InternLM/Intern-Decision

Fast multi-modal decision model

Language modelsPython

4.5 Early signal Magnitude out of 10 — how fast interest is growing, not a quality score. Star growth looks organic. Data as of September 27, 2026, 09:23 UTC.

Open on Seismograph Open on GitHub

About the project

A multimodal decision model built on Qwen3.5 that turns a state, optional images, and typed questions (choice, score, yes/no) into decisions with probabilities. Ships with training, two inference backends, temperature calibration, and a browser demo.

Useful for

Run local inference of Intern-Decision-4B on an RTX 4090 to measure latency and accuracy
Calibrate model probabilities on a custom dataset via temperature scaling
Train the model on your own records using the runtime schema and collation from the repo

README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.

Why it’s trending

10 stars so far today, about 41 expected by the end of the day.
The spike has held for 2 days in a row — not a one-off blip.
The repository is 3 days old and already has 76 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
Top new repositories this week: #190.
About 9 forks a day — people are taking the code.

Stars per day

Bars are daily stars, the line is the usual pace. Red marks spike days.

Numbers

Total stars: 76
Today: 10 · ≈ 41 by evening
Forks: 8
Issues and pull requests: 0
Watchers: 1
Language: Python
Created: September 24, 2026
Last push: September 26, 2026

Star trust

Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.

These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.

Spotted in

September 27, 2026Top new repositories this week: #190

README badge

Paste it into your README — the badge shows the current magnitude and links to this page.

[![Seismograph](https://gitnova.dev/badge/InternLM/Intern-Decision.svg?lang=en)](https://gitnova.dev/en/r/InternLM/Intern-Decision)

Similar by description

4.3
Liuziyu77/Valen
A multimodal decision model built on a Qwen3.5-0.8B/2B backbone: it takes text, images and video with an instruction and returns probabilities over supplied candidates without generating answer tokens. The repo…

Early signalLanguage modelsPython+6 stars today, ≈ 42 by evening
1.0
fstandhartinger/jevbench
A benchmark for Jev-class decision models: the model receives state and a rubric, returns a typed answer with probabilities. It scores accuracy, calibration, speed, and cost.

CoolingLanguage modelsPython+0 stars today, ≈ 2 by evening
3.7
nokia-applied-research/AnyJev
Turns any LLM into a decision model with typed questions (choice, yes/no, score) that return real probabilities read from the next-token distribution, without training. L0 removes position and label-prior bias; L1 adds…

CoolingLanguage modelsPython+1 star today, ≈ 25 by evening
2.2
togethercomputer/tev1
Open dataset and fine-tuning recipe for Qwen3.5-4B that picks one of 2–24 options given context and a question. The repo ships data, build scripts, Together AI training and evaluation tooling.

CoolingLanguage modelsPython+3 stars today, ≈ 8 by evening
0.7
kshetrajna12/reflex
An open decision model: given a state (text, JSON, or image) and typed questions, it returns calibrated probabilities over fixed answer options. Runs on top of Qwen3.5 and answers with numbers instead of free text.

SteadyLanguage modelsPython+0 stars today, ≈ 1 by evening
1.2
SiliconLabAI/OpenJev
A System One-style decision playground: state plus typed questions in, structured answers out. Supports three backends — parallel LLM micro-scorers, a single JSON call to any OpenAI-compatible model, and the decider…

CoolingAI agentsTypeScript+0 stars today, ≈ 2 by evening