextsize 4096` to 2x your context size! without much perplexity gain. Note that you'll have to increase the max context in the Kobold Lite UI as well (click and edit the number text field).
+- **Increasing Context Size**: Try `--contextsize 4096` to 2x your context size! without much perplexity gain. Note that you'll have to increase the max context in the KoboldAI Lite UI as well (click and edit the number text field).
 - If you are having crashes or issues, you can try turning off BLAS with the `--noblas` flag. You can also try running in a non-avx2 compatibility mode with `--noavx2`. Lastly, you can try turning off mmap with `--nommap`.
 
 For more information, be sure to run the program with the `--help` flag, or [check the wiki](https://github.com/LostRuins/koboldcpp/wiki).
@@ -122,7 +122,7 @@ There are some community made AUR packages available: [CUBLAS](https://aur.archl
 
 ## License
 - The original GGML library and llama.cpp by ggerganov are licensed under the MIT License
-- However, Kobold Lite is licensed under the AGPL v3.0 License
+- However, KoboldAI Lite is licensed under the AGPL v3.0 License
 - The other files are also under the AGPL v3.0 License unless otherwise stated
 
 ## Notes

kcpp_docs.embd

@@ -607,7 +607,7 @@
                             "description": "Successful request"
                          }
                       },
-                      "description": "Retrieves the KoboldCpp preloaded story, --preloadstory configures a prepared story json save file to be hosted on the server, which frontends (such as Kobold Lite) can access over the API.",
+                      "description": "Retrieves the KoboldCpp preloaded story, --preloadstory configures a prepared story json save file to be hosted on the server, which frontends (such as KoboldAI Lite) can access over the API.",
                       "summary": "Retrieves the KoboldCpp preloaded story",
                       "tags": [
                          "api/extra"

klite.embd

@@ -1,12 +1,12 @@
 <!DOCTYPE html>
 <html lang="en">
 <!--
-Kobold Lite WebUI is a standalone WebUI for use with KoboldAI United, AI Horde, or koboldcpp.
+KoboldAI Lite WebUI is a standalone WebUI for use with KoboldAI United, AI Horde, or koboldcpp.
 It requires no dependencies, installation or setup.
 Just copy this single static HTML file anywhere and open it in a browser, or from a webserver.
-Please go to https://github.com/LostRuins/lite.koboldai.net for updates on Kobold Lite.
+Please go to https://github.com/LostRuins/lite.koboldai.net for updates on KoboldAI Lite.
 If you are submitting a pull request for Lite, PLEASE use the above repo, not the KoboldCpp one.
-Kobold Lite is under the AGPL v3.0 License unless otherwise exempted. Please do not remove this line.
+KoboldAI Lite is under the AGPL v3.0 License unless otherwise exempted. Please do not remove this line.
 Current version: 146
 -Concedo
 -->
@@ -3400,7 +3400,7 @@ Current version: 146
 		if ("Notification" in window) {
 			// Request permission to show notifications
 			if (Notification.permission === "granted" || notify_allowed) {
-				var notification = new Notification("Kobold Lite", {
+				var notification = new Notification("KoboldAI Lite", {
 					body: "Text Generation Completed!"
 				});
 			} else {
@@ -4295,7 +4295,7 @@ Current version: 146
 			document.getElementById("customkoboldendpoint").value = protocol + localmodehost + ":" + localmodeport + sublocalpathname;
 			connect_custom_endpoint();
 			document.getElementById("lastreq").innerHTML = document.getElementById("lastreq2").innerHTML =
-			`<span class=color_gray>You're using Kobold Lite Embedded.</span>`;
+			`<span class=color_gray>You're using KoboldAI Lite Embedded.</span>`;
 
 			read_url_params_data();
 		}
@@ -4605,7 +4605,7 @@ Current version: 146
 
 	function set_dalle_key()
 	{
-		inputBox("Enter DALL-E API Key.\n\nNote: DALL-E is known to rephrase and rewrite submitted image prompts before generating, for censorship purposes. There is nothing Kobold Lite can do about that. ","DALL-E API Key",localsettings.saved_dalle_key,"Input DALL-E API Key", ()=>{
+		inputBox("Enter DALL-E API Key.\n\nNote: DALL-E is known to rephrase and rewrite submitted image prompts before generating, for censorship purposes. There is nothing KoboldAI Lite can do about that. ","DALL-E API Key",localsettings.saved_dalle_key,"Input DALL-E API Key", ()=>{
 			let userinput = getInputBoxValue();
 			userinput = userinput.trim();
 			if (userinput != null && userinput!="") {
@@ -4615,7 +4615,7 @@ Current version: 146
 	}
 	function set_dalle_url()
 	{
-		inputBox("Enter DALL-E API URL.\n\nNote: DALL-E is known to rephrase and rewrite submitted image prompts before generating, for censorship purposes. There is nothing Kobold Lite can do about that. ","DALL-E API URL",localsettings.saved_dalle_url,"Input DALL-E API URL", ()=>{
+		inputBox("Enter DALL-E API URL.\n\nNote: DALL-E is known to rephrase and rewrite submitted image prompts before generating, for censorship purposes. There is nothing KoboldAI Lite can do about that. ","DALL-E API URL",localsettings.saved_dalle_url,"Input DALL-E API URL", ()=>{
 			let userinput = getInputBoxValue();
 			userinput = userinput.trim();
 			if (userinput != null && userinput!="") {
@@ -15400,7 +15400,7 @@ Current version: 146
 			<div class="layer-bottom gamescreenbgnormal normal_viewport_height" id="gamescreen">
 				<span id="gametext" contenteditable="false" onclick="click_gametext()" onblur="merge_edit_field()">
 					<p id="tempgtloadtxt">Loading...</p>
-					<noscript><style>#tempgtloadtxt { display: none; } #gametext { white-space: normal!important; }</style><p>Sorry, Kobold Lite requires Javascript to function.</p></noscript>
+					<noscript><style>#tempgtloadtxt { display: none; } #gametext { white-space: normal!important; }</style><p>Sorry, KoboldAI Lite requires Javascript to function.</p></noscript>
 				</span>
 				<div class="hidden" id="wimenu">
 				</div>
@@ -16404,7 +16404,7 @@ Current version: 146
 						</div>
 						<div class="settinglabel">
 							<div class="justifyleft settingsmall">Run In Background <span class="helpicon">?<span
-								class="helptext">Prevents the browser from suspending Kobold Lite by playing a silent audio track. This setting cannot be saved.</span></span></div>
+								class="helptext">Prevents the browser from suspending KoboldAI Lite by playing a silent audio track. This setting cannot be saved.</span></span></div>
 						   <input type="checkbox" id="run_in_background" style="margin:0px 0px 0px auto;">
 						</div>
 					</div>

