Instructions to use pravsels/molmoact2_tool_insert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LeRobot
How to use pravsels/molmoact2_tool_insert with LeRobot:
- Notebooks
- Google Colab
- Kaggle
Add model card
Browse files
README.md
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: lerobot
|
| 3 |
+
tags:
|
| 4 |
+
- molmoact2
|
| 5 |
+
- robotics
|
| 6 |
+
- lerobot
|
| 7 |
+
- vla
|
| 8 |
+
base_model: allenai/MolmoAct2
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# molmoact2_tool_insert
|
| 12 |
+
|
| 13 |
+
Fine-tuned [MolmoAct2](https://huggingface.co/allenai/MolmoAct2) (action-expert-only) on SO101 data.
|
| 14 |
+
|
| 15 |
+
| | |
|
| 16 |
+
|---|---|
|
| 17 |
+
| **Base model** | [allenai/MolmoAct2](https://huggingface.co/allenai/MolmoAct2) |
|
| 18 |
+
| **Dataset** | [villekuosmanen/armnetbench_tool_insert](https://huggingface.co/datasets/villekuosmanen/armnetbench_tool_insert) |
|
| 19 |
+
| **Task** | `tool_insert` |
|
| 20 |
+
| **Training** | Vast.ai H100 SXM, batch 64, bf16, gradient checkpointing |
|
| 21 |
+
| **W&B project** | [molmoact2_tool_insert](https://wandb.ai/pravsels/molmoact2_tool_insert) |
|
| 22 |
+
| **W&B run** | [8m94f03c](https://wandb.ai/pravsels/molmoact2_tool_insert/runs/8m94f03c) |
|
| 23 |
+
|
| 24 |
+
## Checkpoints
|
| 25 |
+
|
| 26 |
+
| Step | Path |
|
| 27 |
+
|------|------|
|
| 28 |
+
| 006000 | `checkpoints/006000/pretrained_model/` |
|
| 29 |
+
| 004000 | `checkpoints/004000/pretrained_model/` |
|
| 30 |
+
|
| 31 |
+
## Usage
|
| 32 |
+
|
| 33 |
+
```python
|
| 34 |
+
from lerobot.policies.molmoact2.modeling_molmoact2 import MolmoAct2Policy
|
| 35 |
+
policy = MolmoAct2Policy.from_pretrained("pravsels/molmoact2_tool_insert", revision="main")
|
| 36 |
+
```
|