- https://hackmd.io/@whYPD8MBSHWRZV6y-ymFwQ/r1Wbg9DrA (請用此版本)
- https://hackmd.io/@whYPD8MBSHWRZV6y-ymFwQ/Hk8pJ95eA
- https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html
sudo apt update
sudo apt install php-cli jq
git clone https://github.com/c00cjz00/llmservice_ip.git
cd llmservice_ip/llmservice_one_ip
vi env.sample
- ./01-init.sh [cpu/gpu]
./01-init.sh gpu
docker compose up -d
docker compose down
- openwebui: http://$IP:8080
- ollama api: http://$IP:11434
- anythingllm: http://$IP:3001
- portal: http://$IP:80
- ollama api: http://host.docker.internal:11434
FROM ./taide-8b-a.3-q4_k_m.gguf
TEMPLATE """{{ if .System }}<|start_header_id|>system<|end_header_id|>
{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>
{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>
{{ .Response }}<|eot_id|>"""
PARAMETER stop "<|start_header_id|>"
PARAMETER stop "<|end_header_id|>"
PARAMETER stop "<|eot_id|>"
PARAMETER num_keep 24
PARAMETER num_ctx 4096
sudo nvidia-smi -pm 1
sudo nvidia-smi -e 0