koboldcpp.py

@@ -6,7 +6,7 @@
 # and adds a versatile Kobold API endpoint, additional format support,
 # backward compatibility, as well as a fancy UI with persistent stories,
 # editing tools, save formats, memory, world info, author's note, characters,
-# scenarios and everything Kobold and Kobold Lite have to offer.
+# scenarios and everything Kobold and KoboldAI Lite have to offer.
 
 import ctypes
 import os, math, re
@@ -1165,7 +1165,7 @@ class ServerRequestHandler(http.server.SimpleHTTPRequestHandler):
 <h2>KoboldCpp NoScript Mode</h2>
 <div>
 <p>KoboldCpp can be used without Javascript enabled, however this is not recommended.
-<br>If you have Javascript, please use <a href="/">Kobold Lite WebUI</a> instead.</p><hr>
+<br>If you have Javascript, please use <a href="/">KoboldAI Lite WebUI</a> instead.</p><hr>
 <form action="/noscript">
 Enter Prompt:<br>
 <textarea name="prompt" cols="60" rows="8" wrap="soft" placeholder="Enter Prompt Here">{prompt}</textarea>
@@ -1201,7 +1201,7 @@ Enter Prompt:<br>
         if self.path in ["", "/?"] or self.path.startswith(('/?','?')): #it's possible for the root url to have ?params without /
             content_type = 'text/html'
             if embedded_kailite is None:
-                response_body = (f"Embedded Kobold Lite is not found.<br>You will have to connect via the main KoboldAI client, or <a href='https://lite.koboldai.net?local=1&port={self.port}'>use this URL</a> to connect.").encode()
+                response_body = (f"Embedded KoboldAI Lite is not found.<br>You will have to connect via the main KoboldAI client, or <a href='https://lite.koboldai.net?local=1&port={self.port}'>use this URL</a> to connect.").encode()
             else:
                 response_body = embedded_kailite
 
@@ -3478,14 +3478,14 @@ def main(launch_args,start_server=True):
         with open(os.path.join(basepath, "klite.embd"), mode='rb') as f:
             embedded_kailite = f.read()
             # patch it with extra stuff
-            origStr = "Sorry, Kobold Lite requires Javascript to function."
+            origStr = "Sorry, KoboldAI Lite requires Javascript to function."
-            patchedStr = "Sorry, Kobold Lite requires Javascript to function.<br>You can use <a class=\"color_blueurl\" href=\"/noscript\">KoboldCpp NoScript mode</a> instead."
+            patchedStr = "Sorry, KoboldAI Lite requires Javascript to function.<br>You can use <a class=\"color_blueurl\" href=\"/noscript\">KoboldCpp NoScript mode</a> instead."
             embedded_kailite = embedded_kailite.decode("UTF-8","ignore")
             embedded_kailite = embedded_kailite.replace(origStr, patchedStr)
             embedded_kailite = embedded_kailite.encode()
-            print("Embedded Kobold Lite loaded.")
+            print("Embedded KoboldAI Lite loaded.")
     except Exception as e:
-        print("Could not find Kobold Lite. Embedded Kobold Lite will not be available.")
+        print("Could not find KoboldAI Lite. Embedded KoboldAI Lite will not be available.")
 
     try:
         basepath = os.path.abspath(os.path.dirname(__file__))
@@ -3698,7 +3698,7 @@ if __name__ == '__main__':
     advparser.add_argument("--remotetunnel", help="Uses Cloudflare to create a remote tunnel, allowing you to access koboldcpp remotely over the internet even behind a firewall.", action='store_true')
     advparser.add_argument("--highpriority", help="Experimental flag. If set, increases the process CPU priority, potentially speeding up generation. Use caution.", action='store_true')
     advparser.add_argument("--foreground", help="Windows only. Sends the terminal to the foreground every time a new prompt is generated. This helps avoid some idle slowdown issues.", action='store_true')
-    advparser.add_argument("--preloadstory", help="Configures a prepared story json save file to be hosted on the server, which frontends (such as Kobold Lite) can access over the API.", default="")
+    advparser.add_argument("--preloadstory", help="Configures a prepared story json save file to be hosted on the server, which frontends (such as KoboldAI Lite) can access over the API.", default="")
     advparser.add_argument("--quiet", help="Enable quiet mode, which hides generation inputs and outputs in the terminal. Quiet mode is automatically enabled when running a horde worker.", action='store_true')
     advparser.add_argument("--ssl", help="Allows all content to be served over SSL instead. A valid UNENCRYPTED SSL cert and key .pem files must be provided", metavar=('[cert_pem]', '[key_pem]'), nargs='+')
     advparser.add_argument("--nocertify", help="Allows insecure SSL connections. Use this if you have cert errors and need to bypass certificate restrictions.", action='store_true')