Downloads · 30 days
0
task23-dino
jerseyjerry/task23-dino
task23-dino is a machine learning model from jerseyjerry. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Self-contained policy produced by trainsiglip2actionchunkvla.py.
Access
Public
Updated Jul 24, 2026
Parameters
1.1B
11.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors4.6 GB · 99%
At a glance
- Access
- Public
- Created
- Jul 22, 2026
- Updated
- Jul 24, 2026
- SHA
- 54d18433
Model card
From the Hugging Face model README
SigLIP2 So400m temporal action-chunk robotics VLA
Self-contained policy produced by train_siglip2_action_chunk_vla.py.
- Frozen SigLIP2 So400m 384/14 visual encoder
- Official global pooler token + pooled 8x8 spatial patch tokens (no CLS)
- Frozen SigLIP2 text encoder and normalized 1152D instruction embeddings
- Lowercased SentencePiece instructions with a 64-token context
- Raw-RGB spatial color tokens
- Four-step visual/proprio/phase history
- Three-head, eight-step 7D action chunks
- Overlapping temporal ensemble and gripper hysteresis at inference
- Parameters:
1,138,041,878 - Selected/refit epochs:
31
Upload every file in this directory. The adapter loads model.safetensors
strictly and performs no model-hub or network access.
The SigLIP2 checkpoint is distributed under Apache License 2.0. See LICENSE
and ATTRIBUTION.md.
- Created
- Jul 22, 2026
- Updated
- Jul 24, 2026