Instructions to use bigshanedogg/Concerto-Base-Origin with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bigshanedogg/Concerto-Base-Origin with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="bigshanedogg/Concerto-Base-Origin", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("bigshanedogg/Concerto-Base-Origin", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download NOTICE from bigshanedogg/Concerto-Base-Origin: direct link, hf CLI and curl.
- Browser
- Download file 1.6 kB
-
https://huggingface.co/bigshanedogg/Concerto-Base-Origin/resolve/main/NOTICE
- Command line
-
hf download hf://bigshanedogg/Concerto-Base-Origin/NOTICE
-
curl -L -o NOTICE https://huggingface.co/bigshanedogg/Concerto-Base-Origin/resolve/main/NOTICE
1.6 kB
| Concerto-Base-Origin -- unofficial transformers-format package (trust_remote_code) | |
| Packaged by bigshanedogg, 2026. NOT an official release of the original authors. | |
| Components | |
| ---------- | |
| 1. Concerto-Base-Origin weights (concerto_base_origin.pth) | |
| Source: https://huggingface.co/Pointcept/Concerto | |
| Copyright: Yujia Zhang, Xiaoyang Wu, Yixing Lao, Chengyao Wang, Zhuotao Tian, Naiyan Wang, Hengshuang Zhao | |
| License: CC-BY-NC-4.0 (non-commercial) -- LICENSE | |
| 2. Concerto inference code (vendored into concerto_*.py) | |
| Source: https://github.com/Pointcept/Concerto @ 5b41117160cdd92c3538be1911277b17e7ef5871 | |
| Copyright: Copyright (c) Meta Platforms, Inc. and affiliates; Pointcept | |
| License: Apache-2.0 -- LICENSE.code | |
| Changes made in this package | |
| ---------------------------- | |
| - concerto_*.py: the official files concatenated into flat files; package-internal imports replaced by relative imports (serialization's aliased encode / decode imports kept as aliased relative imports). No computation changed. | |
| - configuration_ / modeling_ / feature_extraction_ / processing_concerto.py: new transformers wrappers; the model runs PointTransformerV3.forward; the feature extractor is concerto.transform.default() applied to a copy of the input arrays (the transforms modify them in place). | |
| - model.safetensors: the .pth state dict under model.<original name>, converted by save_pretrained, every tensor checked equal. | |
| License files | |
| ------------- | |
| - LICENSE: Creative Commons Attribution-NonCommercial 4.0 International (weights) | |
| - LICENSE.code: Apache License 2.0, copy from Pointcept/Concerto (code) | |