# Node-RED Flows for the StableCode-Completion-Alpha-3B-4K AI model

**URL:** <https://discourse.nodered.org/t/node-red-flows-for-the-stablecode-completion-alpha-3b-4k-ai-model/83124>\
**Category:** Share Your Projects\
**Created:** [23 November 2023 08:00 UTC](https://discourse.nodered.org/t/node-red-flows-for-the-stablecode-completion-alpha-3b-4k-ai-model/83124 "2023-11-23T08:00:57Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![rozek](https://sea2.discourse-cdn.com/flex026/user_avatar/discourse.nodered.org/rozek/32/48594_2.png) [@rozek](https://discourse.nodered.org/u/rozek)\
**Post date:** [23 November 2023 08:00 UTC](https://discourse.nodered.org/t/node-red-flows-for-the-stablecode-completion-alpha-3b-4k-ai-model/83124/1 "2023-11-23T08:00:58Z")

</div>

Just to let you know: I've just published a flow with HTTP endpoints for text completion and prompt tokenization [Stability AI's](https://huggingface.co/stabilityai) [StableCode-Completion-Alpha-3B-4K model](https://huggingface.co/stabilityai/stablecode-completion-alpha-3b-4k/blob/main/README.md) using [ggml](https://github.com/ggerganov/ggml) under the hood for inferencing on one's own machine.

Further details and instructions can be found in the related [GitHub repository](https://github.com/rozek/node-red-flow-stablecode-completion-alpha-3b-4k).

---

<div class="post-metadata">

**Author:** ![cymplecy](https://sea2.discourse-cdn.com/flex026/user_avatar/discourse.nodered.org/cymplecy/32/2773_2.png) [@cymplecy](https://discourse.nodered.org/u/cymplecy)\
**Post date:** [23 November 2023 14:07 UTC](https://discourse.nodered.org/t/node-red-flows-for-the-stablecode-completion-alpha-3b-4k-ai-model/83124/2 "2023-11-23T14:07:31Z")

</div>

What does this do - in muggle speak please? 🙂

---

<div class="post-metadata">

**Author:** ![rozek](https://sea2.discourse-cdn.com/flex026/user_avatar/discourse.nodered.org/rozek/32/48594_2.png) [@rozek](https://discourse.nodered.org/u/rozek)\
**Post date:** [23 November 2023 15:55 UTC](https://discourse.nodered.org/t/node-red-flows-for-the-stablecode-completion-alpha-3b-4k-ai-model/83124/3 "2023-11-23T15:55:28Z")

</div>

well, in the extreme case, this lets your computer write code in various programming languages for you - and since it offers HTML endpoints, you may access this functionality from a browser or any program that can handle HTTP requests. That way, you may build your own "autonomous agent" - with all components running locally, keeping your data safe and not requiring you to pay OpenAI...

---

<div class="post-metadata">

**Author:** ![cymplecy](https://sea2.discourse-cdn.com/flex026/user_avatar/discourse.nodered.org/cymplecy/32/2773_2.png) [@cymplecy](https://discourse.nodered.org/u/cymplecy)\
**Post date:** [23 November 2023 15:57 UTC](https://discourse.nodered.org/t/node-red-flows-for-the-stablecode-completion-alpha-3b-4k-ai-model/83124/4 "2023-11-23T15:57:18Z")

</div>

> [@rozek](#):
>
> well, in the extreme case

How about in the simplest case?

Or is this something too clever to have a simple use?

---

<div class="post-metadata">

**Author:** ![rozek](https://sea2.discourse-cdn.com/flex026/user_avatar/discourse.nodered.org/rozek/32/48594_2.png) [@rozek](https://discourse.nodered.org/u/rozek)\
**Post date:** [23 November 2023 16:00 UTC](https://discourse.nodered.org/t/node-red-flows-for-the-stablecode-completion-alpha-3b-4k-ai-model/83124/5 "2023-11-23T16:00:18Z")

</div>

well, just tell it to program a loop or s.th. similar - complexity depends on your request (and the abilities of the model - don't expect ChatGPT performance from a 3B LLM). Since everything is free, you may experiment freely with the tool - a user interface is in the making...

Just for comparison: ChatGPT is told to have 1000B parameters, Google Bard around 137B