Tabby

Dev tools

code completion

SHOW HN2023

627points
126comments
#34of 3,109 in 2023
Top 2%of 2023 by points

How HN took it

MixedNo clear lean

15 positive, 27 neutral or asking, 4 mixed, 14 critical, out of 60 comments about the project. Thread score +0.05.

Execution: 3 for, 7 againstIdea: 5 for, 2 againstDocs: 0 for, 3 againstPrivacy: 2 for, 0 againstPerformance: 0 for, 1 against

The thread, comment by comment

Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.

positive neutral or mixed critical about another commenter or something else the maker

What HN said

What people liked

  • Self-hosting addresses privacy and control concerns

    From 2 comments
    • “privacy” sits in a broader sea that includes “control”, “customization” and “lock-in”. i’ve been using the GPT family of tools less than otherwise because they’re constantly…
      colinsane on HN
    • Great to have a self-hosted solution, both for data privacy and quality improvement potentials.
      myin on HN
  • Good to see a self-hosted Copilot alternative

    From 2 comments
    • Very interesting to have a self-hosted version of Copilot. Will definitely try this out.
      arco1991 on HN
    • I think that this is a really cool project. Personally, I am working at a financial institution which is regulated, and the legal team + cyber are still evaluating if there would…
      funnyfoobar on HN

Objections

  • Demo generated buggy binary search code

    From 1 comment
    • I'm glad to see projects like this. I had a look at the demo (https://huggingface.co/spaces/TabbyML/tabby) and wasn't too impressed with the generated code for the default sample…
      hddqsb on HN
  • Docker image unavailable for Apple Silicon

    From 1 comment
    • Anyone know of a quick workaround for this? ``` % docker run \ -it --rm \ -v ./data:/data \ -v ./data/hf_cache:/home/app/.cache/huggingface \ -p 5000:5000 \ -e…
      simonw on HN
  • No training documentation in the introduction

    From 1 comment
    • I'm confused about the premise here. The power of self-hosting such a thing is presumably that you would be able to train it on your own company's codebase as a corpus of…
      uglycoyote on HN
  • Name clashes with the existing Tabby project

    From 1 comment
    • This exakt name is already used by a big open-source projekt, https://github.com/eugeny/tabby (50k stars) maybe consider changing the name for better SEO
      lfkdev on HN

Requests

  • AMD GPU support

    From 2 comments
    • Hi, will this work on AMD Gpu? I have plenty of VRAM available
      grudg3 on HN
    • Is AMD gpu support on the roadmap? I'm interested in this stuff but I won't be buying Nvidea cards.
      accelbred on HN
  • VS Code, Vim and IntelliJ extensions

    From 2 comments
    • I think that this is a really cool project. Personally, I am working at a financial institution which is regulated, and the legal team + cyber are still evaluating if there would…
      funnyfoobar on HN
    • Considering it's an alpha version I think a VSCode extension is the missing part
      jslakro on HN
  • Ability to fine-tune on own codebase

    From 2 comments
    • I think that this is a really cool project. Personally, I am working at a financial institution which is regulated, and the legal team + cyber are still evaluating if there would…
      funnyfoobar on HN
    • I'm confused about the premise here. The power of self-hosting such a thing is presumably that you would be able to train it on your own company's codebase as a corpus of…
      uglycoyote on HN

Questions

  • How does it compare to FauxPilot?

    From 2 comments
    • How does this compare to fauxpilot - https://github.com/fauxpilot/fauxpilot? Fauxpilot also uses Triton with fastertransformers and GPT-J style models (codegen).
      vikp on HN
    • What sort of resources do we need to run this, particularly VRAM? Also, how does this compare to Fauxpilot?
      syntaxing on HN
  • What VRAM is required?

    From 1 comment
    • What sort of resources do we need to run this, particularly VRAM? Also, how does this compare to Fauxpilot?
      syntaxing on HN
  • Will it run fast enough on Apple M1/M2 laptops?

    From 1 comment
    • My assumption is that this would not be fast enough for practical use on M1/M2 Macbooks. Is that correct?
      zoba on HN

Alternatives named

  • FauxPilot

    From 1 comment
    • How does this compare to fauxpilot - https://github.com/fauxpilot/fauxpilot? Fauxpilot also uses Triton with fastertransformers and GPT-J style models (codegen).
      vikp on HN
  • GitHub Copilot

    From 1 comment
    • Copilot has so far been pretty useful to me as a "sometimes smarter intellisense". It'll frequently correctly guess the arguments I want for a function (and their types), and…
      DanHulton on HN

Category, keywords, summaries and labels on this page were made by AI (Thread Reader v2) and not checked by hand. Each point links to the comments it came from.

Add a badge to your READMEShown on HackerShow
[![Shown on HackerShow](https://hackershow.org/badge.svg)](https://hackershow.org/show/35470915)