121–130 of 160 posts
Very cool! I understand that the 1.5B is small enough to run locally... but does it actually in the Sweep AI Jetbrains plugin? That is, if I install the plugin, will I download the model automatically and the plugin doesn't phone home?
Surprising how badly Jetbrains implemented AI. Apparently to such an extent that even after multiple years of LLM's someone felt confident enough to build a company that can do better. This looks really neat, interesting technical writeup as well!
This is cool! I am more interested in how you guys generated next edit training data from repos, seems like there are lots of caveats here. Would love your insights Again amazing work! waiting for what you guys cook next
The blog post has more information: https://blog.sweep.dev/posts/oss-next-edit
https://blog.sweep.dev/posts/next-edit-jetbrains#building-au...
It's good. The blog post about it is very interesting. I hope, a plugin for neovim will be made soon. https://blog.sweep.dev/posts/oss-next-edit
Where is the training data? We can't keep calling those models "open source" if we have a black box and know precisely how they were made. "Open weights" are the new binary.
Hey, ollama run as suggested in hf doesn't seem to work with this model. This worked instead: ollama pull hf.co/sweepai/sweep-next-edit-1.5B
I've been using it with the Zed editor and it works quite well! Congrats. This kind of AI are the ones I like and I'm looking to run in my workstation.
Example here: https://huggingface.co/sweepai/sweep-next-edit-1.5B/blob/mai...
This is so cool. What is the second order effect of model training becoming democratized? And local models becoming the norm? Tasks like agentic work are well handled by current AI as long as you know what you're doing and can stress the agent against tests/spec, etc. I am thinking that one effect is: - it will become normal for meta-models to train a model specific to a particular task/product. Also, differently, I'…
This is really awesome detail. I’m very impressed by the amount of care taken to identify a good template. I started a small hook to try and do this using DSPy prompt optimizers, but haven’t had a compelling use case to try it with. This seems like an ideal case for trying DFT as well. I’m not sure if you’re using trl, but I’d suggest checking that out.
This is actually a game changer. I’ve been meaning to want to run models to accomplish exactly this, but don’t have enough VRAM on my GPU for the conventional LLM-method for the most part. This seems to be a far more efficient method of accomplishing a more scoped problem. Thank you for making it open source!
Hey, ollama run as suggested in hf doesn't seem to work with this model. This worked instead: ollama pull hf.co/sweepai/sweep-next-edit-1.5B