Downloads · 30 days
24
45% of all-time downloads
jasper0314/starvla-libero-qwen3.5-0.8b-discrete-oft
starvla-libero-qwen3.5-0.8b-discrete-oft is a reinforcement learning model from jasper0314. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product.
This is a compact vision-language-action policy built on Qwen/Qwen3.5-0.8B and supervised-fine-tuned on the combined LIBERO training data. It uses a parallel categorical OFT action head and is packaged as a portable c…
Downloads · 30 days
24
45% of all-time downloads
All-time downloads
53
Public
Parameters
1.1B
2.3 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors2.2 GB · 99%
From the Hugging Face model README
This is a compact vision-language-action policy built on
Qwen/Qwen3.5-0.8B and supervised-fine-tuned on the combined LIBERO training
data. It uses a parallel categorical OFT action head and is packaged as a
portable checkpoint for the QwenDiscreteOFT integration in SimpleVLA-RL.
The checkpoint contains the complete VLM and action-head weights. In
particular, base_vlm in qwen_discrete_oft.json is provenance metadata; the
SimpleVLA-RL runtime does not download or import vla-mono, StarVLA, or
OpenVLA-OFT.
| Field | Value |
|---|---|
| Parameters | 867,163,968 |
| Visual input | Agent view + wrist view, 224×224 RGB |
| Action chunk | 8 steps × 7 dimensions |
| Discretization | 256 bins over [-1, 1] |
| Gripper | Binary categorical dimension |
| Normalization | Dataset min/max |
| SFT data | libero_all |
| SFT steps | 30,000 |
| Seed | 42 |
Evaluation used deterministic argmax actions, the two-view inference pipeline, 50 initial states per task, and all 10 tasks in each suite. There were 2,000 episodes in total and no environment/infrastructure errors.
| Suite | Successes | Episodes | Success rate |
|---|---|---|---|
| LIBERO-Spatial | 483 | 500 | 96.6% |
| LIBERO-Object | 496 | 500 | 99.2% |
| LIBERO-Goal | 472 | 500 | 94.4% |
| LIBERO-10 | 442 | 500 | 88.4% |
| Overall | 1,893 | 2,000 | 94.65% |
The episode horizons were 220, 280, 300, and 520 environment steps for
Spatial, Object, Goal, and LIBERO-10 respectively. See eval_results.json for
machine-readable counts and protocol metadata.
Use the QwenDiscreteOFT branch of JustinKai0527/VLASafety:
cd SimpleVLA-RL
pip install -r requirements-qwen35.txt
SFT_MODEL_PATH=jasper0314/starvla-libero-qwen3.5-0.8b-discrete-oft \
CKPT_PATH=/path/to/rl-checkpoints \
bash examples/run_qwen35_discrete_oft_rl_libero.sh
Use a dedicated environment for this model because Qwen3.5 requires Transformers 5.3, while the repository's legacy OpenVLA path uses an older Transformers version. The RL algorithm and trainer remain SimpleVLA-RL's existing veRL/GRPO-PPO path; the integration supplies model loading, multimodal prompting, discrete rollout responses, log-probability recomputation, and portable checkpoint saving.
This is a robotics policy, not a text-generation checkpoint and not a drop-in
AutoModel model. Use it only in a compatible simulator/runtime and validate
actions and safety constraints before any real-robot deployment.