koboldcpp/colab.ipynb
2023-10-20 11:35:44 +08:00

59 lines
No EOL
1.7 KiB
Text

{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "view-in-github"
},
"source": []
},
{
"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_S.gguf\" #@param [\"\"]{allow-input: true}\r\n",
"Layers = 43 #@param [43]{allow-input: true}\r\n",
"\r\n",
"%cd /content\r\n",
"!git clone https://github.com/LostRuins/koboldcpp\r\n",
"%cd /content/koboldcpp\r\n",
"!make LLAMA_CUBLAS=1\r\n",
"\r\n",
"!wget $Model -O model.ggml\r\n",
"!wget -c https://github.com/cloudflare/cloudflared/releases/latest/download/cloudflared-linux-amd64\r\n",
"!chmod +x cloudflared-linux-amd64\r\n",
"!nohup ./cloudflared-linux-amd64 tunnel --url http://localhost:5001 &\r\n",
"!sleep 10\r\n",
"!cat nohup.out\r\n",
"!python koboldcpp.py model.ggml --usecublas 0 mmq --gpulayers $Layers\r\n"
]
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"authorship_tag": "",
"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
}