[-] lynx@sh.itjust.works 1 points 24 minutes ago

It's a good model, way better than the models from half a year ago.

[-] lynx@sh.itjust.works 6 points 2 months ago

You posted about it here: https://sh.itjust.works/post/11722444 This image is different to your last image.

The images you posted looks like this in gray scale:

This map seems to be unrelated to the actual numbers that i found online, but i also have not found any good statistics for the whole world.

17
Qwen2.5-Coder-7B (sh.itjust.works)

I've been using Qwen 2.5 Coder (bartowski/Qwen2.5.1-Coder-7B-Instruct-GGUF) for some time now, and it has shown significant improvements compared to previous open weights models.

Notably, this is the first model that can be used with Aider. Moreover, Qwen 2.5 Coder has made notable strides in editing files without requiring frequent retries to generate in the proper format.

One area where most models struggle, including this one, is when the prompt exceeds a certain length. In this case, it appears that the model becomes unable to remember the system prompt when the prompt length is above ~2000 tokens.

[-] lynx@sh.itjust.works 5 points 1 year ago

Split Horizon with Poison Reverse

[-] lynx@sh.itjust.works 8 points 2 years ago

This is probably the only reason microsoft recall exists, as it is completely useless for anything else.

[-] lynx@sh.itjust.works 12 points 2 years ago* (last edited 2 years ago)

The --rotate normal,inverted,left,right does not work, but you can use the transform option to achieve the same effect. To create the transformation matrix you can use something like: https://angrytools.com/css-generator/transform/

  • for translateXY enter half the screen resolution
  • don't copy the generated code, it has the numbers in the wrong order just type out the matrix row wise.

The final command looks like this:

xrandr --output screen-1 --transform 0.87,-0.50,960,0.50,0.87,540,0,0,1

To restore the original use (type this in first, because if you screw up you might not be able to see anything anymore):

xrandr --output screen-1 --transform 1,0,0,0,1,0,0,0,1

I tested it on x11.

[-] lynx@sh.itjust.works 24 points 2 years ago

How can you do fractional rotation? Does it only work with x11 or is it also supported in wayland?

[-] lynx@sh.itjust.works 29 points 2 years ago

Here is a gray scale version of the image with better contrast.

[-] lynx@sh.itjust.works 8 points 2 years ago

On Huggingface is a space where you can select the model and your graphics card and see if you can run it, or how many cards you need to run it. https://huggingface.co/spaces/Vokturz/can-it-run-llm

You should be able to do inference on all 7b or smaller models with quantization.

[-] lynx@sh.itjust.works 5 points 2 years ago

Question: What is the best self hosted coding assistant?

The (only) project i found, that does what i want:

It works ok for the most part. The problem i have with it is that inline completion is more annoying then helpful, because the AI only sees the last few lines that you wrote and therefore does not know the larger context of the project.

I also found this project, it looks promising. Has anyone tested it? Can you separate the server from the client?

Are there other projects that integrate well into an IDE?

[-] lynx@sh.itjust.works 9 points 2 years ago

You missed one C✝

[-] lynx@sh.itjust.works 16 points 2 years ago

the emotion is very human

view more: next ›

lynx

0 post score
0 comment score
joined 2 years ago