Colabcpp improvements (#512)
* Aria2 * Aria2 Typo fix * Streamlined Wget * Streamlining Fix * Back to .so downloading * Crash colab if no GPU is present * Created using Colaboratory * Restore proper link Colab overwrite the link, manually changing it back so people don't land on my branch. * Restore file juggle * Fixing the colab link... again
This commit is contained in:
henk717
GitHub
parent
5e5be717c3
commit
02595f9d21
1 changed files with 42 additions and 31 deletions
73
colab.ipynb
73
colab.ipynb
|
|
@ -3,8 +3,8 @@
|
|||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"colab_type": "text",
|
||||
"id": "view-in-github"
|
||||
"id": "view-in-github",
|
||||
"colab_type": "text"
|
||||
},
|
||||
"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>"
|
||||
|
|
@ -12,22 +12,28 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"id": "2FCn5tmpn3UV"
|
||||
},
|
||||
"source": [
|
||||
"## Welcome to the Official KoboldCpp Colab Notebook\r\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. \r\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`)"
|
||||
"## 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": {},
|
||||
"metadata": {
|
||||
"id": "QNaj3u0jn3UW"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#@title <-- Tap this if you play on Mobile { display-mode: \"form\" }\r\n",
|
||||
"%%html\r\n",
|
||||
"<b>Press play on the music player to keep the tab alive, then start KoboldCpp below</b><br/>\r\n",
|
||||
"#@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 src=\"https://raw.githubusercontent.com/KoboldAI/KoboldAI-Client/main/colab/silence.m4a\" controls>"
|
||||
]
|
||||
},
|
||||
|
|
@ -40,35 +46,40 @@
|
|||
},
|
||||
"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/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/Mistral-7B-Instruct-v0.1-GGUF/resolve/main/mistral-7b-instruct-v0.1.Q4_K_S.gguf\"]{allow-input: true}\r\n",
|
||||
"Layers = 43 #@param [43]{allow-input: true}\r\n",
|
||||
"ContextSize = 4096 #@param [4096] {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",
|
||||
"kvers = !(cat koboldcpp.py | grep 'KcppVersion = ' | cut -d '\"' -f2)\r\n",
|
||||
"kvers = kvers[0]\r\n",
|
||||
"!echo Finding prebuilt binary for {kvers}\r\n",
|
||||
"!wget -O dlfile.tmp -c 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\r\n",
|
||||
"!cp koboldcpp_cublas.so koboldcpp_cublas.dat\r\n",
|
||||
"!wget $Model -O model.ggml\r\n",
|
||||
"!python koboldcpp.py model.ggml --usecublas 0 mmq --multiuser --gpulayers $Layers --contextsize $ContextSize --hordeconfig concedo 1 1 --remotetunnel\r\n"
|
||||
"#@title <b>v-- Enter your model below and then click this to start Koboldcpp</b>\n",
|
||||
"\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/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/Mistral-7B-Instruct-v0.1-GGUF/resolve/main/mistral-7b-instruct-v0.1.Q4_K_S.gguf\"]{allow-input: true}\n",
|
||||
"Layers = 43 #@param [43]{allow-input: true}\n",
|
||||
"ContextSize = 4096 #@param [4096] {allow-input: true}\n",
|
||||
"\n",
|
||||
"import os\n",
|
||||
"if not os.path.isfile(\"/opt/bin/nvidia-smi\"):\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.⚠️\")\n",
|
||||
"\n",
|
||||
"%cd /content\n",
|
||||
"!git clone https://github.com/LostRuins/koboldcpp\n",
|
||||
"%cd /content/koboldcpp\n",
|
||||
"kvers = !(cat koboldcpp.py | grep 'KcppVersion = ' | cut -d '\"' -f2)\n",
|
||||
"kvers = kvers[0]\n",
|
||||
"!echo Finding prebuilt binary for {kvers}\n",
|
||||
"!wget -O dlfile.tmp -c https://kcppcolab.concedo.workers.dev/?{kvers} && mv dlfile.tmp koboldcpp_cublas.so\n",
|
||||
"!test -f koboldcpp_cublas.so && echo Prebuilt Binary Exists || echo Prebuilt Binary Does Not Exist\n",
|
||||
"!test -f koboldcpp_cublas.so && echo Build Skipped || make koboldcpp_cublas LLAMA_CUBLAS=1\n",
|
||||
"!cp koboldcpp_cublas.so koboldcpp_cublas.dat\n",
|
||||
"!apt install aria2 -y\n",
|
||||
"!aria2c -x 10 -o model.ggml --allow-overwrite=true --file-allocation=none $Model\n",
|
||||
"!python koboldcpp.py model.ggml --usecublas 0 mmq --multiuser --gpulayers $Layers --contextsize $ContextSize --hordeconfig concedo 1 1 --remotetunnel\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"accelerator": "GPU",
|
||||
"colab": {
|
||||
"authorship_tag": "",
|
||||
"gpuType": "T4",
|
||||
"include_colab_link": true,
|
||||
"private_outputs": true,
|
||||
"provenance": []
|
||||
"provenance": [],
|
||||
"cell_execution_strategy": "setup",
|
||||
"include_colab_link": true
|
||||
},
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3",
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue