Skip to content

MindForge

MindForge is the web training console for MinT. It implements a recursive self-improvement loop: the model solves problems, passing trajectories become SFT training data, the trained model solves more problems, and the cycle repeats — producing a continuously evolving model without hand-written training data.

All compute runs on remote MinT servers. You do not need a local GPU — only a browser, a MinT API key, and (for SDK use) a Python environment.

MindForge UI is Chinese-only

The MindForge web console is currently localised in Chinese only. The English documentation below describes the pages and actions in English; the in-product labels you see will be Chinese. Screenshots are therefore omitted from this English documentation and provided only in the Chinese version.

Accessing MindForge

MindForge is reached through the Playground on the MinT console — sign in at mint.macaron.im (outside mainland China) or mintcn.macaron.xin (mainland China), then click Playground in the sidebar; you are single-sign-on'd into MindForge. You can also open mindforge.macaron.xin directly.

The training loop

solve → score → train → solve again (with a stronger model) → ...
  1. Solve — the model reads each problem and generates solution code.
  2. Score — the code is executed and compared against expected results; each attempt is marked pass/fail.
  3. Training data — only passing trajectories are kept and turned into SFT data.
  4. Train — MinT LoRA SFT fine-tunes the model, producing a new version.
  5. Loop — the new version keeps solving, producing more correct trajectories.

You maintain the harness (the scoring and training pipeline); you do not hand-write training data. The model produces its own training data and keeps improving.

Platform features

The web console gives every operation in the loop a visual surface:

Page Function
Overview Resource status, MinT connection, running tasks, model-version evolution, evaluation-score comparison
Training Launch LoRA SFT training, pick base model and hyperparameters, resume from a checkpoint, view training curves
Evaluation Launch official SciCode Benchmark or question-bank evaluations, view details, heatmaps, pass-rate comparisons
Question Bank Browse question-bank versions, preview problems, launch question-bank eval, generate SFT data from passing trajectories
Data Manage SFT training data and question-bank data, upload/download files, preview rows
Guide Concept reference: checkpoints, using a trained model, switching the MinT backend

All compute-heavy operations (evaluation, training, data generation) run as background tasks; you can watch progress and logs live in the sidebar task panel.

Next steps