Spaces:
Sleeping
Sleeping
| # Start the Ollama server in the background | |
| ollama serve & | |
| # Wait a few seconds for the server to be fully operational | |
| sleep 5 | |
| # Pull the model from Hugging Face. | |
| # This command downloads the model and makes it available to the API. | |
| # It's the non-interactive version of "ollama run". | |
| 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 hf.co/bartowski/Qwen_Qwen3-1.7B-GGUF:Q4_K_M | |
| #ollama pull gemma3n:e2b-it-q4_K_M #slow on Spaces CPU | |
| ollama pull granite3.3:2b | |
| ollama pull hf.co/bartowski/tencent_Hunyuan-4B-Instruct-GGUF:Q4_K_M | |
| #---- 20250722 fail to run | |
| #ollama pull hf.co/ggml-org/SmolLM3-3B-GGUF:Q4_K_M | |
| #ollama pull hf.co/bartowski/nvidia_OpenReasoning-Nemotron-1.5B-GGUF:Q5_K_M | |
| # Start the Gradio web application | |
| # This will connect to the Ollama server which is already running. | |
| python3 app.py |