Adapters
t5
legacy107 commited on
Commit
33a941b
1 Parent(s): 3301019

Upload T5ForConditionalGeneration

Browse files
README.md ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - t5
4
+ - adapter-transformers
5
+ datasets:
6
+ - minh21/cpgQA-v1.0-unique-context-test-10-percent-validation-10-percent
7
+ ---
8
+
9
+ # Adapter `legacy107/adapter-flan-t5-large-bottleneck-16-ia3-cpgQA` for legacy107/flan-t5-large-ia3-cpgQA-merged
10
+
11
+ An [adapter](https://adapterhub.ml) for the `legacy107/flan-t5-large-ia3-cpgQA-merged` model that was trained on the [minh21/cpgQA-v1.0-unique-context-test-10-percent-validation-10-percent](https://huggingface.co/datasets/minh21/cpgQA-v1.0-unique-context-test-10-percent-validation-10-percent/) dataset.
12
+
13
+ This adapter was created for usage with the **[adapter-transformers](https://github.com/Adapter-Hub/adapter-transformers)** library.
14
+
15
+ ## Usage
16
+
17
+ First, install `adapter-transformers`:
18
+
19
+ ```
20
+ pip install -U adapter-transformers
21
+ ```
22
+ _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)_
23
+
24
+ Now, the adapter can be loaded and activated like this:
25
+
26
+ ```python
27
+ from transformers import AutoAdapterModel
28
+
29
+ model = AutoAdapterModel.from_pretrained("legacy107/flan-t5-large-ia3-cpgQA-merged")
30
+ adapter_name = model.load_adapter("legacy107/adapter-flan-t5-large-bottleneck-16-ia3-cpgQA", source="hf", set_active=True)
31
+ ```
32
+
33
+ ## Architecture & Training
34
+
35
+ <!-- Add some description here -->
36
+
37
+ ## Evaluation results
38
+
39
+ <!-- Add some description here -->
40
+
41
+ ## Citation
42
+
43
+ <!-- Add some description here -->
adapter_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": {
3
+ "adapter_residual_before_ln": false,
4
+ "cross_adapter": false,
5
+ "factorized_phm_W": true,
6
+ "factorized_phm_rule": false,
7
+ "hypercomplex_nonlinearity": "glorot-uniform",
8
+ "init_weights": "bert",
9
+ "inv_adapter": null,
10
+ "inv_adapter_reduction_factor": null,
11
+ "is_parallel": false,
12
+ "learn_phm": true,
13
+ "leave_out": [],
14
+ "ln_after": false,
15
+ "ln_before": false,
16
+ "mh_adapter": true,
17
+ "non_linearity": "swish",
18
+ "original_ln_after": true,
19
+ "original_ln_before": false,
20
+ "output_adapter": true,
21
+ "phm_bias": true,
22
+ "phm_c_init": "normal",
23
+ "phm_dim": 4,
24
+ "phm_init_range": 0.0001,
25
+ "phm_layer": false,
26
+ "phm_rank": 1,
27
+ "reduction_factor": 16,
28
+ "residual_before_ln": true,
29
+ "scaling": 1.0,
30
+ "shared_W_phm": false,
31
+ "shared_phm_rule": true,
32
+ "use_gating": false
33
+ },
34
+ "hidden_size": 1024,
35
+ "model_class": "T5ForConditionalGeneration",
36
+ "model_name": "legacy107/flan-t5-large-ia3-cpgQA-merged",
37
+ "model_type": "t5",
38
+ "name": "question_answering",
39
+ "version": "3.2.1"
40
+ }
head_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config": null,
3
+ "hidden_size": 1024,
4
+ "label2id": {
5
+ "LABEL_0": 0,
6
+ "LABEL_1": 1
7
+ },
8
+ "model_class": "T5ForConditionalGeneration",
9
+ "model_name": "legacy107/flan-t5-large-ia3-cpgQA-merged",
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 sha256:9746a2632d851da9d124c38927d1d56d6a1cc665828d457983c3deb79d54e308
3
+ size 50890833
pytorch_model_head.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdb5464bf1c6913a7a4b42eaceb34922625395282f520135121f9e769da254d5
3
+ size 131597132