Instructions to use Haongchen/MemoryVLA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Piper
How to use Haongchen/MemoryVLA with Piper:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Fix default checkpoint layout for direct loading
Browse files
README.md
CHANGED
|
@@ -21,7 +21,7 @@ organized so that additional real-world task checkpoints can be added under
|
|
| 21 |
The current default checkpoint is:
|
| 22 |
|
| 23 |
```text
|
| 24 |
-
checkpoints/
|
| 25 |
```
|
| 26 |
|
| 27 |
It is the EMA action-diffusion checkpoint from the Frozen+EMA training run.
|
|
@@ -150,8 +150,7 @@ pipeline.
|
|
| 150 |
|
| 151 |
```text
|
| 152 |
checkpoints/
|
| 153 |
-
|
| 154 |
-
frozen-ema-step-20000.pt
|
| 155 |
configs/
|
| 156 |
piper-color-sorting/
|
| 157 |
config.yaml
|
|
@@ -163,7 +162,6 @@ Future tasks should use a separate directory, for example:
|
|
| 163 |
|
| 164 |
```text
|
| 165 |
checkpoints/
|
| 166 |
-
piper-color-sorting/
|
| 167 |
drawer-opening/
|
| 168 |
peg-insertion/
|
| 169 |
configs/
|
|
|
|
| 21 |
The current default checkpoint is:
|
| 22 |
|
| 23 |
```text
|
| 24 |
+
checkpoints/frozen-ema-step-20000.pt
|
| 25 |
```
|
| 26 |
|
| 27 |
It is the EMA action-diffusion checkpoint from the Frozen+EMA training run.
|
|
|
|
| 150 |
|
| 151 |
```text
|
| 152 |
checkpoints/
|
| 153 |
+
frozen-ema-step-20000.pt
|
|
|
|
| 154 |
configs/
|
| 155 |
piper-color-sorting/
|
| 156 |
config.yaml
|
|
|
|
| 162 |
|
| 163 |
```text
|
| 164 |
checkpoints/
|
|
|
|
| 165 |
drawer-opening/
|
| 166 |
peg-insertion/
|
| 167 |
configs/
|