vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-09 16:44:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Breaking Change: Remove deprecated commands

Browse source
This commit is contained in:
Concedo 2023-10-03 17:16:09 +08:00
parent 5d3e142145
commit d10470a1e3
5 changed files with 49 additions and 136 deletions
Download patch file Download diff file Expand all files Collapse all files

78
colab.ipynb
View file

@ -1,29 +1,10 @@
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"private_outputs": true,
"provenance": [],
"gpuType": "T4",
"authorship_tag": "",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
},
"accelerator": "GPU"
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
"colab_type": "text",
"id": "view-in-github"
},
"source": []
},
@ -36,24 +17,43 @@
},
"outputs": [],
"source": [
"#@title <b>v-- Enter your model below and then click this to start Koboldcpp</b>\n",
"\n",
"Model = \"https://huggingface.co/TheBloke/Airoboros-L2-13B-2.2-GGUF/resolve/main/airoboros-l2-13b-2.2.Q4_K_M.gguf\" #@param [\"\"]{allow-input: true}\n",
"Layers = 43 #@param [43]{allow-input: true}\n",
"\n",
"%cd /content\n",
"!git clone https://github.com/LostRuins/koboldcpp\n",
"%cd /content/koboldcpp\n",
"!make LLAMA_CUBLAS=1\n",
"\n",
"!wget $Model -O model.ggml\n",
"!wget -c https://github.com/cloudflare/cloudflared/releases/latest/download/cloudflared-linux-amd64\n",
"!chmod +x cloudflared-linux-amd64\n",
"!nohup ./cloudflared-linux-amd64 tunnel --url http://localhost:5001 &\n",
"!sleep 10\n",
"!cat nohup.out\n",
"!python koboldcpp.py model.ggml --stream --usecublas 0 mmq --gpulayers $Layers --hordeconfig concedo\n"
"#@title <b>v-- Enter your model below and then click this to start Koboldcpp</b>\r\n",
"\r\n",
"Model = \"https://huggingface.co/TheBloke/Airoboros-L2-13B-2.2-GGUF/resolve/main/airoboros-l2-13b-2.2.Q4_K_M.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 --hordeconfig concedo\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
}