# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("immanuelpeter/MiniMax-M3.1-Flash-Vision")
model = AutoModel.from_pretrained("immanuelpeter/MiniMax-M3.1-Flash-Vision", device_map="auto")MiniMax-M3.1-Flash Vision
This repository packages the Tower and Projector from MiniMax M3.1 Flash.
Contents
| File | Tensors | What it holds |
|---|---|---|
model.safetensors |
515 | MiniMax-M3.1-Flash vision Tower |
projector.safetensors |
8 | multi_modal_projector and remapped patch_merge_mlp |
projector_config.json, projector.py |
Projector shapes and loader | |
config.json, preprocessor_config.json |
Vision-only model and image-processing configuration | |
export_manifest.json |
Source pin, tensor counts and file hashes | |
LICENSE, LICENSE-CODE, NOTICE |
Weight license, code license and attribution |
Architecture
| Component | Details |
|---|---|
| Tower | 32 layers, 1280 hidden, 16 heads, 5120 intermediate, patch size 14, 3D RoPE, image size 672 |
| Token compression | 2x2 spatial merge, temporal patch size 2 |
| Projector | Linear(1280, 6144), GELU, Linear(6144, 6144), flatten four 6144-wide patches, Linear(24576, 6144), GELU, Linear(6144, 6144) |
The class is MiniMaxM3VLVisionModel. Still images are repeated as two frames for the
temporal patch embedding. At 448 pixels the example reports Tower (1, 1024, 1280),
merged (1, 256, 5120) and projected (1, 256, 6144).
Usage
See examples/inference.py for image feature extraction.
Forward one image per call: the native HF attention couples images in a single call.
Validation
The release tests compare all 515 Tower tensors and eight Projector tensors with the
pinned parent checkpoint using torch.equal. Fixed-image Tower, merged and projected
outputs also match the native parent implementation at 56 and 448 pixels.
Reproduction
The export script reads the Tower and Projector tensors from the pinned parent and writes the original tensors, preserving their dtypes. The script pins the parent revision.
Credits
MiniMax released the MiniMax-M3.1-Flash weights and the native Transformers implementation.
License
MiniMax Community License, the same license as the source model. Helper code is MIT; see LICENSE-CODE and NOTICE.
- Downloads last month
- 77
Model tree for immanuelpeter/MiniMax-M3.1-Flash-Vision
Base model
MiniMaxAI/MiniMax-M3.1-Flash
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="immanuelpeter/MiniMax-M3.1-Flash-Vision")