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

Add context size parameter to google colab notebook (#489)

Browse source 
-add configurable context size to parameters along with models and layers for ease of use

-this can already be done with a simple edit by experienced llm users but new users may not know this is a parameter they should set.

Co-authored-by: LostRuins <39025047+LostRuins@users.noreply.github.com>
This commit is contained in:
teddybear082 2023-10-24 05:13:01 -04:00 • committed by GitHub
parent 7744aa6a9c
commit 7d120f2794
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
colab.ipynb
View file

@ -44,6 +44,7 @@
"\r\n", "\r\n",
"Model = \"https://huggingface.co/KoboldAI/LLaMA2-13B-Tiefighter-GGUF/resolve/main/LLaMA2-13B-Tiefighter.Q4_K_M.gguf\" #@param [\"\"]{allow-input: true}\r\n", "Model = \"https://huggingface.co/KoboldAI/LLaMA2-13B-Tiefighter-GGUF/resolve/main/LLaMA2-13B-Tiefighter.Q4_K_M.gguf\" #@param [\"\"]{allow-input: true}\r\n",
"Layers = 43 #@param [43]{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", "\r\n",
"%cd /content\r\n", "%cd /content\r\n",
"!git clone https://github.com/LostRuins/koboldcpp\r\n", "!git clone https://github.com/LostRuins/koboldcpp\r\n",
@ -58,11 +59,10 @@
"!wget $Model -O model.ggml\r\n", "!wget $Model -O model.ggml\r\n",
"!wget -c https://github.com/cloudflare/cloudflared/releases/latest/download/cloudflared-linux-amd64\r\n", "!wget -c https://github.com/cloudflare/cloudflared/releases/latest/download/cloudflared-linux-amd64\r\n",
"!chmod +x cloudflared-linux-amd64\r\n", "!chmod +x cloudflared-linux-amd64\r\n",
"!rm nohup.out\r\n",
"!nohup ./cloudflared-linux-amd64 tunnel --url http://localhost:5001 &\r\n", "!nohup ./cloudflared-linux-amd64 tunnel --url http://localhost:5001 &\r\n",
"!sleep 8\r\n", "!sleep 8\r\n",
"!cat nohup.out\r\n", "!cat nohup.out\r\n",
"!python koboldcpp.py model.ggml --usecublas 0 mmq --multiuser --gpulayers $Layers --contextsize 4096 --hordeconfig concedo 1 1 --onready \"echo Connect to the link below && cat nohup.out | grep trycloudflare.com\"\r\n" "!python koboldcpp.py model.ggml --usecublas 0 mmq --multiuser --gpulayers $Layers --contextsize $ContextSize --hordeconfig concedo 1 1 --onready \"echo Connect to the link below && cat nohup.out | grep trycloudflare.com && rm nohup.out\"\r\n"
] ]
} }
], ],