Instructions to use corechan/MiniMax-H3_NF4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use corechan/MiniMax-H3_NF4 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("corechan/MiniMax-H3_NF4", dtype=torch.bfloat16, device_map="cuda") prompt = "Hi, what can you help me with?" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
|
Download README.md from corechan/MiniMax-H3_NF4: direct link, hf CLI and curl.
- Browser
- Download file 3.7 kB
-
https://huggingface.co/corechan/MiniMax-H3_NF4/resolve/main/README.md
- Command line
-
hf download hf://corechan/MiniMax-H3_NF4/README.md
-
curl -L -o README.md https://huggingface.co/corechan/MiniMax-H3_NF4/resolve/main/README.md
3.7 kB
| license: other | |
| license_name: minimax-h3-community-license | |
| license_link: https://huggingface.co/corechan/MiniMax-H3_NF4/resolve/main/LICENSE | |
| tags: | |
| - text-generation | |
| - text-to-video | |
| - video-generation | |
| - quantized | |
| - nf4 | |
| - bitsandbytes | |
| # MiniMax-H3-NF4 | |
| This repository contains an **NF4 (NormalFloat 4) quantized version** of the **MiniMax-H3** text-to-video model. It was quantized using `bitsandbytes` to reduce memory footprints while preserving model quality as much as possible. | |
| ## Original Model Details | |
| * **Developed by:** MiniMax | |
| * **Original Repository:** [MiniMaxAI/MiniMax-H3](https://huggingface.co/MiniMaxAI/MiniMax-H3) | |
| ## Quantization Details | |
| * **Format:** NF4 (NormalFloat 4) via `bitsandbytes` | |
| * **Target:** Linear layers | |
| ## License and Terms of Use ⚠️ IMPORTANT | |
| This model is a derivative work of MiniMax-H3 and is distributed under the **MiniMax H3 Community License Agreement**. By downloading or using this model, you and your downstream users agree to be bound by all terms, conditions, and the Acceptable Use Policy of the original license. | |
| ### Key Terms to Remember: | |
| 1. **Commercial Use Threshold:** Free commercial use, modification, and redistribution are permitted **ONLY** for entities with an annual revenue of **less than $20 million USD**. If your annual revenue exceeds this threshold, you must obtain a separate written license from MiniMax. | |
| 2. **Excluded Territories:** This community license **DOES NOT** grant any rights to use, display, or distribute this model or its outputs within the following territories: **The United States, The European Union, The United Kingdom, and South Korea**. Users in these regions must contact MiniMax directly for separate authorization. | |
| 3. **No Cross-Model Improvement:** You may not use this model or its outputs to train, align, or improve any AI models other than MiniMax-H3 or its direct derivatives. | |
| 4. **Attribution:** Any commercial products or interfaces utilizing this model must display appropriate credit to MiniMax. | |
| For the full license terms, please read the `LICENSE` file in this repository or refer to the official [MiniMax H3 Community License Agreement](https://huggingface.co). | |
| --- | |
| ## 日本語概要 (Japanese Summary) | |
| 本リポジトリは **MiniMax-H3** の **NF4 (NormalFloat 4) 量子化版**モデルです。 | |
| ### ライセンスに関する重要な注意点 | |
| 本モデルは独自の **MiniMax H3 Community License Agreement** に基づいて配布されています。ダウンロードおよび利用にあたっては、以下の制限が自動的に適用されます。 | |
| * **商用利用の制限**: 年間売上が **2,000万米ドル(約31億円)未満** の組織・個人に限り、無料での商用利用・改変・再配布が認められています。これを超える場合はMiniMax社との個別契約が必要です。 | |
| * **地域制限(適用外地域)**: **アメリカ、EU、イギリス、韓国** の4地域は本ライセンスの適用外(除外地域)です。これらの地域での利用や、出力結果の表示・頒布には別途許諾が必要です。 | |
| * **禁止事項**: 本モデルの出力成果物を、MiniMax-H3シリーズ以外の別のAIモデルの学習や改善(蒸留など)に利用することは禁止されています。 | |
| * **帰属表示**: 商用プロダクトで利用する際は、MiniMax社のベースモデルである旨のクレジット表記が必要です。 | |
| --- | |
| ### Disclaimer | |
| The author of this repository is not affiliated with MiniMax. This quantized version is provided "as-is" for the community, and users are solely responsible for ensuring compliance with the original license terms. | |