mkdir gguf && cd gguf
wget -c https://nextcloud.openit.dev/s/4dRA4KdJb7rqDqw/download/Llama-3.2-3B-Instruct-Q4_K_M.gguf
cd
wget -c https://github.com/ggml-org/llama.cpp/releases/download/b9351/llama-b9351-bin-ubuntu-x64.tar.gz
wget -c https://github.com/ggml-org/llama.cpp/releases/download/b9371/llama-b9371-bin-ubuntu-x64.tar.gz tar -xvzf llama-b9371-bin-ubuntu-x64.tar.gz
mkdir build && mv llama-b9371/ build/bin/
nano .bashrc
export PATH="$HOME/build/bin:$PATH"
source .bashrc
llama-cli --version
llama-server -m gguf/Llama-3.2-3B-Instruct-Q4_K_M.gguf --host 0.0.0.0 --port 11435 -c 2048 -t 4
#!/bin/bash # Cambiar esta ruta cuando quieras otro modelo MODEL="$HOME/gguf/Llama-3.2-3B-Instruct-Q4_K_M.gguf" nohup llama-server \ --jinja \ -m "$MODEL" \ --host 127.0.0.1 \ --port 11435 \ -c 8192 \ -t 4 \ > /tmp/llama-server.log 2>&1 & echo $! > /tmp/llama-server.pid echo "Servidor iniciado. PID: $(cat /tmp/llama-server.pid)"
chmod u+x start-llama.sh ./start-llama.sh
#!/bin/bash if [ -f /tmp/llama-server.pid ]; then kill $(cat /tmp/llama-server.pid) rm /tmp/llama-server.pid echo "Servidor detenido" else pkill -f llama-server echo "Servidor detenido" fi
chmod u+x stop-llama.sh ./stop-llama.sh
pipx install git+https://github.com/OpenInterpreter/open-interpreter.git
interpreter --local
interpreter --api_base "http://127.0.0.1:11435/v1" --api_key "dummy"