Update README.md
#4
by
heloise-chomet
- opened
README.md
CHANGED
|
@@ -9,7 +9,7 @@ Nature Communications, 13(1), May 2022. ISSN: 2041-1723. URL: https://dx.doi.org
|
|
| 9 |
|
| 10 |
## How to Use
|
| 11 |
|
| 12 |
-
For complete usage instructions, please refer to our [documentation](https://
|
| 13 |
|
| 14 |
## Model architecture
|
| 15 |
| Parameter | Value | Description |
|
|
@@ -27,7 +27,7 @@ For complete usage instructions, please refer to our [documentation](https://ins
|
|
| 27 |
| `avg_um_neighbors` | `None` | Mean number of neighbors. |
|
| 28 |
|
| 29 |
For more information about NequIP hyperparameters,
|
| 30 |
-
please refer to our [documentation](https://
|
| 31 |
|
| 32 |
## Training
|
| 33 |
|
|
@@ -49,7 +49,7 @@ We use our default MLIP optimizer in v1.0.0 with the following settings:
|
|
| 49 |
| `num_gradient_accumulation_steps`| `1` | Steps to accumulate before taking an optimizer step. |
|
| 50 |
|
| 51 |
For more information about the optimizer,
|
| 52 |
-
please refer to our [documentation](https://
|
| 53 |
## Dataset
|
| 54 |
| Parameter | Value | Description |
|
| 55 |
|-----------------------------|-------|--------------------------------------------|
|
|
@@ -60,7 +60,7 @@ please refer to our [documentation](https://instadeep.github.io/mlip/api_referen
|
|
| 60 |
|
| 61 |
This model was trained on the [SPICE2_curated dataset](https://huggingface.co/datasets/InstaDeepAI/SPICE2-curated).
|
| 62 |
For more information about dataset configuration
|
| 63 |
-
please refer to our [documentation](https://
|
| 64 |
## License summary
|
| 65 |
|
| 66 |
1. The Licensed Models are **only** available under this License for Non-Commercial Purposes.
|
|
|
|
| 9 |
|
| 10 |
## How to Use
|
| 11 |
|
| 12 |
+
For complete usage instructions, please refer to our [documentation](https://instadeepai.github.io/mlip)
|
| 13 |
|
| 14 |
## Model architecture
|
| 15 |
| Parameter | Value | Description |
|
|
|
|
| 27 |
| `avg_um_neighbors` | `None` | Mean number of neighbors. |
|
| 28 |
|
| 29 |
For more information about NequIP hyperparameters,
|
| 30 |
+
please refer to our [documentation](https://instadeepai.github.io/mlip/api_reference/models/nequip.html#mlip.models.nequip.config.NequipConfig)
|
| 31 |
|
| 32 |
## Training
|
| 33 |
|
|
|
|
| 49 |
| `num_gradient_accumulation_steps`| `1` | Steps to accumulate before taking an optimizer step. |
|
| 50 |
|
| 51 |
For more information about the optimizer,
|
| 52 |
+
please refer to our [documentation](https://instadeepai.github.io/mlip/api_reference/training/optimizer.html#mlip.training.optimizer_config.OptimizerConfig)
|
| 53 |
## Dataset
|
| 54 |
| Parameter | Value | Description |
|
| 55 |
|-----------------------------|-------|--------------------------------------------|
|
|
|
|
| 60 |
|
| 61 |
This model was trained on the [SPICE2_curated dataset](https://huggingface.co/datasets/InstaDeepAI/SPICE2-curated).
|
| 62 |
For more information about dataset configuration
|
| 63 |
+
please refer to our [documentation](https://instadeepai.github.io/mlip/api_reference/data/dataset_configs.html#mlip.data.configs.GraphDatasetBuilderConfig)
|
| 64 |
## License summary
|
| 65 |
|
| 66 |
1. The Licensed Models are **only** available under this License for Non-Commercial Purposes.
|