Hacktoberfest 2026: los issues que los mantenedores marcaron para octubre, abiertos y aptos para principiantes. Explorar issues de Hacktoberfest

[Reproducibility] Training script / config for MiniMax-H3-TrainingAdapter (DeCFG adapter) itself

Abierto
  • ¿Algo no está bien?
#1,713 1 comentario 0 reacciones 0 asignados Ver en GitHub

Los mantenedores suelen responder en 1 día

Nadie ha tomado este issue todavía.

Evaluación

Dificultad
5/5
Tiempo estimado
Más de una semana
Aptitud para principiantes
35/100
Tipo de issue
Documentación
Claridad
Bastante claro
Estado de actividad
Activo
Stack tecnológico
python
Área
documentation, machine-learning

Línea de trabajo

Start with examples/minimax_h3/model_training/train.py and the scripts under examples/minimax_h3/model_training/lora/, then trace how preset_lora_path and preset_lora_model are consumed. Done means documenting or adding the adapter-training command, data selection, objective, hyperparameters, checkpoint choice, and weight conversion well enough to reproduce the named adapter files.

Escrito por el modelo de indexación a partir del texto del issue.

Descripción

Hi, and thanks for open-sourcing the MiniMax-H3 work.

I'd like to reproduce the training adapter itself — https://modelscope.ai/models/DiffSynth-Studio/MiniMax-H3-TrainingAdapter — not the downstream LoRAs.

What I've already found in the repo

  • examples/minimax_h3/model_training/train.py and the two-stage sft:data_process → sft:train workflow.
  • The .sh scripts under examples/minimax_h3/model_training/lora/ (e.g. MiniMax-H3-Pruned-FL2VA.sh, the Ref2VA variants). These train downstream LoRAs and reference the adapter only as an optional --preset_lora_path / --preset_lora_model "dit" to fuse in during training.
  • The base weights (Comfy-Org/MiniMax-H3, MiniMax/MiniMax-H3) and the MiniMax-H3-Self-Generated-Dataset.

What I can't find
A script or config that produces the adapter itself (the rank-64 DeCFG LoRA, FL2VA and Ref2VA variants) from the CFG-distilled base + the self-generated dataset. The example scripts consume the adapter rather than create it.

Could you share the following for the adapter's own training?

  1. The exact training script / command (equivalent .sh) used to produce model_for_comfy_dit.safetensors and model_ref2va_for_comfy_dit.safetensors.
  2. The DeCFG / "differential training" details — what the objective is and how it differs from standard SFT LoRA training (loss formulation, any CFG/DeCFG-specific handling, timestep sampling/shift).
  3. Hyperparameters: LoRA rank (64?) and target modules, learning rate, batch size, number of steps/epochs, dataset_repeat, resolution / num_frames, audio_loss_weight, optimizer/schedule, and seed if fixed.
  4. Which subset/split of MiniMax-H3-Self-Generated-Dataset was used, and whether the released dataset is the complete training set or a sample.
  5. Base checkpoint used as the starting point (the pruned bf16 DiT, or another), plus any pre/post-processing of the adapter weights (e.g. the ComfyUI qkv layout conversion).

Happy to open a PR to add a reproduction script/README under examples/minimax_h3/ if that's easier on your side. Thanks!

Lenguaje dominante
Python
Estrellas
13.2k
Forks
1.3k
Merge medio
22 h 15 min
PR fusionados (30 d)
31

Preparar el entorno

Este proyecto no incluye contenedor de desarrollo, Dockerfile ni guía de contribución, así que la configuración corre por tu cuenta: empieza por su README y consulta nuestra guía para la primera contribución para los pasos generales.

Primeros pasos

  1. Lee el issue completo y luego la guía de contribución del proyecto.
  2. Comenta en el issue que vas a ocuparte — evita que dos personas hagan lo mismo.
  3. Haz un fork del repositorio y trabaja en una rama.
  4. Abre un pull request que haga referencia al número del issue.

Más de modelscope/DiffSynth-Studio

Todos los issues de modelscope/DiffSynth-Studio

Issues similares

Más issues de Python

Recibe los nuevos issues en tu correo

Un resumen breve de issues de GitHub para principiantes.