DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to use Pssa: what you can do with it

What is Pssa? PSSA is a small non-transformer language model written from scratch in Rust, with a recurrent state-space layer, episodic memory, and a terminal dashboard.

How do I use it? Clone https://github.com/Sparticle62ops/pssa and build the Pssa binary with cargo; then run pssa train corpus.txt --no-tui to fit a PSSA checkpoint on your text file; run pssa train-transformer corpus.txt to fit the CPU decoder-only baseline. Full steps below.

Trended earlier

View repo on GitHub

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer

What do you want to do?

5 use cases

  • Train a PSSA checkpoint and benchmark it against a transformer

    Fit a small PSSA model on your own text, then score it against a matched transformer on held-out tokens.

    View prompt
    Use the Sparticle62ops/pssa repository. Train a PSSA checkpoint on <corpus-path> with `pssa train <corpus-path> --no-tui`, then run `pssa compare`. Report the held-out scores for both the PSSA and transformer models as JSON. Verify that both models were scored on the same held-out tokens before reporting a winner.

  • Monitor a long PSSA training run in the terminal dashboard

    Pipe a plain training log into the TUI to watch loss, speed, and checkpoints while training runs.

    View prompt
    In the Sparticle62ops/pssa repository, run `pssa train <corpus-path> -o chain/ck01.pssa --max-tokens 200000 -e 1 --no-tui | pssa tui --chain chain`. Report the loss, speed, and checkpoint events shown in the monitor. Verify that the file chain/ck01.pssa exists after the run.

  • Stop PSSA training when the loss blows up

    Use the loss guard flags to abort a run before a bad loss overwrites a good checkpoint.

    View prompt
    In the Sparticle62ops/pssa repository, run `pssa train <corpus-path> --loss-guard-high-factor 4 --loss-guard-jump-factor 8 --loss-guard-patience 3`. Report whether the run finished or halted, and the halt reason if it halted. Verify that no checkpoint was replaced after a halt.

  • Chat with a local PSSA checkpoint in the terminal

    Load a trained checkpoint in the TUI inference page and talk to it, with saved conversations.

    View prompt
    In the Sparticle62ops/pssa repository, start `pssa tui`, select a checkpoint with `/model <checkpoint-path>`, and send one message. Report the reply and the tokens per second shown. Verify that a JSON file was written in the chats folder.

  • Run the boxes-world recurrent model experiment

    Train an RSSM-style PSSA against a plain autoregressive control on a tiny box-pushing grid.

    View prompt
    In the Sparticle62ops/pssa repository, run `pssa world-model --seed <seed> --train-episodes 32 --heldout-episodes 12 --epochs 3`. Report the held-out next-frame NLL for the RSSM-style model and the plain control. Verify that the report states the comparison is not parameter or time matched before drawing any conclusion.

Quick start with Pssa

  1. Check you have what it needs: A Rust toolchain (inferred from the Rust implementation and the cargo commands in the README); The pssa binary built from the Sparticle62ops/pssa repository; A plain UTF-8 text file to train on.
  2. Open Sparticle62ops/pssa on GitHub and read the README and license.
  3. Clone https://github.com/Sparticle62ops/pssa and build the Pssa binary with cargo. (inferred, check the README)
  4. Run pssa train corpus.txt --no-tui to fit a PSSA checkpoint on your text file. (inferred, check the README)
  5. Run pssa train-transformer corpus.txt to fit the CPU decoder-only baseline. (inferred, check the README)
  6. Run pssa compare to replay the PSSA chain with a token and update matched transformer and score both on held-out tokens. (inferred, check the README)

These steps come from our top use case, Train a PSSA checkpoint and benchmark it against a transformer, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for Sparticle62ops/pssa

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Pssa alternatives · Best AI repos for Research

About this repo

  • Who it is forBuilt for ML researchers, students, and Rust developers who want to train, inspect, or extend a non-transformer language model on their own text.
  • Why it is hot117 stars, launched 68 days ago
  • LanguageRust
  • Sourcegithub.com/Sparticle62ops/pssa · Back to Hot repos

Requirements

  • A Rust toolchain (inferred from the Rust implementation and the cargo commands in the README)
  • The pssa binary built from the Sparticle62ops/pssa repository
  • A plain UTF-8 text file to train on
  • A terminal that supports the TUI, or use --no-tui for plain logs

Add this badge to your README

Maintain Pssa? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/Sparticle62ops/pssa.svg)](https://dedupedai.com/use-cases/sparticle62ops-pssa/?utm_source=github&utm_medium=badge&utm_campaign=Sparticle62ops-pssa)

HTML 

<a href="https://dedupedai.com/use-cases/sparticle62ops-pssa/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=Sparticle62ops-pssa"><img src="https://dedupedai.com/badge/Sparticle62ops/pssa.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about Pssa

What is Pssa?

PSSA is a small non-transformer language model written from scratch in Rust, with a recurrent state-space layer, episodic memory, and a terminal dashboard. It is an open-source project on GitHub: https://github.com/Sparticle62ops/pssa.

How do I use Pssa?

Clone https://github.com/Sparticle62ops/pssa and build the Pssa binary with cargo; then run pssa train corpus.txt --no-tui to fit a PSSA checkpoint on your text file; run pssa train-transformer corpus.txt to fit the CPU decoder-only baseline. The use cases on this page give the full steps and a copy-paste agent prompt for each job.

Who is Pssa for?

Built for ML researchers, students, and Rust developers who want to train, inspect, or extend a non-transformer language model on their own text.

What can I do with Pssa?

5 use cases so far, for example: Train a PSSA checkpoint and benchmark it against a transformer; Monitor a long PSSA training run in the terminal dashboard; Stop PSSA training when the loss blows up. Each has steps and a copy-paste agent prompt.

What do I need to run Pssa?

A Rust toolchain (inferred from the Rust implementation and the cargo commands in the README); The pssa binary built from the Sparticle62ops/pssa repository; A plain UTF-8 text file to train on; A terminal that supports the TUI, or use --no-tui for plain logs.

What are alternatives to Pssa?

Other hot AI repos in Research: Scientific Agent Skills, PersonaPlex, PageIndex, Book to Skill, Scientific Figure Library.

Is Pssa safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.