mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2025-09-08 16:19:05 +00:00
107 lines
No EOL
5.6 KiB
Text
107 lines
No EOL
5.6 KiB
Text
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {
|
||
"colab_type": "text",
|
||
"id": "view-in-github"
|
||
},
|
||
"source": [
|
||
"<a href=\"https://colab.research.google.com/github/LostRuins/koboldcpp/blob/concedo/colab.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {
|
||
"id": "2FCn5tmpn3UV"
|
||
},
|
||
"source": [
|
||
"## Welcome to the Official KoboldCpp Colab Notebook\n",
|
||
"It's really easy to get started. Just press the two **Play** buttons below, and then connect to the **Cloudflare URL** shown at the end.\n",
|
||
"You can select a model from the dropdown, or enter a **custom URL** to a GGUF model (Example: `https://huggingface.co/KoboldAI/LLaMA2-13B-Tiefighter-GGUF/resolve/main/LLaMA2-13B-Tiefighter.Q4_K_M.gguf`)\n",
|
||
"\n",
|
||
"**Keep this page open and occationally check for captcha's so that your AI is not shut down**"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"metadata": {
|
||
"id": "QNaj3u0jn3UW"
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"#@title <-- Tap this if you play on Mobile { display-mode: \"form\" }\n",
|
||
"%%html\n",
|
||
"<b>Press play on the music player to keep the tab alive, then start KoboldCpp below</b><br/>\n",
|
||
"<audio autoplay=\"\" src=\"https://raw.githubusercontent.com/KoboldAI/KoboldAI-Client/main/colab/silence.m4a\" loop controls>"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"metadata": {
|
||
"cellView": "form",
|
||
"id": "uJS9i_Dltv8Y"
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"#@title <b>v-- Enter your model below and then click this to start Koboldcpp</b>\r\n",
|
||
"\r\n",
|
||
"Model = \"https://huggingface.co/KoboldAI/LLaMA2-13B-Tiefighter-GGUF/resolve/main/LLaMA2-13B-Tiefighter.Q4_K_M.gguf\" #@param [\"https://huggingface.co/KoboldAI/LLaMA2-13B-Tiefighter-GGUF/resolve/main/LLaMA2-13B-Tiefighter.Q4_K_M.gguf\",\"https://huggingface.co/Sao10K/Fimbulvetr-11B-v2-GGUF/resolve/main/Fimbulvetr-11B-v2-Test-14.q4_K_M.gguf\",\"https://huggingface.co/TheBloke/MythoMax-L2-13B-GGUF/resolve/main/mythomax-l2-13b.Q4_K_M.gguf\",\"https://huggingface.co/TheBloke/ReMM-SLERP-L2-13B-GGUF/resolve/main/remm-slerp-l2-13b.Q4_K_M.gguf\",\"https://huggingface.co/TheBloke/Xwin-LM-13B-v0.2-GGUF/resolve/main/xwin-lm-13b-v0.2.Q4_K_M.gguf\",\"https://huggingface.co/TheBloke/Stheno-L2-13B-GGUF/resolve/main/stheno-l2-13b.Q4_K_M.gguf\",\"https://huggingface.co/TheBloke/MythoMax-L2-Kimiko-v2-13B-GGUF/resolve/main/mythomax-l2-kimiko-v2-13b.Q4_K_M.gguf\",\"https://huggingface.co/TheBloke/airoboros-mistral2.2-7B-GGUF/resolve/main/airoboros-mistral2.2-7b.Q4_K_S.gguf\",\"https://huggingface.co/afrideva/phi-2-uncensored-GGUF/resolve/main/phi-2-uncensored.q3_k_m.gguf\"]{allow-input: true}\r\n",
|
||
"Layers = 99 #@param [99]{allow-input: true}\r\n",
|
||
"ContextSize = 4096 #@param [4096] {allow-input: true}\r\n",
|
||
"ForceRebuild = False #@param {type:\"boolean\"}\r\n",
|
||
"LoadImageModel = False \r\n",
|
||
"SDModel = \"\"\r\n",
|
||
"SDCommand = \"\"\r\n",
|
||
"\r\n",
|
||
"import os\r\n",
|
||
"if not os.path.isfile(\"/opt/bin/nvidia-smi\"):\r\n",
|
||
" raise RuntimeError(\"⚠️Colab did not give you a GPU due to usage limits, this can take a few hours before they let you back in. Check out https://lite.koboldai.net for a free alternative (that does not provide an API link but can load KoboldAI saves and chat cards) or subscribe to Colab Pro for immediate access.⚠️\")\r\n",
|
||
"\r\n",
|
||
"%cd /content\r\n",
|
||
"!git clone https://github.com/LostRuins/koboldcpp\r\n",
|
||
"%cd /content/koboldcpp\r\n",
|
||
"kvers = !(cat koboldcpp.py | grep 'KcppVersion = ' | cut -d '\"' -f2)\r\n",
|
||
"kvers = kvers[0]\r\n",
|
||
"if ForceRebuild:\r\n",
|
||
" kvers = \"force_rebuild\"\r\n",
|
||
"if SDModel and LoadImageModel:\r\n",
|
||
" SDCommand = \"--sdconfig sdmodel.safetensors clamped 4 quant\"\r\n",
|
||
"else:\r\n",
|
||
" SDCommand = \"\"\r\n",
|
||
"!echo Finding prebuilt binary for {kvers}\r\n",
|
||
"!wget -O dlfile.tmp https://kcppcolab.concedo.workers.dev/?{kvers} && mv dlfile.tmp koboldcpp_cublas.so\r\n",
|
||
"!test -f koboldcpp_cublas.so && echo Prebuilt Binary Exists || echo Prebuilt Binary Does Not Exist\r\n",
|
||
"!test -f koboldcpp_cublas.so && echo Build Skipped || make koboldcpp_cublas LLAMA_CUBLAS=1 LLAMA_COLAB=1 LLAMA_PORTABLE=1\r\n",
|
||
"!cp koboldcpp_cublas.so koboldcpp_cublas.dat\r\n",
|
||
"!apt update\r\n",
|
||
"!apt install aria2 -y\r\n",
|
||
"!aria2c -x 10 -o model.gguf --summary-interval=5 --download-result=default --allow-overwrite=true --file-allocation=none $Model\r\n",
|
||
"if SDCommand:\r\n",
|
||
" !aria2c -x 10 -o sdmodel.safetensors --summary-interval=5 --download-result=default --allow-overwrite=true --file-allocation=none $SDModel\r\n",
|
||
"!python koboldcpp.py model.gguf --usecublas 0 mmq --multiuser --gpulayers $Layers --contextsize $ContextSize --quiet --remotetunnel $SDCommand\r\n"
|
||
]
|
||
}
|
||
],
|
||
"metadata": {
|
||
"accelerator": "GPU",
|
||
"colab": {
|
||
"cell_execution_strategy": "setup",
|
||
"gpuType": "T4",
|
||
"include_colab_link": true,
|
||
"private_outputs": true,
|
||
"provenance": []
|
||
},
|
||
"kernelspec": {
|
||
"display_name": "Python 3",
|
||
"name": "python3"
|
||
},
|
||
"language_info": {
|
||
"name": "python"
|
||
}
|
||
},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 0
|
||
} |