Hugging Face's logo

SimpleJev
/
JevAny-Robotics-4B-LoRA

Robotics
PEFT
Safetensors
jevany
lora
decision-model
pointer
reward-model
judge
calibration
conformal-prediction
Model card Files
xet
 Community
HuanxinSheng commited on
Commit
e25ce9f
·
verified ·
1 Parent(s): 5b4e444

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -33,7 +33,7 @@ failure localisation, trajectory preference), built only from train-side splits
33
 
34
  | Model | Size | RoboPulse acc ↑ | RoboPulse AUROC ↑ | RoboPulse++ AUROC ↑ | RoboPulse++ bal. acc ↑ | RoboRewardBench MAE ↓ | JevJudge-Robotics skill_role ↑ |
35
  |---|---:|---:|---:|---:|---:|---:|---:|
36
- | **JevAny-4B-RoboJudge (this model)** | 4B | **71.1** | **0.806** | **0.728** | **65.9** | **0.443** | 0.567 |
37
  | JevAny-Qwen3.5-4B-LoRA (parent) | 4B | 52.7 | 0.588 | 0.641 | 59.1 | 1.057 | 0.149 |
38
  | Qwen3.5-4B zero-shot (constrained choice) | 4B | 49.9 | 0.519 | 0.592 | 50.0 | 1.261 | 0.203 |
39
  | OneJev-4B | 4B | 53.9 | 0.586 | 0.617 | 58.3 | 1.005 | 0.425 |
 
33
 
34
  | Model | Size | RoboPulse acc ↑ | RoboPulse AUROC ↑ | RoboPulse++ AUROC ↑ | RoboPulse++ bal. acc ↑ | RoboRewardBench MAE ↓ | JevJudge-Robotics skill_role ↑ |
35
  |---|---:|---:|---:|---:|---:|---:|---:|
36
+ | **JevAny-Robotics-4B-LoRA (this model)** | 4B | **71.1** | **0.806** | **0.728** | **65.9** | **0.443** | 0.567 |
37
  | JevAny-Qwen3.5-4B-LoRA (parent) | 4B | 52.7 | 0.588 | 0.641 | 59.1 | 1.057 | 0.149 |
38
  | Qwen3.5-4B zero-shot (constrained choice) | 4B | 49.9 | 0.519 | 0.592 | 50.0 | 1.261 | 0.203 |
39
  | OneJev-4B | 4B | 53.9 | 0.586 | 0.617 | 58.3 | 1.005 | 0.425 |