# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("immanuelpeter/PixtralViT-Large-4", trust_remote_code=True, device_map="auto")PixtralViT-Large-4
This repository packages the Tower and Projector from Mistral Large 4.
Contents
| File | Tensors | What it holds |
|---|---|---|
model.safetensors |
272 | Pixtral vision encoder, from the parent's vision_encoder.* |
projector.safetensors |
4 | pre_mm_projector_norm, patch_merger and vision_language_adapter |
modeling_pixtral_large4.py |
PixtralVisionModel subclass following the parent's numeric order |
|
projector.py, projector_config.json |
Projector shapes and loader | |
config.json, preprocessor_config.json |
Vision configuration and PixtralImageProcessor settings |
|
examples/inference.py |
Single-image extraction example | |
export_manifest.json |
Source pin, shard SHA256 and tensor name map | |
LICENSE, LICENSE-CODE, NOTICE |
Weight license, code license and attribution |
Architecture
| Component | Details |
|---|---|
| Tower | 30 blocks, 2048 hidden, 16 heads of 128, SwiGLU 6144, RMSNorm (eps 1e-5), 14 px patches, axial 2D RoPE, no class token, no final norm |
| Token compression | 2x2 patch merge inside the Projector |
| Projector | RMSNorm(2048), 2x2 patch merge to 8192, Linear(8192, 2048), Linear(2048, 6144), GELU, Linear(6144, 6144), no biases |
At 448 pixels the bench reports 1,024 Tower tokens of width 2048, 256 merged tokens of width 2048 and 256 projected tokens of width 6144.
Usage
See examples/inference.py for image feature extraction.
Validation
The release tests compare all 276 tensors with the pinned parent checkpoint using
torch.equal. Fixed-image Tower, merged and projected outputs also match the parent
implementation bit-for-bit in FP32 and BF16 at 448 and 1540 pixels.
Reproduction
The export script
range-reads the 276 vision tensors from the shard the pinned index names, renames
them to HF Pixtral names and reorders each wq and wk head from interleaved
rotary pairs to rotate-half order. It writes the original BF16 tensors. The script
pins the parent revision.
Credits
Mistral AI released the Mistral Large 4 weights and the mistral-inference reference code.
License
The weights keep the Mistral Ecosystem Open-Weight License from the source model. The Python files are MIT; see LICENSE-CODE.
- Downloads last month
- 79
Model tree for immanuelpeter/PixtralViT-Large-4
Base model
mistralai/Mistral-Large-4-1T-A52B
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="immanuelpeter/PixtralViT-Large-4", trust_remote_code=True)