[Usage] Follow Quickstart but failed in HTTPConnectionPool(host='localhost', port=3000): Max retries exceeded with url: /api/download?author=example&name=academic_agent #242
Labels
usage
Question about how to use
Checked other resources
Your current environment
Ubuntu22,Using conda with python3.11
GPU v100
How would you like to use aios
I want to run aios with the Ollama llm endpoint
All the steps I used:
pip install -r requirements-cuda.txt
python main.py --llm_name ollama/llama3.1 --use_backend ollama --max_gpu_memory '{"0": "24GB"}' --eval_device "cuda:0" --max_new_tokens 256
But got traceback:
What did I miss. I saw port 3000 is for webui from source code?
The text was updated successfully, but these errors were encountered: