Push model using huggingface_hub.
Browse files- README.md +2 -8
- config.json +1 -6
README.md
CHANGED
|
@@ -1,13 +1,7 @@
|
|
| 1 |
---
|
| 2 |
-
license: cc-by-nc-4.0
|
| 3 |
-
pipeline_tag: time-series-forecasting
|
| 4 |
tags:
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
- pretrained models
|
| 8 |
-
- foundation models
|
| 9 |
-
- time series foundation models
|
| 10 |
-
- time-series
|
| 11 |
---
|
| 12 |
|
| 13 |
This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
tags:
|
| 3 |
+
- model_hub_mixin
|
| 4 |
+
- pytorch_model_hub_mixin
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
---
|
| 6 |
|
| 7 |
This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
|
config.json
CHANGED
|
@@ -1,7 +1,5 @@
|
|
| 1 |
{
|
| 2 |
"attn_dropout_p": 0.0,
|
| 3 |
-
"aux_loss_weight": 0.0,
|
| 4 |
-
"clusters_path": null,
|
| 5 |
"d_ff": 512,
|
| 6 |
"d_model": 384,
|
| 7 |
"distr_output": {
|
|
@@ -24,12 +22,9 @@
|
|
| 24 |
},
|
| 25 |
"dropout_p": 0.0,
|
| 26 |
"max_seq_len": 512,
|
| 27 |
-
"num_experts": 32,
|
| 28 |
-
"num_experts_per_token": 2,
|
| 29 |
"num_layers": 6,
|
| 30 |
"patch_sizes": [
|
| 31 |
16
|
| 32 |
],
|
| 33 |
-
"scaling": true
|
| 34 |
-
"use_clusters": true
|
| 35 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"attn_dropout_p": 0.0,
|
|
|
|
|
|
|
| 3 |
"d_ff": 512,
|
| 4 |
"d_model": 384,
|
| 5 |
"distr_output": {
|
|
|
|
| 22 |
},
|
| 23 |
"dropout_p": 0.0,
|
| 24 |
"max_seq_len": 512,
|
|
|
|
|
|
|
| 25 |
"num_layers": 6,
|
| 26 |
"patch_sizes": [
|
| 27 |
16
|
| 28 |
],
|
| 29 |
+
"scaling": true
|
|
|
|
| 30 |
}
|