HN Explorer

Show HN: Sweep, Open-weights 1.5B model for next-edit autocomplete (huggingface.co)

534 points by williamzeng0 ↗ HN
Hey HN, we trained and open-sourced a 1.5B model that predicts your next edits, similar to Cursor. You can download the weights here (https://huggingface.co/sweepai/sweep-next-edit-1.5b) or try it in our JetBrains plugin (https://plugins.jetbrains.com/plugin/26860-sweep-ai-autocomp...).

Next-edit autocomplete differs from standard autocomplete by using your recent edits as context when predicting completions. The model is small enough to run locally while outperforming models 4x its size on both speed and accuracy.

We tested against Mercury (Inception), Zeta (Zed), and Instinct (Continue) across five benchmarks: next-edit above/below cursor, tab-to-jump for distant changes, standard FIM, and noisiness. We found exact-match accuracy correlates best with real usability because code is fairly precise and the solution space is small.

Prompt format turned out to matter more than we expected. We ran a genetic algorithm over 30+ diff formats and found simple `original`/`updated` blocks beat unified diffs. The verbose format is just easier for smaller models to understand.

Training was SFT on ~100k examples from permissively-licensed repos (4hrs on 8xH100), then RL for 2000 steps with tree-sitter parse checking and size regularization. The RL step fixes edge cases SFT can’t like, generating code that doesn’t parse or overly verbose outputs.

We're open-sourcing the weights so the community can build fast, privacy-preserving autocomplete for any editor. If you're building for VSCode, Neovim, or something else, we'd love to see what you make with it!

76 comments

[ 2.7 ms ] story [ 77.1 ms ] thread
kamranjon
I read the release but didn't quite understand the difference between a next-edit model and a FIM model - does anyone have a clear explanation of when to use one over the other? I'd love if there was a sublime plugin to utilize this model and try it out, might see if I can figure that out.
evolving-silica
I was curious as well and wanted to try how this work, so I asked claude to create a plugin for that. This utilizes built-in autocomplete behavior. If you want to give it a try then feel free to have a look here https://github.com/lumnn/AItoComplete (did not push it to packagecontrol yet)
mgz
I use Sweep’s Jetbrains autocomplete plugin daily, it really stands out.
dcreater
Based on qwen2.5-coder? seems like a "why not/resume embellish/show VC" type release I guess
kevinlu1248
You can see that Qwen3 does worse than Qwen2.5 on our benchmark. Reason is it's never been pretrained for FIM / autocomplete.
ing33k
can it be integrated in monaco editor ?
bangaladore
So SFT cost less only low hundreds of dollars? (1-10$ per hour per H100 if I'm seeing this correctly).

What about SFT?

Presumably basing this of Qwen is the reason it can be done for so cheap?

syntaxing
Wow super fun read, I love how it went into the technical details. Any way to make it work with vscode?
sim04ful
I'm very green to this so forgive if this question sounds silly:

Would instead of the RL step a constrained decoding say via something like xgrammar fix syntax generation issue ?

rationably
Do you plan to release Sweep 3B/7B on HF?
kevinlu1248
Not at the moment but we do host it for our Jetbrains plugin
_boffin_
Followed your work since the beginning and used it for inspiration for some cool demos on self-healing web scrapers. fascinating to see the transition from original concept to producing models. cool stuff.
whimsicalism
Very interesting - and cool to read about the development process. I'd love to hear more about how genetic algorithm worked here.

I wonder whether we are perhaps the point of usefulness of 'next edit' code development in 2026 though.

esquire_900
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!

kevinlu1248
Thanks! Let us know if you have any questions / feedback.
h33t-l4x0r
It sounds like you might be killing Zed's ability to monetize, am I misunderstanding that?
kleiba
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?

kevinlu1248
Not at the moment, if you install the hosted Sweep AI Jetbrains plugin it uses our hosted (larger) model.
moelf
what do people use for Neovim to integrate these models for tab-completion level of stuff. (i.e. non agentic/vibe coding)
magnat
Is there a way to use this (or similar) model in Visual Studio? Extensions on Visual Studio Marketplace are clunky and sluggish at best, if they even work at all.
KronisLV
I remember using Qwen 2.5 Coder for autocomplete with Continue.dev, that experience was a mess both in JetBrains IDEs, as well as Visual Studio Code.

People posting stuff like this is really cool because otherwise it kinda feels like nobody gives a crap, for example even with Cline/RooCode/KiloCode there’s no good way for me to hook up an autocomplete model that either runs in Ollama or maybe a remote Cerebras Code model, like KiloCode doesn’t have a proper model configuration option even if it has it for the chat or regular agentic stuff - I don’t get why autocomplete is such a special case.

I guess what I’m saying is that I’m glad someone’s at least trying so I don’t have to keep a Copilot subscription just because I genuinely like their autocomplete and the rest of it is basically wasted: Claude Code and Codex and others are better for the actual chat/agentic stuff, KiloCode and others are really nice IDE plugins.

vichle
What type of hardware do I need to run a small model like this? I don't do Apple.
andruby
How easy is it to re-train these to specific subset of programming languages? Could there be a "ruby+rails+html" version, etc?
bradfa
I'd love to be able to take an open model like this and feed it the codebases that I work on regularly in order to improve its performance for less "hip/modern" languages and frameworks. It would be awesome to see a blog post about how normal users can find tune these models and rough cost estimates with examples!
vanillameow
Sometimes when I use a plugin like this I get reminded just how much of a productivity nerf it is to code without an autocomplete AI. Honestly in my opinion if you write a lot of boilerplate code this is almost more useful than something like Claude Code, because it turbocharges your own train of thought rather than making you review someone else's, which may not align with your vision.

This is a really good plugin. I'm a diehard JetBrains user, I tried switching to VSCode and its various forks many times because of AI but muscle memory from years of use is hard to override. And for a lot of languages JetBrains is just much better, especially out of the box. But they dropped the ball so hard on AI it's unbelievable. Claude Code pulled it back a bit because at least now the cutting edge tools aren't just VSCode plugins, but I was still missing a solid autocomplete tool. Glad this is here to fill that niche. Very likely will be switching my GitHub copilot subscription to this.

I also really appreciate publishing open weights and allowing a privacy mode for anonymous trial users, even if it's opt-in. Usually these things seem to be reserved for paying tiers these days...

esafak
Junie is irredeemable but if it's autocomplete that you are unhappy about, IntelliJ has both local- and cloud autocomplete now.
norir
It is depressing that our collective solution to the problem of excess boilerplate keeps moving towards auto-generation of it.