| #!/bin/bash |
| echo "=== STARTING AI SERVER (DUAL-CORE OPTIMIZED) ===" |
|
|
| |
| pkill -9 ollama || true |
| rm -rf /tmp/ollama* |
|
|
| |
| export OLLAMA_NUM_PARALLEL=1 |
| export OLLAMA_MAX_LOADED_MODELS=1 |
|
|
| |
| python -B download_models.py & |
|
|
| |
| ollama serve > ollama.log 2>&1 & |
|
|
| |
| for i in {1..60}; do |
| if curl -s http://127.0.0.1:11434/api/tags > /dev/null; then |
| echo "Ollama Ready" |
| break |
| fi |
| sleep 2 |
| done |
|
|
| |
| echo "Pulling DeepSeek-R1 7b (this may take a few minutes)..." |
| ollama pull deepseek-r1:7b |
|
|
| echo "Pulling Qwen-2.5 7b Instruct (Paling nurut format JSON)..." |
| ollama pull qwen2.5:7b-instruct |
|
|
| |
| exec uvicorn app:app --host 0.0.0.0 --port 7860 --workers 1 --timeout-keep-alive 600 |
