Comment by alkh
7 days ago
I personally found Qwen2.5 Coder 7B to be on pair with deepseek-coder-v2:16b(but consumes less RAM on inference and faster), so that's what I am using locally. I actually created a custom model called "oneliner" that uses Qwen2.5 Coder 7B as a base and this system prompt:
SYSTEM """ You are a professional coder. You goal is to reply to user's questions in a consise and clear way. Your reply must include only code orcommands , so that the user could easily copy and paste them.
Follow these guidelines for python: 1) NEVER recommend using "pip install" directly, always recommend "python3 -m pip install" 2) The following are pypi modules: ruff, pylint, black, autopep8, etc. 3) If the error is module not found, recommend installing the module using "python3 -m pip install" command. 4) If activate is not available create an environment using "python3 -m venv .venv". """
I specifically use it for asking quick questions in terminal that I can copy & paste straight away(for ex. about git). For heavy-lifting I am using ChatGPT Plus(my own) + Github Copilot(provided by my company) + Gemini(provided by my company as well).
Can someone explain how one can set up autocomplete via ollama? That's something I would be interested to try.
NEVER recommend using "pip install" directly, always recommend "python3 -m pip install"
Just out of curiosity, what's the difference?
Seems like all the cool kids are using uv.
When you do `python -m pip install` you're going to get a version of pip that has the same idea of what its environment looks like as the python executable, which is what you want, and which isn't guaranteed with the the `pip` executable in your path.
As an aside, I disagree with the `python3` part... the `python3` name is a crutch that it's long past time to discard; if in 2025 just typing `python` gives you a python 2.x executable your workstation needs some serious updating and/or clean-up, and the sooner you find that out, the better.
Perhaps, but that's not really up to users. Linux distributions, for example, control this pretty directly. You can alias it, but why bother? If you know that Ubuntu links python3, every Ubuntu installation that gets python from apt is going to do this.
1 reply →
You mean to say that there is a lot of hype for uv because it is nice and quick but also gives an easy rhetorical win for junior people in any discussion about packaging in Python currently, so obviously that's going to be very popular even if it doesn't work for everyone.
The difference is to try to decouple the environment from the runtime essentially.
I only recently switched to uv and previously used pyenv, so this was more relevant to me before. There is a case when pip might not be pointing to the right python version, while `python3 -m pip` ensures you use the same one as your environment. For me it is mostly a habbit :)
If you ever find yourself arguing about the best Python package manager then you've already lost. Just use a real language with real library management. I dropped Python for Go and haven't looked back. There's plenty other alternatives. Python is such a waste of time.
Said unironically in a discussion about local llms and AI models.
uv? guess I'm old school.
pip install it is for me
There's nothing old school / cool kids about uv and pip. uv is a pip/venv/... interface. If you know how to use pip and venv, you know how to use uv. I use it as a useful toolchain to circumvent missing project/setup.py/requirements shenanigans