Instructions to use SimpleJev/JevAny-Robotics-4B-LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use SimpleJev/JevAny-Robotics-4B-LoRA with PEFT:
from peft import PeftModel from transformers import AutoModel base_model = AutoModel.from_pretrained("Qwen/Qwen3.5-4B") model = PeftModel.from_pretrained(base_model, "SimpleJev/JevAny-Robotics-4B-LoRA") - Notebooks
- Google Colab
- Kaggle
Download NOTICE from SimpleJev/JevAny-Robotics-4B-LoRA: direct link, hf CLI and curl.
- Browser
- Download file 866 Bytes
-
https://huggingface.co/SimpleJev/JevAny-Robotics-4B-LoRA/resolve/main/NOTICE
- Command line
-
hf download hf://SimpleJev/JevAny-Robotics-4B-LoRA/NOTICE
-
curl -L -o NOTICE https://huggingface.co/SimpleJev/JevAny-Robotics-4B-LoRA/resolve/main/NOTICE
866 Bytes
| JevAny | |
| Copyright 2026 Tianxin Wei | |
| This product includes modified source code from Kev by Jared Palmer: | |
| https://github.com/jaredpalmer/kev | |
| Kev is distributed under the Apache License 2.0. JevAny keeps that license, | |
| marks derived source files, and documents the changes in ACKNOWLEDGEMENTS.md. | |
| The Phi-4 conversion helper includes configuration and weight-name mappings | |
| adapted from Hugging Face Transformers, Copyright 2025 The HuggingFace Inc. team, | |
| under the Apache License 2.0: | |
| https://github.com/huggingface/transformers | |
| The released adapters require Qwen3.8-27B by the Qwen team. The base model is | |
| distributed separately under its own Apache License 2.0 terms. | |
| JevAny's decision interface is compatible with the public System One request | |
| shape. Jev and TypeSafe are names of their respective owners; this project is | |
| not affiliated with or endorsed by them. | |