File size: 652 Bytes
a5a3a6c c64c0bf 1d10d19 0727337 4040edc 5484659 a5a3a6c f5439f3 a5a3a6c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 |
#!/bin/bash
echo "$PWD"
export PATH="llama-b6795-bin-ubuntu-x64/build/bin:$PATH"
#huggingface-cli download unsloth/Qwen3-4B-Thinking-2507-GGUF --include --local-dir . --local-dir-use-symlinks False
#huggingface-cli download unsloth/Qwen3-4B-Thinking-2507-GGUF Qwen3-4B-Thinking-2507-Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
echo "$(ls)"
# Starting server
echo "Starting Llama-Cpp server"
sleep 10
cd llama-b6795-bin-ubuntu-x64/build/bin && chmod +x ./llama-server && ./llama-server --model /app/Qwen3-4B-Thinking-2507-Q4_K_M.gguf --host 0.0.0.0 --port 7860 --temp 1.0 --top-k 64 --top-k 0.95 --min-p 0.0 --log-file llama.log &
wait |