TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

TextSynth Server

274 pointsby catfishxabout 2 years ago

15 comments

hardwaresoftonabout 2 years ago
I&#x27;ve been feeling FOMO (for lack of a better term) about recent AI &amp; ML&#x2F;GPT progression.<p>It feels like ML&#x2F;AI it might be the beginning of the end for a large class of things (if I wanted to be alarmist I&#x27;d say &quot;everything&quot;) -- and the fact that Fabrice Bellard has jumped in and done the absolutely obvious rising-tide thing (building an API that abstracts the technologies) speaks volumes.<p>Releasing something like this fits to Fabrice&#x27;s pattern of work -- he built Qemu and that served as a similar enabling fabric for people to run virtual machines. QuickJS quietly powers some JS-on-another-platform functionality.<p>Simon was right. The Stable Diffusion moment[0] is already here. It&#x27;s going to accelerate. It was already moving at a speed that was hard to follow, and it&#x27;s about to get even faster.<p>There are too many world-changing things moving forward at the same time, and I&#x27;m only looking at such a small cut of the tech sphere. I don&#x27;t know what to do with myself, I feel so thoroughly unprepared.<p>[0]: <a href="https:&#x2F;&#x2F;simonwillison.net&#x2F;2023&#x2F;Mar&#x2F;11&#x2F;llama" rel="nofollow">https:&#x2F;&#x2F;simonwillison.net&#x2F;2023&#x2F;Mar&#x2F;11&#x2F;llama</a>
评论 #35200449 未加载
评论 #35198948 未加载
评论 #35196606 未加载
评论 #35195041 未加载
评论 #35194910 未加载
networkedabout 2 years ago
&gt; All is included in a single binary. Very few external dependencies (Python is not needed) so installation is easy on most Linux distributions.<p>I have to disagree. The combination of being closed-source and dynamically linked makes a program a hassle to run on Linux. Even if it isn&#x27;t at the moment of release, it soon becomes one. While <i>ts_server</i> is better than most, it already requires an old version of <i>libjpeg-turbo</i> not available in my distribution&#x27;s repositories. I had to run it in a Rocky Linux container:<p><pre><code> docker run \ --rm \ --mount type=bind,source=&quot;$(pwd)&quot;,target=&#x2F;app&#x2F; \ --publish 127.0.0.1:8080:8080 \ rockylinux:9 \ sh -c &#x27;dnf install -y libjpeg libmicrohttpd &amp;&amp; cd &#x2F;app&#x2F; &amp;&amp; .&#x2F;ts_server ts_server.cfg&#x27; </code></pre> The solutions to this problem that I am aware of that do not involve releasing the source code are: 1) static linking; 2) containers; 3) shipping a Windows binary :-) (&quot;Win32 is the only stable ABI on Linux&quot; -- <a href="https:&#x2F;&#x2F;blog.hiler.eu&#x2F;win32-the-only-stable-abi&#x2F;" rel="nofollow">https:&#x2F;&#x2F;blog.hiler.eu&#x2F;win32-the-only-stable-abi&#x2F;</a>).
评论 #35197514 未加载
JoachimSabout 2 years ago
The Fabrice Bellard web page must be one of the most underselling ones on the entire web. So many amazing projects. Not a word that really emphasize the importance, coolness. Just a simple list with short factual descriptions.
评论 #35194567 未加载
JacobiXabout 2 years ago
Very interesting as usual from Fabrice Bellard, but I&#x27;m a little bit disappointed this time, because libnc is a closed source DLL. Nevertheless it will be interesting to compare it to the amazing work of Georgi Gerganov: GGML Tensor Library. Both are heavily optimized, supports AVX intrinsics and are plain C&#x2F;C++ implementation without dependencies.
评论 #35195270 未加载
评论 #35195745 未加载
评论 #35211007 未加载
superkuhabout 2 years ago
Anyone know what format the models have to be in for use with textsynth? I looked at the gpt2 example binary (gpt2_117M.bin) and it seems like the &quot;normal&quot; params.json is embedded as a header for the binary and then some ascii string like &quot;attn&#x2F;c_attn&#x2F;&quot; and then the binary weights.<p>I tried just using the Stanford Alpaca fine-tuned version of the llama 7B weights that work with llama.cpp with textsynth but it didn&#x27;t like that (ggml-alpaca-7b-q4.bin: invalid file header). Having a textsynth HTTP API would save me a lot of hassle . I&#x27;m currently wrapping the stdin&#x2F;out of a execution of a modified llama.cpp binary and that&#x27;s extremely messy.
评论 #35215363 未加载
jefc1111about 2 years ago
In comments on this post, and elsewhere on other posts about AI, I see a lot of people referring to worries around the potential for lots of types of jobs to be heavily impacted by this technology.<p>I feel like people are often referring to &#x27;coding&#x27; when they express these worries. You know, actually writing code, having been given a spec to do so, and perhaps also participating in code review, writing tests, all the usual engineer stuff.<p>My question is, amongst the HN crowd, what kinds of roles or areas do we think might be somewhat immune to this effect? The first thing that occurs to me are security, infrastructure &amp; ops, networking. And of course the requirements gathering stage of software development. It is already the case that a lot of senior devs probably don&#x27;t write much code and spend more time on communication between different stakeholders and overseeing whoever (or whatever) is writing the code.<p>Anyone else been thinking about this? What tech roles might thrive in the face of AI.
评论 #35196449 未加载
评论 #35198629 未加载
canistelabout 2 years ago
This man, Fabrice Bellard again...<p>Frankly, I have not seen a more impressive portfolio of programming output.
评论 #35194984 未加载
评论 #35194396 未加载
Loicabout 2 years ago
For me, the most interesting part is the statistics on all the models. These show that 8 bit quantization is basically as good as the full model and 4 bit is very close. This is the first time I see such table across a large number of models in one place.
评论 #35194356 未加载
pierrecabout 2 years ago
&quot;<i>The CPU version is released as binary code under the MIT license</i>&quot;<p>This gives off the surreal sci-fi vibe that the binary <i>is</i> the source. And who knows... true wizards work in mysterious ways.
ggerganovabout 2 years ago
Very inspiring stuff! I hope one day we get to see the magic behind libnc.
generalizationsabout 2 years ago
Is it just me, or is the llama model not available to download there?<p>Edit: nevermind, the models are all there, just some of the links aren&#x27;t.
DeathArrowabout 2 years ago
If there were Oscars or Nobels for programming, Fabrice Bellard should have won one long ago!
评论 #35195595 未加载
aww_dangabout 2 years ago
Is it necessary to pre-process models from hugging face before using them with libnc ?
评论 #35206343 未加载
a_subsystemabout 2 years ago
&quot;...REST JSON API...&quot;<p>Please update.<p><a href="https:&#x2F;&#x2F;roy.gbiv.com&#x2F;untangled&#x2F;2008&#x2F;rest-apis-must-be-hypertext-driven" rel="nofollow">https:&#x2F;&#x2F;roy.gbiv.com&#x2F;untangled&#x2F;2008&#x2F;rest-apis-must-be-hypert...</a>
评论 #35201367 未加载
summarityabout 2 years ago
&gt; The GPU version is commercial software. Please contact...<p>Shame.
评论 #35194800 未加载
评论 #35194432 未加载
评论 #35196511 未加载
评论 #35194366 未加载
评论 #35194370 未加载