Update model card
Browse files
README.md
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: lerobot
|
| 3 |
+
tags:
|
| 4 |
+
- molmoact2
|
| 5 |
+
- robotics
|
| 6 |
+
- lerobot
|
| 7 |
+
- vla
|
| 8 |
+
- bimanual
|
| 9 |
+
base_model: allenai/MolmoAct2
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# molmoact2_insert_candle_quantile_norm_fix_25k
|
| 13 |
+
|
| 14 |
+
Fine-tuned [MolmoAct2](https://huggingface.co/allenai/MolmoAct2) (action-expert-only) for `insert_candle` on SO101 data.
|
| 15 |
+
|
| 16 |
+
| | |
|
| 17 |
+
|---|---|
|
| 18 |
+
| **Policy** | MolmoAct2 (`policy.type=molmoact2`) |
|
| 19 |
+
| **Init checkpoint** | [allenai/MolmoAct2](https://huggingface.co/allenai/MolmoAct2) |
|
| 20 |
+
| **Dataset** | [villekuosmanen/armnetbench_insert_candle](https://huggingface.co/datasets/villekuosmanen/armnetbench_insert_candle) |
|
| 21 |
+
| **Task** | `insert_candle` |
|
| 22 |
+
| **Action dim** | 12 (bimanual) |
|
| 23 |
+
| **Cameras** | `top`, `left_wrist`, `right_wrist` |
|
| 24 |
+
| **Training** | 25k steps, QUANTILES norm, freeze, batch 32 global, Isambard GH200 |
|
| 25 |
+
| **Prior HF repo** | [pravsels/molmoact2_insert_candle](https://huggingface.co/pravsels/molmoact2_insert_candle) |
|
| 26 |
+
| **W&B project** | [molmoact2_insert_candle_quantile_norm_fix_25k](https://wandb.ai/pravsels/molmoact2_insert_candle_quantile_norm_fix_25k) |
|
| 27 |
+
| **W&B run** | [b07rlk7i](https://wandb.ai/pravsels/molmoact2_insert_candle_quantile_norm_fix_25k/runs/b07rlk7i) |
|
| 28 |
+
|
| 29 |
+
## Checkpoints
|
| 30 |
+
|
| 31 |
+
The checkpoint (local step `025000`, 25k training steps) lives at the **repository root** for direct loading.
|
| 32 |
+
|
| 33 |
+
|
| 34 |
+
## Verification
|
| 35 |
+
|
| 36 |
+
| **Checkpoint step** | `025000` |
|
| 37 |
+
| **Source path** | `checkpoints/025000/pretrained_model/` |
|
| 38 |
+
| **model.safetensors** | 10,884,573,720 bytes, sha256 `af86903eebd5c089c4e74c694db6345671569d38e23da12840159744e8f4b593` |
|
| 39 |
+
| **policy_preprocessor.json** | 2,523 bytes, sha256 `aac2ee4e61c26a5322c9b3e2f727ce060c90071e012185d9f39cceb2d43ea04a` |
|
| 40 |
+
| **policy_postprocessor.json** | 758 bytes, sha256 `8690a8e7015281571c9de7d88073b302cd03123e5f677ea582c669dbf014e7ad` |
|
| 41 |
+
| **train_config.json** | 8,836 bytes, sha256 `2ac88bc6f39c14eb153b6dd8a59e6686a51e1d2c2647206573d8dde433c82d1f` |
|
| 42 |
+
|
| 43 |
+
Verify after download:
|
| 44 |
+
|
| 45 |
+
```bash
|
| 46 |
+
sha256sum model.safetensors
|
| 47 |
+
# expected: af86903eebd5c089c4e74c694db6345671569d38e23da12840159744e8f4b593
|
| 48 |
+
```
|
| 49 |
+
|
| 50 |
+
## Usage
|
| 51 |
+
|
| 52 |
+
```python
|
| 53 |
+
from lerobot.policies.molmoact2.modeling_molmoact2 import MolmoAct2Policy
|
| 54 |
+
policy = MolmoAct2Policy.from_pretrained("pravsels/molmoact2_insert_candle_quantile_norm_fix_25k")
|
| 55 |
+
```
|