TeleEmbodied
/

PRTS-4B

feature-extraction

vision-language-action

contrastive-reinforcement-learning

goal-conditioned-rl

Model card Files Files and versions

breezeyoung commited on 6 days ago

Commit

c9b60a0

·

verified ·

1 Parent(s): 922b63e

Update README.md

Files changed (1) hide show

README.md +0 -1

README.md CHANGED Viewed

@@ -90,7 +90,6 @@ PRTS expects a **single user turn** containing camera images, a discretized prop
 | `<\|im_start\|>` `<\|im_end\|>` | Qwen-style turn delimiters |
 | `<\|vision_start\|>` `<\|image_pad\|>` `<\|vision_end\|>` | One image placeholder block per camera |
 | `<\|goal_repr\|>` | CRL value-head anchor tokens |
-| `<\|action_start\|>` `<\|action_pad\|>` `<\|action_end\|>` | Slot the action expert fills with the predicted action chunk token |
 ### Layout of one rollout step

 | `<\|im_start\|>` `<\|im_end\|>` | Qwen-style turn delimiters |
 | `<\|vision_start\|>` `<\|image_pad\|>` `<\|vision_end\|>` | One image placeholder block per camera |
 | `<\|goal_repr\|>` | CRL value-head anchor tokens |
 ### Layout of one rollout step