run.sh

#!/bin/bash

# Start the Ollama server in the background
ollama serve &

# Wait a few seconds for the server to be fully operational
sleep 5

ollama pull hf.co/bartowski/Qwen_Qwen3-4B-Instruct-2507-GGUF:Q4_K_M
#ollama pull hf.co/bartowski/Qwen_Qwen3-4B-Thinking-2507-GGUF:Q4_K_M
ollama pull smollm2:360m-instruct-q5_K_M
ollama pull hf.co/bartowski/Llama-3.2-3B-Instruct-GGUF:Q4_K_M
#ollama pull gemma3n:e2b-it-q4_K_M #slow on Spaces CPU
ollama pull granite3.3:2b

###20250812 ollama fail to run
#ollama pull hf.co/bartowski/tencent_Hunyuan-1.8B-Instruct-GGUF:Q4_K_M
#ollama pull hf.co/bartowski/tencent_Hunyuan-4B-Instruct-GGUF:Q4_K_M


# Start the Gradio web application
# This will connect to the Ollama server which is already running.
python3 app.py