Instructions to use siyulw2025/v2-lora-full-abs with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use siyulw2025/v2-lora-full-abs with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
Configuration Parsing Warning:In adapter_config.json: "peft.task_type" must be a string
v2-lora-full-abs
LoRA with absolute action encoding. Scored 63/300.
Training Details
| Field | Value |
|---|---|
| Base model | 2toINF/X-VLA-Pt |
| Action encoding | absolute |
| Training config | lr=5e-4, coef=1.0, 20K iters |
| LoRA rank | 8 |
| Target modules | all-linear |
| Training data | 180 episodes of teleoperated cable insertion |
Usage
Action Encoding
This model was trained with absolute action encoding. When running inference, set or the serve.py will auto-detect from the sidecar file.
- Downloads last month
- 106
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support