Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Sweep, Open-weights 1.5B model for next-edit autocomplete

huggingface.co

Post reply on HN
Print view View original

91–100 of 160 posts

Re: Show HN: Sweep, Open-weights 1.5B model for next-edit autocomplete

#91

Post by genghisjahn »

zarzavat wrote: post #75
vanillameow wrote: post #39

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 have always said this and had people on HN reply that they don't get much use out of autocomplete, which puzzled me. I'm starting to understand that there are two cultures. Developers who are mostly writing new code get the most benefit from autocomplete and comparatively less from Claude Code. CC is neat but when it attempts to create something from nothing the code is often low quality and needs substantial work.…

I’m in the “write new stuff with cc and get great code.” Of course I’ll be told I don’t really know what I’m doing. That I just don’t know the difference between good and bad quality code. Sigh.

Re: Show HN: Sweep, Open-weights 1.5B model for next-edit autocomplete

#92

Post by cmrdporcupine »

I've been trying my hands at implementing an emacs package for inline completions with this. I have it mostly working and performance is good enough but I haven't been blown away by the quality of its suggestions unfortunately. Which I guess is expected from a 1.5B model.

I'd love to see them making a larger model in the 10-20b range maybe? I know most people wouldn't be able to run that on their machines, but some could.

Running on ollama locally on NVIDIA Spark GB10. Tried it also with vLLM. Pretty fast.

Re: Show HN: Sweep, Open-weights 1.5B model for next-edit autocomplete

#93

Post by evolving-silica »

kamranjon wrote: post #4

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.

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)

Re: Show HN: Sweep, Open-weights 1.5B model for next-edit autocomplete

#94

Post by knowaveragejoe »

martianlantern wrote: post #11

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

Re: Show HN: Sweep, Open-weights 1.5B model for next-edit autocomplete

#95

Post by lasgawe »

leonardcser wrote: post #55

Hi, I tried the model and I am super impressed by the performance/quality. Thanks for making this open source! I am the author of this Neovim plugin for edit completions. I was able to integrate it with the Sweep Edit model. For anyone who is interested: https://github.com/leonardcser/cursortab.nvim

Hey this is really interesting. I'll try your nvim plugin

Re: Show HN: Sweep, Open-weights 1.5B model for next-edit autocomplete

#96

Post by jrop »

Between GLM-4.7-Flash and this announcement, THIS is what I'm excited to see in this space: pushing the capabilities of _small_ models further and further. It really feels like we're breaking into a space where models that can run on hardware that I actually own is getting better and better, and that has me excited.

Re: Show HN: Sweep, Open-weights 1.5B model for next-edit autocomplete

#97

Post by Imustaskforhelp »

Imustaskforhelp wrote: post #88
theophaniel wrote: post #80

Earlier quoted context omitted.

Could you give the gist / config on how you made it work with Zed ?

+1, I wasn't able to make it work on zed either and It would really help if woile can tell how they made it work on their workstation.

Edit: I asked chatgpt and just tinkered around till I found a setting which could work

{ "agent": { "default_model": { "model": "hf.co/sweepai/sweep-next-edit-1.5B:latest" } }, "inline_completion": { "default_provider": { "model": "hf.co/sweepai/sweep-next-edit-1.5B" } }, "chat_panel": { "default_provider": { "model": "hf.co/sweepai/sweep-next-edit-1.5B" } } }

Then go on the down bottom AI button or that gemini like logo and then select sweep model. And also you are expected to run ollama run command and ollama serve it

ollama pull hf.co/sweepai/sweep-next-edit-1.5B ollama run hf.co/sweepai/sweep-next-edit-1.5B

I did ask Chatgpt some parts about it tho and had to add this setting into my other settings too so ymmw but Its working for me

It's an interesting model for sure but I am unable to get tab auto_completion/inline in zed, I can ask it in summary and agentic mode of sorts and have a button at top which can generate code in file itself (which I found to be what I preferred in all this)

But I asked it to generate a simple hello world on localhost:8080 in golang and in the end it was able to but it took me like 10 minutes. But some other things like simple hello world was one shot for the most part

It's definitely an interesting model that's for sure. We need stronger model like these I can't imagine how strong it might be at 7B or 8B as iirc someone mentioned that this i think already has it or similar.

A lot of new developments are happening in here to make things smaller and I am all for it man!

Re: Show HN: Sweep, Open-weights 1.5B model for next-edit autocomplete

#98

Post by zarzavat »

genghisjahn wrote: post #91
zarzavat wrote: post #75

Earlier quoted context omitted.

I have always said this and had people on HN reply that they don't get much use out of autocomplete, which puzzled me. I'm starting to understand that there are two cultures. Developers who are mostly writing new code get the most benefit from autocomplete and comparatively less from Claude Code. CC is neat but when it attempts to create something from nothing the code is often low quality and needs substantial work.…

I’m in the “write new stuff with cc and get great code.” Of course I’ll be told I don’t really know what I’m doing. That I just don’t know the difference between good and bad quality code. Sigh.

The best code is no code.[0]

The main "issue" I have with Claude is that it is not good at noticing when code can be simplified with an abstraction. It will keep piling on lines until the file is 3000 lines long. You have to intervene and suggest abstractions and refactorings. I'm not saying that this is a bad thing. I don't want Claude refactoring my code (GPT-5 does this and it's very annoying). Claude is a junior developer that thinks it's a junior. GPT-5 is a junior developer that thinks it's a senior.

[0]: https://www.folklore.org/Negative_2000_Lines_Of_Code.html

Re: Show HN: Sweep, Open-weights 1.5B model for next-edit autocomplete

#99

Post by mika6996 »

Imustaskforhelp wrote: post #97
Imustaskforhelp wrote: post #88

Earlier quoted context omitted.

+1, I wasn't able to make it work on zed either and It would really help if woile can tell how they made it work on their workstation.

Edit: I asked chatgpt and just tinkered around till I found a setting which could work { "agent": { "default_model": { "model": "hf.co/sweepai/sweep-next-edit-1.5B:latest" } }, "inline_completion": { "default_provider": { "model": "hf.co/sweepai/sweep-next-edit-1.5B" } }, "chat_panel": { "default_provider": { "model": "hf.co/sweepai/sweep-next-edit-1.5B" } } } Then go on the down bottom AI button or that gemini like…

You sure this works? inline_completion and chat_panel give me "Property inline_completion is not allowed." - not sure if this works regardless?

Re: Show HN: Sweep, Open-weights 1.5B model for next-edit autocomplete

#100

Post by bradfa »

andruby wrote: post #37

How easy is it to re-train these to specific subset of programming languages? Could there be a "ruby+rails+html" version, etc?

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!
Post reply on HN