Update README.md
Browse files
README.md
CHANGED
@@ -4,21 +4,27 @@ datasets:
|
|
4 |
- allenai/scirepeval
|
5 |
---
|
6 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
**Dec 2023 Update:**
|
8 |
|
9 |
Model usage updated to be compatible with latest versions of transformers and adapters (newly released update to adapter-transformers) libraries.
|
10 |
|
11 |
-
|
12 |
**\*\*\*\*\*\*Update\*\*\*\*\*\***
|
13 |
|
14 |
This update introduces a new set of SPECTER2 models with the base transformer encoder pre-trained on an extended citation dataset containing more recent papers.
|
15 |
For benchmarking purposes please use the existing SPECTER2 [models](https://huggingface.co/allenai/specter2) w/o the **aug2023refresh** suffix.
|
16 |
|
17 |
-
# SPECTER2 (Base)
|
18 |
-
SPECTER2 is the successor to [SPECTER](https://huggingface.co/allenai/specter) and is capable of generating task specific embeddings for scientific tasks when paired with [adapters](https://huggingface.co/models?search=allenai/specter-2_).
|
19 |
-
This is the base model to be used along with the adapters.
|
20 |
-
Given the combination of title and abstract of a scientific paper or a short texual query, the model can be used to generate effective embeddings to be used in downstream applications.
|
21 |
-
|
22 |
**Note:For general embedding purposes, please use [allenai/specter2](https://huggingface.co/allenai/specter2).**
|
23 |
|
24 |
**To get the best performance on a downstream task type please load the associated adapter with the base model as in the example below.**
|
|
|
4 |
- allenai/scirepeval
|
5 |
---
|
6 |
|
7 |
+
## SPECTER2
|
8 |
+
|
9 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
10 |
+
|
11 |
+
SPECTER2 is a family of models that succeeds [SPECTER](https://huggingface.co/allenai/specter) and is capable of generating task specific embeddings for scientific tasks when paired with [adapters](https://huggingface.co/models?search=allenai/specter-2_).
|
12 |
+
This is the base encoder to be used with relevant task specific adapters.
|
13 |
+
Given the combination of title and abstract of a scientific paper or a short texual query, the model can be used to generate effective embeddings to be used in downstream applications.
|
14 |
+
|
15 |
+
**Note:For general embedding purposes, please use [allenai/specter2](https://huggingface.co/allenai/specter2).**
|
16 |
+
|
17 |
+
**To get the best performance on a downstream task type please load the associated adapter () with the base model as in the example below.**
|
18 |
+
|
19 |
**Dec 2023 Update:**
|
20 |
|
21 |
Model usage updated to be compatible with latest versions of transformers and adapters (newly released update to adapter-transformers) libraries.
|
22 |
|
|
|
23 |
**\*\*\*\*\*\*Update\*\*\*\*\*\***
|
24 |
|
25 |
This update introduces a new set of SPECTER2 models with the base transformer encoder pre-trained on an extended citation dataset containing more recent papers.
|
26 |
For benchmarking purposes please use the existing SPECTER2 [models](https://huggingface.co/allenai/specter2) w/o the **aug2023refresh** suffix.
|
27 |
|
|
|
|
|
|
|
|
|
|
|
28 |
**Note:For general embedding purposes, please use [allenai/specter2](https://huggingface.co/allenai/specter2).**
|
29 |
|
30 |
**To get the best performance on a downstream task type please load the associated adapter with the base model as in the example below.**
|