Downloads · 30 days
7
5% of all-time downloads
v2-lora-full-abs
siyulw2025/v2-lora-full-abs
v2-lora-full-abs is a machine learning model from siyulw2025. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.
LoRA with absolute action encoding. Scored 63/300.
All-time downloads
133
Public
Repo size
47.6 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors47.6 MB · 95%
At a glance
- Library
- peft
- License
- apache-2.0
- Model type
- xvla
- Access
- Public
- Created
- Apr 30, 2026
- Updated
- Apr 30, 2026
- SHA
- ddd93ed3
Base models
Model card
From the Hugging Face model README
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.
- Library
- peft
- Type
- xvla
- License
- apache-2.0
- Created
- Apr 30, 2026
- Updated
- Apr 30, 2026