Difference between revisions of "LLM: ollama install ubuntu 24.04"
Jump to navigation
Jump to search
Onnowpurbo (talk | contribs) (Created page with "Sumber: https://www.jeremymorgan.com/blog/generative-ai/local-llm-ubuntu/ Download curl -fsSL https://ollama.com/install.sh | sh Download model LLama3 wget https://oll...") |
Onnowpurbo (talk | contribs) |
||
(11 intermediate revisions by the same user not shown) | |||
Line 1: | Line 1: | ||
Sumber: https://www.jeremymorgan.com/blog/generative-ai/local-llm-ubuntu/ | Sumber: https://www.jeremymorgan.com/blog/generative-ai/local-llm-ubuntu/ | ||
+ | |||
+ | Pastikan: | ||
+ | * OS bisa linux server, seperti ubuntu server. | ||
+ | * Memory RAM pastikan cukup untuk menyimpan model-nya. Model llama3 butuh memory paling tidak 8GB. | ||
+ | * Kalau mau lebih enak/lebih cepat sebaiknya pakai GPU, seperti nvidia telsa yang agak baru. | ||
+ | |||
+ | |||
+ | Install aplikasi pendukung | ||
+ | |||
+ | sudo su | ||
+ | apt install curl net-tools | ||
Line 6: | Line 17: | ||
curl -fsSL https://ollama.com/install.sh | sh | curl -fsSL https://ollama.com/install.sh | sh | ||
− | + | Sebagai user biasa run & download model | |
+ | |||
+ | ollama serve | ||
+ | ollama pull llama3 | ||
+ | ollama run llama3 | ||
+ | |||
+ | |||
+ | OPTIONAL: Sebagai super user, | ||
+ | |||
+ | sudo su | ||
+ | sudo snap install --beta open-webui | ||
+ | |||
− | + | ==Contoh== | |
+ | curl http://localhost:11434/api/generate -d '{ | ||
+ | "model" : "llama3", | ||
+ | "prompt" : "tell me a joke", | ||
+ | "stream" : false | ||
+ | }' | ||
+ | |||
Line 15: | Line 43: | ||
* https://www.jeremymorgan.com/blog/generative-ai/local-llm-ubuntu/ | * https://www.jeremymorgan.com/blog/generative-ai/local-llm-ubuntu/ | ||
+ | * https://ollama.com/library |
Latest revision as of 17:08, 17 July 2024
Sumber: https://www.jeremymorgan.com/blog/generative-ai/local-llm-ubuntu/
Pastikan:
- OS bisa linux server, seperti ubuntu server.
- Memory RAM pastikan cukup untuk menyimpan model-nya. Model llama3 butuh memory paling tidak 8GB.
- Kalau mau lebih enak/lebih cepat sebaiknya pakai GPU, seperti nvidia telsa yang agak baru.
Install aplikasi pendukung
sudo su apt install curl net-tools
Download
curl -fsSL https://ollama.com/install.sh | sh
Sebagai user biasa run & download model
ollama serve ollama pull llama3 ollama run llama3
OPTIONAL: Sebagai super user,
sudo su sudo snap install --beta open-webui
Contoh
curl http://localhost:11434/api/generate -d '{ "model" : "llama3", "prompt" : "tell me a joke", "stream" : false }'