Upload T5ForConditionalGeneration
Browse files- README.md +44 -0
- adapter_config.json +24 -0
- head_config.json +14 -0
- pytorch_adapter.bin +3 -0
- pytorch_model_head.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- adapter-transformers
|
| 4 |
+
- t5
|
| 5 |
+
- adapterhub:self-explanations
|
| 6 |
+
datasets:
|
| 7 |
+
- self-explanations
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# Adapter `nbogdan/bdn-se-flan_adapters` for google/flan-t5-small
|
| 11 |
+
|
| 12 |
+
An [adapter](https://adapterhub.ml) for the `google/flan-t5-small` model that was trained on the [self-explanations](https://adapterhub.ml/explore/self-explanations/) dataset.
|
| 13 |
+
|
| 14 |
+
This adapter was created for usage with the **[adapter-transformers](https://github.com/Adapter-Hub/adapter-transformers)** library.
|
| 15 |
+
|
| 16 |
+
## Usage
|
| 17 |
+
|
| 18 |
+
First, install `adapter-transformers`:
|
| 19 |
+
|
| 20 |
+
```
|
| 21 |
+
pip install -U adapter-transformers
|
| 22 |
+
```
|
| 23 |
+
_Note: adapter-transformers is a fork of transformers that acts as a drop-in replacement with adapter support. [More](https://docs.adapterhub.ml/installation.html)_
|
| 24 |
+
|
| 25 |
+
Now, the adapter can be loaded and activated like this:
|
| 26 |
+
|
| 27 |
+
```python
|
| 28 |
+
from transformers import AutoAdapterModel
|
| 29 |
+
|
| 30 |
+
model = AutoAdapterModel.from_pretrained("google/flan-t5-small")
|
| 31 |
+
adapter_name = model.load_adapter("nbogdan/bdn-se-flan_adapters", source="hf", set_active=True)
|
| 32 |
+
```
|
| 33 |
+
|
| 34 |
+
## Architecture & Training
|
| 35 |
+
|
| 36 |
+
<!-- Add some description here -->
|
| 37 |
+
|
| 38 |
+
## Evaluation results
|
| 39 |
+
|
| 40 |
+
<!-- Add some description here -->
|
| 41 |
+
|
| 42 |
+
## Citation
|
| 43 |
+
|
| 44 |
+
<!-- Add some description here -->
|
adapter_config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"config": {
|
| 3 |
+
"alpha": 16,
|
| 4 |
+
"architecture": "lora",
|
| 5 |
+
"attn_matrices": [
|
| 6 |
+
"q",
|
| 7 |
+
"v"
|
| 8 |
+
],
|
| 9 |
+
"composition_mode": "add",
|
| 10 |
+
"dropout": 0.0,
|
| 11 |
+
"init_weights": "lora",
|
| 12 |
+
"intermediate_lora": true,
|
| 13 |
+
"output_lora": true,
|
| 14 |
+
"r": 8,
|
| 15 |
+
"selfattn_lora": true,
|
| 16 |
+
"use_gating": false
|
| 17 |
+
},
|
| 18 |
+
"hidden_size": 512,
|
| 19 |
+
"model_class": "T5ForConditionalGeneration",
|
| 20 |
+
"model_name": "google/flan-t5-small",
|
| 21 |
+
"model_type": "t5",
|
| 22 |
+
"name": "flant5-small-1bs-0ex-overall",
|
| 23 |
+
"version": "3.2.1"
|
| 24 |
+
}
|
head_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"config": null,
|
| 3 |
+
"hidden_size": 512,
|
| 4 |
+
"label2id": {
|
| 5 |
+
"LABEL_0": 0,
|
| 6 |
+
"LABEL_1": 1
|
| 7 |
+
},
|
| 8 |
+
"model_class": "T5ForConditionalGeneration",
|
| 9 |
+
"model_name": "google/flan-t5-small",
|
| 10 |
+
"model_type": "t5",
|
| 11 |
+
"name": null,
|
| 12 |
+
"num_labels": 2,
|
| 13 |
+
"version": "3.2.1"
|
| 14 |
+
}
|
pytorch_adapter.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f1b510699908e2ba5bab130dc1f5e817a63d75bb09d33a1fdbf40be542c723c
|
| 3 |
+
size 3009937
|
pytorch_model_head.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:baa3fb1bcb6ce07ab9ce30520eb8c9d6bdef4115e37a1512a5bf99f289bf1d4f
|
| 3 |
+
size 65798988
|