Hugging Face's logo

mewbot97
/
Intent2Action-glimmer-programs

Robotics
PEFT
Safetensors
program-synthesis
lora
qlora
manipulation
Model card Files
xet
 Community
mewbot97 commited on
Commit
5ec6b97
路
verified 路
1 Parent(s): d3b4fdc

Rename to Intent2Action

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -5,11 +5,11 @@ library_name: peft
5
  tags: [robotics, program-synthesis, lora, qlora, manipulation]
6
  ---
7
 
8
- # show-once 路 Glimmer program writer (G1b)
9
 
10
  A QLoRA adapter for [Muse Glimmer 30B](https://huggingface.co/meta-models/Muse-Glimmer-30B). Given a task intent
11
  (explicit rules such as "every cube into the red box") and the robot's object list, it writes a short, checkable
12
- Python program against the robot API of [intent-to-motion](https://github.com/allwinlucious/intent-to-motion): `find`,
13
  `find_all`, `pick`, `place`, `verify`, and so on. The program is checked, dry-run and executed by the robot stack.
14
  The model never issues motions itself.
15
 
 
5
  tags: [robotics, program-synthesis, lora, qlora, manipulation]
6
  ---
7
 
8
+ # Intent2Action 路 Glimmer program writer (G1b)
9
 
10
  A QLoRA adapter for [Muse Glimmer 30B](https://huggingface.co/meta-models/Muse-Glimmer-30B). Given a task intent
11
  (explicit rules such as "every cube into the red box") and the robot's object list, it writes a short, checkable
12
+ Python program against the robot API of [Intent2Action](https://github.com/allwinlucious/Intent2Action): `find`,
13
  `find_all`, `pick`, `place`, `verify`, and so on. The program is checked, dry-run and executed by the robot stack.
14
  The model never issues motions itself.
15