taozhiyuai
taozhiyuai
`taozhiyu@Mac ~ % pip install 'gpt-computer-assistant[wakeword]' Looking in indexes: https://pypi.mirrors.ustc.edu.cn/simple/, https://pypi.tuna.tsinghua.edu.cn/simple, https://mirrors.aliyun.com/pypi/simple/ Requirement already satisfied: gpt-computer-assistant[wakeword] in /Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages (0.22.3) Collecting pvporcupine (from gpt-computer-assistant[wakeword]) Downloading https://mirrors.aliyun.com/pypi/packages/03/c3/e80f3e0cc081287daa439d2d2200d500a44f7a2bfd0efe1c55ecafa2121d/pvporcupine-3.0.3-py3-none-any.whl (2.4 MB) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 2.4/2.4 MB...
I want to use llama 3.1 70b on ollama. 1. what to fill in setting openai api key, openai base url? 2. how to set model name?
`taozhiyu@Mac ~ % computerassistant Profile: None Hardware accelerator e.g. GPU is available in the environment, but no `device` argument is passed to the `Pipeline` object. Model will be on CPU....
### What is the issue? taozhiyu@Mac ~ % ollama run hf-mirror.com/Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2-GGUF:Q8 pulling manifest Error: pull model manifest: 400: The specified tag is not a valid quantization scheme. Please use another...