Push model using huggingface_hub.
Browse files- README.md +6 -11
- config.json +6 -6
- training_config.json +32 -1
README.md
CHANGED
|
@@ -1,15 +1,10 @@
|
|
| 1 |
---
|
| 2 |
-
language: en
|
| 3 |
-
license: mit
|
| 4 |
tags:
|
| 5 |
-
-
|
| 6 |
-
-
|
| 7 |
---
|
| 8 |
|
| 9 |
-
#
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
## Usage
|
| 14 |
-
```python
|
| 15 |
-
model = HFPerturbationTFModel.from_pretrained('weililab/pertTF-small')
|
|
|
|
| 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:
|
| 8 |
+
- Code: [More Information Needed]
|
| 9 |
+
- Paper: [More Information Needed]
|
| 10 |
+
- Docs: [More Information Needed]
|
|
|
|
|
|
|
|
|
config.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"cell_emb_style": "cls",
|
| 3 |
-
"d_hid":
|
| 4 |
-
"d_model":
|
| 5 |
"do_dab": false,
|
| 6 |
-
"do_mvc":
|
| 7 |
"domain_spec_batchnorm": false,
|
| 8 |
"dropout": 0.1,
|
| 9 |
"ecs_threshold": 0.7,
|
|
@@ -12,8 +12,8 @@
|
|
| 12 |
"input_emb_style": "continuous",
|
| 13 |
"mvc_decoder_style": "inner product",
|
| 14 |
"n_bins": 51,
|
| 15 |
-
"n_cls":
|
| 16 |
-
"n_pert":
|
| 17 |
"n_ps": 1,
|
| 18 |
"nhead": 4,
|
| 19 |
"nlayers": 4,
|
|
@@ -29,6 +29,6 @@
|
|
| 29 |
"pred_lochness_next": false,
|
| 30 |
"ps_decoder2_nlayer": 3,
|
| 31 |
"use_batch_labels": false,
|
| 32 |
-
"use_fast_transformer":
|
| 33 |
"vocab": null
|
| 34 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"cell_emb_style": "cls",
|
| 3 |
+
"d_hid": 64,
|
| 4 |
+
"d_model": 64,
|
| 5 |
"do_dab": false,
|
| 6 |
+
"do_mvc": true,
|
| 7 |
"domain_spec_batchnorm": false,
|
| 8 |
"dropout": 0.1,
|
| 9 |
"ecs_threshold": 0.7,
|
|
|
|
| 12 |
"input_emb_style": "continuous",
|
| 13 |
"mvc_decoder_style": "inner product",
|
| 14 |
"n_bins": 51,
|
| 15 |
+
"n_cls": 20,
|
| 16 |
+
"n_pert": 40,
|
| 17 |
"n_ps": 1,
|
| 18 |
"nhead": 4,
|
| 19 |
"nlayers": 4,
|
|
|
|
| 29 |
"pred_lochness_next": false,
|
| 30 |
"ps_decoder2_nlayer": 3,
|
| 31 |
"use_batch_labels": false,
|
| 32 |
+
"use_fast_transformer": true,
|
| 33 |
"vocab": null
|
| 34 |
}
|
training_config.json
CHANGED
|
@@ -49,5 +49,36 @@
|
|
| 49 |
"hvg_col": "highly_variable",
|
| 50 |
"mvc_masked_train": true,
|
| 51 |
"max_seq_len": 3001,
|
| 52 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
}
|
|
|
|
| 49 |
"hvg_col": "highly_variable",
|
| 50 |
"mvc_masked_train": true,
|
| 51 |
"max_seq_len": 3001,
|
| 52 |
+
"n_pert": 40,
|
| 53 |
+
"nlayers_pert": 4,
|
| 54 |
+
"n_ps": 1,
|
| 55 |
+
"ntoken": 36604,
|
| 56 |
+
"d_model": 64,
|
| 57 |
+
"nhead": 4,
|
| 58 |
+
"d_hid": 64,
|
| 59 |
+
"nlayers": 4,
|
| 60 |
+
"nlayers_cls": 3,
|
| 61 |
+
"n_cls": 20,
|
| 62 |
+
"vocab": null,
|
| 63 |
+
"dropout": 0.1,
|
| 64 |
+
"pad_token": "<pad>",
|
| 65 |
+
"pad_value": -2,
|
| 66 |
+
"do_mvc": true,
|
| 67 |
+
"do_dab": false,
|
| 68 |
+
"use_batch_labels": false,
|
| 69 |
+
"num_batch_labels": null,
|
| 70 |
+
"domain_spec_batchnorm": false,
|
| 71 |
+
"input_emb_style": "continuous",
|
| 72 |
+
"n_bins": 51,
|
| 73 |
+
"cell_emb_style": "cls",
|
| 74 |
+
"mvc_decoder_style": "inner product",
|
| 75 |
+
"ecs_threshold": 0.7,
|
| 76 |
+
"explicit_zero_prob": true,
|
| 77 |
+
"use_fast_transformer": true,
|
| 78 |
+
"fast_transformer_backend": "flash",
|
| 79 |
+
"pre_norm": false,
|
| 80 |
+
"pred_lochness_next": false,
|
| 81 |
+
"ps_decoder2_nlayer": 3,
|
| 82 |
+
"pert_pad_id": null,
|
| 83 |
+
"pert_dim": null
|
| 84 |
}
|