vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

removed c flag in wget

Browse source
This commit is contained in:
Concedo 2023-11-05 10:21:28 +08:00
parent 02595f9d21
commit faae84ee1d
1 changed files with 30 additions and 30 deletions
Download patch file Download diff file Expand all files Collapse all files

58
colab.ipynb
View file

@ -3,8 +3,8 @@
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": { "metadata": {
"id": "view-in-github", "colab_type": "text",
"colab_type": "text" "id": "view-in-github"
}, },
"source": [ "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>" "<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>"
@ -46,40 +46,40 @@
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
"#@title <b>v-- Enter your model below and then click this to start Koboldcpp</b>\n", "#@title <b>v-- Enter your model below and then click this to start Koboldcpp</b>\r\n",
"\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}\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}\n", "Layers = 43 #@param [43]{allow-input: true}\r\n",
"ContextSize = 4096 #@param [4096] {allow-input: true}\n", "ContextSize = 4096 #@param [4096] {allow-input: true}\r\n",
"\n", "\r\n",
"import os\n", "import os\r\n",
"if not os.path.isfile(\"/opt/bin/nvidia-smi\"):\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.⚠️\")\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",
"\n", "\r\n",
"%cd /content\n", "%cd /content\r\n",
"!git clone https://github.com/LostRuins/koboldcpp\n", "!git clone https://github.com/LostRuins/koboldcpp\r\n",
"%cd /content/koboldcpp\n", "%cd /content/koboldcpp\r\n",
"kvers = !(cat koboldcpp.py | grep 'KcppVersion = ' | cut -d '\"' -f2)\n", "kvers = !(cat koboldcpp.py | grep 'KcppVersion = ' | cut -d '\"' -f2)\r\n",
"kvers = kvers[0]\n", "kvers = kvers[0]\r\n",
"!echo Finding prebuilt binary for {kvers}\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\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\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\n", "!test -f koboldcpp_cublas.so && echo Build Skipped || make koboldcpp_cublas LLAMA_CUBLAS=1\r\n",
"!cp koboldcpp_cublas.so koboldcpp_cublas.dat\n", "!cp koboldcpp_cublas.so koboldcpp_cublas.dat\r\n",
"!apt install aria2 -y\n", "!apt install aria2 -y\r\n",
"!aria2c -x 10 -o model.ggml --allow-overwrite=true --file-allocation=none $Model\n", "!aria2c -x 10 -o model.ggml --allow-overwrite=true --file-allocation=none $Model\r\n",
"!python koboldcpp.py model.ggml --usecublas 0 mmq --multiuser --gpulayers $Layers --contextsize $ContextSize --hordeconfig concedo 1 1 --remotetunnel\n" "!python koboldcpp.py model.ggml --usecublas 0 mmq --multiuser --gpulayers $Layers --contextsize $ContextSize --hordeconfig concedo 1 1 --remotetunnel\r\n"
] ]
} }
], ],
"metadata": { "metadata": {
"accelerator": "GPU", "accelerator": "GPU",
"colab": { "colab": {
"gpuType": "T4",
"private_outputs": true,
"provenance": [],
"cell_execution_strategy": "setup", "cell_execution_strategy": "setup",
"include_colab_link": true "gpuType": "T4",
"include_colab_link": true,
"private_outputs": true,
"provenance": []
}, },
"kernelspec": { "kernelspec": {
"display_name": "Python 3", "display_name": "Python 3",